Change search
Refine search result
12 1 - 50 of 59
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1. Andersson, Malin
    et al.
    Jägervall, Karl
    Eriksson, Per
    Persson, Anders
    Granerus, Göran
    Wang, Chunliang
    Linköping Univ, Sweden.
    Smedby, Örjan
    Linköping Univ, Sweden.
    How to measure renal artery stenosis - a retrospective comparison of morphological measurement approaches in relation to hemodynamic significance2015In: BMC Medical Imaging, ISSN 1471-2342, E-ISSN 1471-2342, Vol. 15, article id 42Article in journal (Refereed)
    Abstract [en]

    Background: Although it is well known that renal artery stenosis may cause renovascular hypertension, it is unclear how the degree of stenosis should best be measured in morphological images. The aim of this study was to determine which morphological measures from Computed Tomography Angiography (CTA) and Magnetic Resonance Angiography (MRA) are best in predicting whether a renal artery stenosis is hemodynamically significant or not. Methods: Forty-seven patients with hypertension and a clinical suspicion of renovascular hypertension were examined with CTA, MRA, captopril-enhanced renography (CER) and captopril test (Ctest). CTA and MRA images of the renal arteries were analyzed by two readers using interactive vessel segmentation software. The measures included minimum diameter, minimum area, diameter reduction and area reduction. In addition, two radiologists visually judged the diameter reduction without automated segmentation. The results were then compared using limits of agreement and intra-class correlation, and correlated with the results from CER combined with Ctest (which were used as standard of reference) using receiver operating characteristics (ROC) analysis. Results: A total of 68 kidneys had all three investigations (CTA, MRA and CER + Ctest), where 11 kidneys (16.2 %) got a positive result on the CER + Ctest. The greatest area under ROC curve (AUROC) was found for the area reduction on MRA, with a value of 0.91 (95 % confidence interval 0.82-0.99), excluding accessory renal arteries. As comparison, the AUROC for the radiologists' visual assessments on CTA and MRA were 0.90 (0.82-0.98) and 0.91 (0.83-0.99) respectively. None of the differences were statistically significant. Conclusions: No significant differences were found between the morphological measures in their ability to predict hemodynamically significant stenosis, but a tendency of MRA having higher AUROC than CTA. There was no significant difference between measurements made by the radiologists and measurements made with fuzzy connectedness segmentation. Further studies are required to definitely identify the optimal measurement approach.

  • 2.
    Astaraki, Mehdi
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Buizza, G.
    Toma-Dasu, I.
    Lazzeroni, M.
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Early survival prediction in non-small cell lung cancer with PET/CT size aware longitudinal pattern2019In: Radiotherapy and Oncology, ISSN 0167-8140, E-ISSN 1879-0887, Vol. 133, p. S208-S209Article in journal (Refereed)
  • 3.
    Astaraki, Mehdi
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging. Karolinska Inst, Dept Oncol Pathol, Karolinska Univ Sjukhuset, SE-17176 Stockholm, Sweden.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Buizza, Giulia
    Politecn Milan, Dept Elect Informat & Bioengn, Piazza Leonardo da Vinci 42, I-20133 Milan, Italy..
    Toma-Dasu, Iuliana
    Karolinska Inst, Dept Oncol Pathol, Karolinska Univ Sjukhuset, SE-17176 Stockholm, Sweden.;Stockholm Univ, Dept Phys, SE-10691 Stockholm, Sweden..
    Lazzeroni, Marta
    Karolinska Inst, Dept Oncol Pathol, Karolinska Univ Sjukhuset, SE-17176 Stockholm, Sweden.;Stockholm Univ, Dept Phys, SE-10691 Stockholm, Sweden..
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Early survival prediction in non-small cell lung cancer from PET/CT images using an intra-tumor partitioning method2019In: Physica medica (Testo stampato), ISSN 1120-1797, E-ISSN 1724-191X, Vol. 60, p. 58-65Article in journal (Refereed)
    Abstract [en]

    Purpose: To explore prognostic and predictive values of a novel quantitative feature set describing intra-tumor heterogeneity in patients with lung cancer treated with concurrent and sequential chemoradiotherapy. Methods: Longitudinal PET-CT images of 30 patients with non-small cell lung cancer were analysed. To describe tumor cell heterogeneity, the tumors were partitioned into one to ten concentric regions depending on their sizes, and, for each region, the change in average intensity between the two scans was calculated for PET and CT images separately to form the proposed feature set. To validate the prognostic value of the proposed method, radiomics analysis was performed and a combination of the proposed novel feature set and the classic radiomic features was evaluated. A feature selection algorithm was utilized to identify the optimal features, and a linear support vector machine was trained for the task of overall survival prediction in terms of area under the receiver operating characteristic curve (AUROC). Results: The proposed novel feature set was found to be prognostic and even outperformed the radiomics approach with a significant difference (AUROC(sALop) = 0.90 vs. AUROC(radiomic) = 0.71) when feature selection was not employed, whereas with feature selection, a combination of the novel feature set and radiomics led to the highest prognostic values. Conclusion: A novel feature set designed for capturing intra-tumor heterogeneity was introduced. Judging by their prognostic power, the proposed features have a promising potential for early survival prediction.

  • 4. Astaraki, Mehdi
    et al.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Buizza, Giulia
    Toma-Dasu, Iuliana
    Lazzeroni, Marta
    Smedby, Örjan
    Early survival prediction in non-small cell lung cancer from PET/CT images using an intra-tumor partitioning method2019In: Physica Medica, Vol. 60, p. 58-65Article in journal (Refereed)
  • 5. Bendazzoli, Simone
    et al.
    Brusini, Irene
    Damberg, Peter
    Smedby, Örjan
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Wang, Chunliang
    Automatic rat brain segmentation from MRI using statistical shape models and random forest2019Conference paper (Refereed)
  • 6. Bernard, Olivier
    et al.
    Bosch, J G
    Heyde, Brecht
    Alessandrini, Martino
    Barbosa, Daniel
    Camarasu-Pop, S
    Cervenansky, F
    Valette, S
    Mirea, O
    Bernier, M
    Jodoin, P M
    Domingos, J S
    Stebbing, R V
    Keraudren, K
    Oktay, O
    Caballero, J
    Shi, W
    Rueckert, D
    Milletari, F
    Ahmadi, S A
    Smistad, E
    Lindseth, F
    van Stralen, M
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Donal, E
    Monaghan, M
    Papachristidis, A
    Geleijnse, M L
    Galli, E
    Dhooge, Jan
    Standardized evaluation system for left ventricular segmentation algorithms in 3D echocardiography.2015In: IEEE Transactions on Medical Imaging, ISSN 0278-0062, E-ISSN 1558-254XArticle in journal (Refereed)
    Abstract [en]

    Real-time 3D Echocardiography (RT3DE) has been proven to be an accurate tool for left ventricular (LV) volume assessment. However, identification of the LV endocardium remains a challenging task, mainly because of the low tissue/blood contrast of the images combined with typical artifacts. Several semi and fully automatic algorithms have been proposed for segmenting the endocardium in RT3DE data in order to extract relevant clinical indices, but a systematic and fair comparison between such methods has so far been impossible due to the lack of a publicly available common database. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms developed to segment the LV border in RT3DE. A database consisting of 45 multivendor cardiac ultrasound recordings acquired at different centers with corresponding reference measurements from 3 experts are made available. The algorithms from nine research groups were quantitatively evaluated and compared using the proposed online platform. The results showed that the best methods produce promising results with respect to the experts' measurements for the extraction of clinical indices, and that they offer good segmentation precision in terms of mean distance error in the context of the experts' variability range. The platform remains open for new submissions.

  • 7.
    Brusini, Irene
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Carneiro, Miguel
    Univ Porto, Ctr Invest Biodiversidade & Recursos Genet CIBIO, InBIO, P-4485661 Vairao, Portugal.;Univ Porto, Dept Biol, Fac Ciencias, P-4169007 Porto, Portugal..
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Rubin, Carl-Johan
    Uppsala Univ, Sci Life Lab Uppsala, Dept Med Biochem & Microbiol, S-75236 Uppsala, Sweden..
    Ring, Henrik
    Uppsala Univ, Dept Neurosci, S-75236 Uppsala, Sweden..
    Afonso, Sandra
    Univ Porto, Ctr Invest Biodiversidade & Recursos Genet CIBIO, InBIO, P-4485661 Vairao, Portugal..
    Blanco-Aguiar, Jose A.
    Univ Porto, Ctr Invest Biodiversidade & Recursos Genet CIBIO, InBIO, P-4485661 Vairao, Portugal.;CSIC, Inst Invest Recursos Cineget IREC, Ciudad Real 13005, Spain.;UCLM, CSIC, Ciudad Real 13005, Spain..
    Ferrand, Nuno
    Univ Porto, Ctr Invest Biodiversidade & Recursos Genet CIBIO, InBIO, P-4485661 Vairao, Portugal.;Univ Porto, Dept Biol, Fac Ciencias, P-4169007 Porto, Portugal.;Univ Johannesburg, Dept Zool, ZA-2006 Auckland Pk, South Africa..
    Rafati, Nima
    Uppsala Univ, Sci Life Lab Uppsala, Dept Med Biochem & Microbiol, S-75236 Uppsala, Sweden..
    Villafuerte, Rafael
    CSIC, IESA, Cordoba 14004, Spain..
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Damberg, Peter
    Karolinska Univ Hosp, Karolinska Expt Res & Imaging Ctr, S-17176 Solna, Sweden..
    Hallbook, Finn
    Uppsala Univ, Dept Neurosci, S-75236 Uppsala, Sweden..
    Fredrikson, Mats
    Uppsala Univ, Dept Psychol, S-75236 Uppsala, Sweden.;Karolinska Inst, Dept Clin Neurosci, S-17177 Stockholm, Sweden..
    Andersson, Leif
    Uppsala Univ, Sci Life Lab Uppsala, Dept Med Biochem & Microbiol, S-75236 Uppsala, Sweden.;Texas A&M Univ, Coll Vet Med & Biomed Sci, Dept Vet Integrat Biosci, College Stn, TX 77843 USA.;Swedish Univ Agr Sci, Dept Anim Breeding & Genet, S-75007 Uppsala, Sweden..
    Changes in brain architecture are consistent with altered fear processing in domestic rabbits2018In: Proceedings of the National Academy of Sciences of the United States of America, ISSN 0027-8424, E-ISSN 1091-6490, Vol. 115, no 28, p. 7380-7385Article in journal (Refereed)
    Abstract [en]

    The most characteristic feature of domestic animals is their change in behavior associated with selection for tameness. Here we show, using high-resolution brain magnetic resonance imaging in wild and domestic rabbits, that domestication reduced amygdala volume and enlarged medial prefrontal cortex volume, supporting that areas driving fear have lost volume while areas modulating negative affect have gained volume during domestication. In contrast to the localized gray matter alterations, white matter anisotropy was reduced in the corona radiata, corpus callosum, and the subcortical white matter. This suggests a compromised white matter structural integrity in projection and association fibers affecting both afferent and efferent neural flow, consistent with reduced neural processing. We propose that compared with their wild ancestors, domestic rabbits are less fearful and have an attenuated flight response because of these changes in brain architecture.

  • 8.
    Buizza, Giulia
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems. Politecnico di Milano, CartCasLab, Department of Electronics Information and Bioengineering, piazza Leonardo Da Vinci 42, Milan 20133, Italy.
    Toma-Dasu, I.
    Lazzeroni, M.
    Paganelli, C.
    Riboldi, M.
    Chang, Yongjun
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems.
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Early tumor response prediction for lung cancer patients using novel longitudinal pattern features from sequential PET/CT image scans2018In: Physica medica (Testo stampato), ISSN 1120-1797, E-ISSN 1724-191X, Vol. 54, p. 21-29Article in journal (Refereed)
    Abstract [en]

    Purpose: A new set of quantitative features that capture intensity changes in PET/CT images over time and space is proposed for assessing the tumor response early during chemoradiotherapy. The hypothesis whether the new features, combined with machine learning, improve outcome prediction is tested. Methods: The proposed method is based on dividing the tumor volume into successive zones depending on the distance to the tumor border. Mean intensity changes are computed within each zone, for CT and PET scans separately, and used as image features for tumor response assessment. Doing so, tumors are described by accounting for temporal and spatial changes at the same time. Using linear support vector machines, the new features were tested on 30 non-small cell lung cancer patients who underwent sequential or concurrent chemoradiotherapy. Prediction of 2-years overall survival was based on two PET-CT scans, acquired before the start and during the first 3 weeks of treatment. The predictive power of the newly proposed longitudinal pattern features was compared to that of previously proposed radiomics features and radiobiological parameters. Results: The highest areas under the receiver operating characteristic curves were 0.98 and 0.93 for patients treated with sequential and concurrent chemoradiotherapy, respectively. Results showed an overall comparable performance with respect to radiomics features and radiobiological parameters. Conclusions: A novel set of quantitative image features, based on underlying tumor physiology, was computed from PET/CT scans and successfully employed to distinguish between early responders and non-responders to chemoradiotherapy. 

  • 9.
    Buizza, Giulia
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems. Politecn Milan, CartCasLab, Dept Elect Informat & Bioengn, Piazza Leonardo Da Vinci 42, I-20133 Milan, Italy..
    Toma-Dasu, Iuliana
    Karolinska Univ Sjukhuset, Karolinska Inst, Dept Oncol Pathol, Med Radiat Phys, S-17176 Solna, Sweden..
    Lazzeroni, Marta
    Karolinska Univ Sjukhuset, Karolinska Inst, Dept Oncol Pathol, Med Radiat Phys, S-17176 Solna, Sweden..
    Paganelli, Chiara
    Politecn Milan, CartCasLab, Dept Elect Informat & Bioengn, Piazza Leonardo Da Vinci 42, I-20133 Milan, Italy..
    Riboldi, Marco
    Politecn Milan, CartCasLab, Dept Elect Informat & Bioengn, Piazza Leonardo Da Vinci 42, I-20133 Milan, Italy.;Ludwig Maximilians Univ Munchen, Fac Phys, Coloumbwall 1, D-5748 Garching, Germany..
    Chang, Yong Jun
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems.
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Early tumor response prediction for lung cancer patients using novel longitudinal pattern features from sequential PET/CT image scans2018In: Physica medica (Testo stampato), ISSN 1120-1797, E-ISSN 1724-191X, Vol. 54, p. 21-29Article in journal (Refereed)
    Abstract [en]

    Purpose: A new set of quantitative features that capture intensity changes in PET/CT images over time and space is proposed for assessing the tumor response early during chemoradiotherapy. The hypothesis whether the new features, combined with machine learning, improve outcome prediction is tested. Methods: The proposed method is based on dividing the tumor volume into successive zones depending on the distance to the tumor border. Mean intensity changes are computed within each zone, for CT and PET scans separately, and used as image features for tumor response assessment. Doing so, tumors are described by accounting for temporal and spatial changes at the same time. Using linear support vector machines, the new features were tested on 30 non-small cell lung cancer patients who underwent sequential or concurrent chemoradiotherapy. Prediction of 2-years overall survival was based on two PET-CT scans, acquired before the start and during the first 3 weeks of treatment. The predictive power of the newly proposed longitudinal pattern features was compared to that of previously proposed radiomics features and radiobiological parameters. Results: The highest areas under the receiver operating characteristic curves were 0.98 and 0.93 for patients treated with sequential and concurrent chemoradiotherapy, respectively. Results showed an overall comparable performance with respect to radiomics features and radiobiological parameters. Conclusions: A novel set of quantitative image features, based on underlying tumor physiology, was computed from PET/CT scans and successfully employed to distinguish between early responders and non-responders to chemoradiotherapy.

  • 10.
    Chowdhury, Manish
    et al.
    KTH, School of Technology and Health (STH).
    Jörgens, Daniel
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. KTH, School of Technology and Health (STH), Medical Engineering, Medical Imaging.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Moreno, Rodrigo
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Segmentation of Cortical Bone using Fast Level Sets2017In: MEDICAL IMAGING 2017: IMAGE PROCESSING / [ed] Styner, MA Angelini, ED, SPIE - International Society for Optical Engineering, 2017, article id UNSP 1013327Conference paper (Refereed)
    Abstract [en]

    Cortical bone plays a big role in the mechanical competence of bone. The analysis of cortical bone requires accurate segmentation methods. Level set methods are usually in the state-of-the-art for segmenting medical images. However, traditional implementations of this method are computationally expensive. This drawback was recently tackled through the so-called coherent propagation extension of the classical algorithm which has decreased computation times dramatically. In this study, we assess the potential of this technique for segmenting cortical bone in interactive time in 3D images acquired through High Resolution peripheral Quantitative Computed Tomography (HR-pQCT). The obtained segmentations are used to estimate cortical thickness and cortical porosity of the investigated images. Cortical thickness and Cortical porosity is computed using sphere fitting and mathematical morphological operations respectively. Qualitative comparison between the segmentations of our proposed algorithm and a previously published approach on six images volumes reveals superior smoothness properties of the level set approach. While the proposed method yields similar results to previous approaches in regions where the boundary between trabecular and cortical bone is well defined, it yields more stable segmentations in challenging regions. This results in more stable estimation of parameters of cortical bone. The proposed technique takes few seconds to compute, which makes it suitable for clinical settings.

  • 11.
    Commowick, Olivier
    et al.
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France..
    Istace, Audrey
    Hosp Civils Lyon, Lyon Sud Hosp, Dept Radiol, Lyon, France..
    Kain, Michael
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France..
    Laurent, Baptiste
    Univ Brest, IBSAM, INSERM, LaTIM,UMR 1101, Brest, France..
    Leray, Florent
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France..
    Simon, Mathieu
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France..
    Pop, Sorina Camarasu
    Univ Claude Bernard Lyon 1, Univ Lyon,INSA Lyon, UJM St Etienne,CNRS,Inserm, CREATIS,UMR 5220,U1206, F-69621 Lyon, France..
    Girard, Pascal
    Univ Claude Bernard Lyon 1, Univ Lyon,INSA Lyon, UJM St Etienne,CNRS,Inserm, CREATIS,UMR 5220,U1206, F-69621 Lyon, France..
    Ameli, Roxana
    Hosp Civils Lyon, Lyon Sud Hosp, Dept Radiol, Lyon, France..
    Ferre, Jean-Christophe
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France.;CHU Rennes, Dept Neuroradiol, F-35033 Rennes, France..
    Kerbrat, Anne
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France.;CHU Rennes, Dept Neurol, F-35033 Rennes, France..
    Tourdias, Thomas
    CHU Bordeaux, Serv Neuroimagerie, Bordeaux, France..
    Cervenansky, Frederic
    Univ Claude Bernard Lyon 1, Univ Lyon,INSA Lyon, UJM St Etienne,CNRS,Inserm, CREATIS,UMR 5220,U1206, F-69621 Lyon, France..
    Glatard, Tristan
    Concordia Univ, Dept Comp Sci & Software Engn, Montreal, PQ, Canada..
    Beaumont, Jeremy
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France..
    Doyle, Senan
    Pixyl Med, Grenoble, France..
    Forbes, Florence
    Pixyl Med, Grenoble, France.;Inria Grenoble Rhone Alpes, Grenoble, France..
    Knight, Jesse
    Univ Guelph, Sch Engn, Image Anal Med Lab, Guelph, ON, Canada..
    Khademi, April
    Ryerson Univ, Image Anal Med Lab IAMLAB, Toronto, ON, Canada..
    Mahbod, Amirreza
    KTH, School of Technology and Health (STH).
    Wang, Chunliang
    KTH, School of Technology and Health (STH).
    McKinley, Richard
    Univ Bern, Dept Diagnost & Intervent Neuroradiol, Inselspital, Bern, Switzerland..
    Wagner, Franca
    Univ Bern, Dept Diagnost & Intervent Neuroradiol, Inselspital, Bern, Switzerland..
    Muschelli, John
    Johns Hopkins Bloomberg Sch Publ Hlth, Baltimore, MD USA..
    Sweeney, Elizabeth
    Johns Hopkins Bloomberg Sch Publ Hlth, Baltimore, MD USA..
    Roura, Eloy
    Univ Girona, Res Inst Comp Vis & Robot VICOROB, Girona, Spain..
    Llado, Xavier
    Univ Girona, Res Inst Comp Vis & Robot VICOROB, Girona, Spain..
    Santos, Michel M.
    Univ Fed Pernambuco, Ctr Informat, Recife, Brazil..
    Santos, Wellington P.
    Univ Fed Pernambuco, Dept Engn Biomed, Recife, Brazil..
    Silva-Filho, Abel G.
    Univ Fed Pernambuco, Ctr Informat, Recife, Brazil..
    Tomas-Fernandez, Xavier
    Childrens Hosp, Dept Radiol, Computat Radiol Lab, 300 Longwood Ave, Boston, MA 02115 USA..
    Urien, Helene
    Univ Paris Saclay, LTCI, Telecom ParisTech, Paris, France..
    Bloch, Isabelle
    Univ Paris Saclay, LTCI, Telecom ParisTech, Paris, France..
    Valverde, Sergi
    Univ Girona, Res Inst Comp Vis & Robot VICOROB, Girona, Spain..
    Cabezas, Mariano
    Univ Girona, Res Inst Comp Vis & Robot VICOROB, Girona, Spain..
    Javier Vera-Olmos, Francisco
    Univ Rey Juan Carlos, Med Image Anal Lab, Madrid, Spain..
    Malpica, Norberto
    Univ Rey Juan Carlos, Med Image Anal Lab, Madrid, Spain..
    Guttmann, Charles
    Brigham & Womens Hosp, Dept Radiol, Ctr Neurol Imaging, 75 Francis St, Boston, MA 02115 USA..
    Vukusic, Sandra
    Hosp Civils Lyon, Lyon Sud Hosp, Dept Radiol, Lyon, France..
    Edan, Gilles
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France.;CHU Rennes, Dept Neurol, F-35033 Rennes, France..
    Dojat, Michel
    Univ Grenoble Alpes, CHU Grenoble, GIN, Inserm,U1216, Grenoble, France..
    Styner, Martin
    Univ N Carolina, Dept Comp Sci, Chapel Hill, NC 27515 USA..
    Warfield, Simon K.
    Childrens Hosp, Dept Radiol, Computat Radiol Lab, 300 Longwood Ave, Boston, MA 02115 USA..
    Cotton, Francois
    Hosp Civils Lyon, Lyon Sud Hosp, Dept Radiol, Lyon, France..
    Barillot, Christian
    Univ Rennes 1, CNRS, INSERM, VISAGES,U1228,UMR6074, Rennes, France..
    Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure2018In: Scientific Reports, ISSN 2045-2322, E-ISSN 2045-2322, Vol. 8, article id 13650Article in journal (Refereed)
    Abstract [en]

    We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning,.), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.

  • 12. Jimenez-del-Toro, Oscar
    et al.
    Muller, Henning
    Krenn, Markus
    Gruenberg, Katharina
    Taha, Abdel Aziz
    Winterstein, Marianne
    Eggel, Ivan
    Foncubierta-Rodriguez, Antonio
    Goksel, Orcun
    Jakab, Andres
    Kontokotsios, Georgios
    Langs, Georg
    Menze, Bjoern H.
    Fernandez, Tomas Salas
    Schaer, Roger
    Walleyo, Anna
    Weber, Marc-Andre
    Cid, Yashin Dicente
    Gass, Tobias
    Heinrich, Mattias
    Jia, Fucang
    Kahl, Fredrik
    Kechichian, Razmig
    Mai, Dominic
    Spanier, Assaf B.
    Vincent, Graham
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Wyeth, Daniel
    Hanbury, Allan
    Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks2016In: IEEE Transactions on Medical Imaging, ISSN 0278-0062, E-ISSN 1558-254X, Vol. 35, no 11, p. 2459-2475Article in journal (Refereed)
    Abstract [en]

    Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for anatomical structure segmentation and landmark detection: the VISCERAL Anatomy benchmarks. The algorithms are implemented in virtual machines in the cloud where participants can only access the training data and can be run privately by the benchmark administrators to objectively compare their performance in an unseen common test set. Overall, 120 computed tomography and magnetic resonance patient volumes were manually annotated to create a standard Gold Corpus containing a total of 1295 structures and 1760 landmarks. Ten participants contributed with automatic algorithms for the organ segmentation task, and three for the landmark localization task. Different algorithms obtained the best scores in the four available imaging modalities and for subsets of anatomical structures. The annotation framework, resulting data set, evaluation setup, results and performance analysis from the three VISCERAL Anatomy benchmarks are presented in this article. Both the VISCERAL data set and Silver Corpus generated with the fusion of the participant algorithms on a larger set of non-manually-annotated medical images are available to the research community.

  • 13. Kiri\csli, H A
    et al.
    Schaap, Michiel
    Metz, C T
    Dharampal, A S
    Meijboom, W B
    Papadopoulou, S L
    Dedic, A
    Nieman, K
    de Graaf, Michiel A
    Meijs, M F L
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Walsum, Theo van
    Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography2013In: Medical image analysis, Vol. 17, no 8, p. 859-876Article in journal (Refereed)
  • 14. Lidayová, K.
    et al.
    Frimmel, H.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping University, Sweden.
    Bengtsson, E.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping University, Sweden.
    Fast vascular skeleton extraction algorithm2016In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 76, p. 67-75Article in journal (Refereed)
    Abstract [en]

    Vascular diseases are a common cause of death, particularly in developed countries. Computerized image analysis tools play a potentially important role in diagnosing and quantifying vascular pathologies. Given the size and complexity of modern angiographic data acquisition, fast, automatic and accurate vascular segmentation is a challenging task.In this paper we introduce a fully automatic high-speed vascular skeleton extraction algorithm that is intended as a first step in a complete vascular tree segmentation program. The method takes a 3D unprocessed Computed Tomography Angiography (CTA) scan as input and produces a graph in which the nodes are centrally located artery voxels and the edges represent connections between them. The algorithm works in two passes where the first pass is designed to extract the skeleton of large arteries and the second pass focuses on smaller vascular structures. Each pass consists of three main steps. The first step sets proper parameters automatically using Gaussian curve fitting. In the second step different filters are applied to detect voxels - nodes - that are part of arteries. In the last step the nodes are connected in order to obtain a continuous centerline tree for the entire vasculature. Structures found, that do not belong to the arteries, are removed in a final anatomy-based analysis. The proposed method is computationally efficient with an average execution time of 29s and has been tested on a set of CTA scans of the lower limbs achieving an average overlap rate of 97% and an average detection rate of 71%.

  • 15. Lidayová, K.
    et al.
    Frimmel, H.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Bengtsson, E.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Skeleton-based fast, fully automated generation of vessel tree structure for clinical evaluation of blood vessel systems2017In: Skeletonization: Theory, Methods and Applications, Elsevier, 2017, p. 345-382Chapter in book (Other academic)
    Abstract [en]

    This chapter focuses on skeleton detection for clinical evaluation of blood vessel systems. In clinical evaluation, there is a need for fast and accurate segmentation algorithms that can reliably provide vessel measurements and additional information for clinicians to decide the diagnosis.Since blood vessels have a characteristic tubular shape, their segmentation can be accelerated and facilitated by first identifying the rough vessel centerlines, which can be seen as a special case of an image skeleton extraction algorithm. A segmentation algorithm will finally use the resulting skeleton as a seed region during the segmentation. The proposed method takes an unprocessed 3D computed tomography angiography (CTA) scan as an input and generates a connected graph of centrally located arterial voxels. The method works in two levels, where large arteries are captured in the first level, and small arteries are added in the second one. Experimental results show that the method can achieve high overlap rate and acceptable detection rate accuracies. High computational efficiency of the method opens the possibility for an interactive clinical use.

  • 16. Lidayová, Kristína
    et al.
    Lindblad, Joakim
    Sladoje, Nataša
    Frimmel, Hans
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Coverage segmentation of 3D thin structures2015In: Image Processing Theory, Tools and Applications (IPTA), 2015 International Conference on, IEEE conference proceedings, 2015, p. 23-28Conference paper (Refereed)
    Abstract [en]

    We present a coverage segmentation method for extracting thin structures in three-dimensional images. The proposed method is an improved extension of our coverage segmentation method for 2D thin structures. We suggest implementation that enables low memory consumption and processing time, and by that applicability of the method on real CTA data. The method needs a reliable crisp segmentation as an input and uses information from linear unmixing and the crisp segmentation to create a high-resolution crisp reconstruction of the object, which can then be used as a final result, or down-sampled to a coverage segmentation at the starting image resolution. Performed quantitative and qualitative analysis confirm excellent performance of the proposed method, both on synthetic and on real data, in particular in terms of robustness to noise.

  • 17. Lidayová, Kristína
    et al.
    Lindblad, Joakim
    Sladoje, Nataša
    Frimmel, Hans
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Smedby, Örjan
    Coverage segmentation of 3D thin structures2015Conference paper (Refereed)
  • 18.
    Mahbod, A.
    et al.
    Romania.
    Ellinger, I.
    Romania.
    Ecker, R.
    Romania.
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Breast Cancer Histological Image Classification Using Fine-Tuned Deep Network Fusion2018In: 15th International Conference on Image Analysis and Recognition, ICIAR 2018, Springer, 2018, p. 754-762Conference paper (Refereed)
    Abstract [en]

    Breast cancer is the most common cancer type in women worldwide. Histological evaluation of the breast biopsies is a challenging task even for experienced pathologists. In this paper, we propose a fully automatic method to classify breast cancer histological images to four classes, namely normal, benign, in situ carcinoma and invasive carcinoma. The proposed method takes normalized hematoxylin and eosin stained images as input and gives the final prediction by fusing the output of two residual neural networks (ResNet) of different depth. These ResNets were first pre-trained on ImageNet images, and then fine-tuned on breast histological images. We found that our approach outperformed a previous published method by a large margin when applied on the BioImaging 2015 challenge dataset yielding an accuracy of 97.22%. Moreover, the same approach provided an excellent classification performance with an accuracy of 88.50% when applied on the ICIAR 2018 grand challenge dataset using 5-fold cross validation.

  • 19. Mahbod, A.
    et al.
    Schaefer, G.
    Ellinger, I.
    Ecker, R.
    Pitiot, A.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Fusing fine-tuned deep features for skin lesion classification2019In: Computerized Medical Imaging and Graphics, ISSN 0895-6111, E-ISSN 1879-0771, Vol. 71, p. 19-29Article in journal (Refereed)
    Abstract [en]

    Malignant melanoma is one of the most aggressive forms of skin cancer. Early detection is important as it significantly improves survival rates. Consequently, accurate discrimination of malignant skin lesions from benign lesions such as seborrheic keratoses or benign nevi is crucial, while accurate computerised classification of skin lesion images is of great interest to support diagnosis. In this paper, we propose a fully automatic computerised method to classify skin lesions from dermoscopic images. Our approach is based on a novel ensemble scheme for convolutional neural networks (CNNs) that combines intra-architecture and inter-architecture network fusion. The proposed method consists of multiple sets of CNNs of different architecture that represent different feature abstraction levels. Each set of CNNs consists of a number of pre-trained networks that have identical architecture but are fine-tuned on dermoscopic skin lesion images with different settings. The deep features of each network were used to train different support vector machine classifiers. Finally, the average prediction probability classification vectors from different sets are fused to provide the final prediction. Evaluated on the 600 test images of the ISIC 2017 skin lesion classification challenge, the proposed algorithm yields an area under receiver operating characteristic curve of 87.3% for melanoma classification and an area under receiver operating characteristic curve of 95.5% for seborrheic keratosis classification, outperforming the top-ranked methods of the challenge while being simpler compared to them. The obtained results convincingly demonstrate our proposed approach to represent a reliable and robust method for feature extraction, model fusion and classification of dermoscopic skin lesion images.

  • 20.
    Mahbod, Amirreza
    et al.
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Chowdhury, Manish
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Automatic brain segmentation using artificial neural networks with shape context2018In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 101, p. 74-79Article in journal (Refereed)
    Abstract [en]

    Segmenting brain tissue from MR scans is thought to be highly beneficial for brain abnormality diagnosis, prognosis monitoring, and treatment evaluation. Many automatic or semi-automatic methods have been proposed in the literature in order to reduce the requirement of user intervention, but the level of accuracy in most cases is still inferior to that of manual segmentation. We propose a new brain segmentation method that integrates volumetric shape models into a supervised artificial neural network (ANN) framework. This is done by running a preliminary level-set based statistical shape fitting process guided by the image intensity and then passing the signed distance maps of several key structures to the ANN as feature channels, in addition to the conventional spatial-based and intensity-based image features. The so-called shape context information is expected to help the ANN to learn local adaptive classification rules instead of applying universal rules directly on the local appearance features. The proposed method was tested on a public datasets available within the open MICCAI grand challenge (MRBrainS13). The obtained average Dice coefficient were 84.78%, 88.47%, 82.76%, 95.37% and 97.73% for gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), brain (WM + GM) and intracranial volume respectively. Compared with other methods tested on the same dataset, the proposed method achieved competitive results with comparatively shorter training time.

  • 21. Mahbod, Amirreza
    et al.
    Schaefer, Gerald
    Ellinger, Isabella
    Ecker, Rupert
    Smedby, Örjan
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    A Two-Stage U-Net Algorithm for Segmentation of Nuclei in H&E-Stained Tissues2019Conference paper (Refereed)
  • 22. Mahbod, Amirreza
    et al.
    Schaefer, Gerald
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Ecker, Rupert
    Ellinge, Isabella
    Skin lesion classification using hybrid deep neural networks2019Conference paper (Refereed)
  • 23. Mahbod, Amirreza
    et al.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Smedby, Orjan
    Automatic multiple sclerosis lesion segmentation using hybrid artificial neural networks2016In: MSSEG Challenge Proceedings: Multiple Sclerosis Lesions Segmentation Challenge Using a Data Management and Processing Infrastructure, Vol. 29Article in journal (Refereed)
  • 24. Marreiros, Filipe M. M.
    et al.
    Rossitti, Sandro
    Karlsson, Per M.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Gustafsson, Torbjorn
    Carleberg, Per
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Superficial vessel reconstruction with a multiview camera system2016In: Journal of Medical Imaging, ISSN 2329-4302, E-ISSN 2329-4310, Vol. 3, no 1, article id 015001Article in journal (Refereed)
    Abstract [en]

    We aim at reconstructing superficial vessels of the brain. Ultimately, they will serve to guide the deformation methods to compensate for the brain shift. A pipeline for three-dimensional (3-D) vessel reconstruction using three mono-complementary metal-oxide semiconductor cameras has been developed. Vessel centerlines are manually selected in the images. Using the properties of the Hessian matrix, the centerline points are assigned direction information. For correspondence matching, a combination of methods was used. The process starts with epipolar and spatial coherence constraints (geometrical constraints), followed by relaxation labeling and an iterative filtering where the 3-D points are compared to surfaces obtained using the thin-plate spline with decreasing relaxation parameter. Finally, the points are shifted to their local centroid position. Evaluation in virtual, phantom, and experimental images, including intraoperative data from patient experiments, shows that, with appropriate camera positions, the error estimates (root-mean square error and mean error) are similar to 1 mm.

  • 25. Marreiros, Filipe M. M.
    et al.
    Rossitti, Sandro
    Karlsson, Per M.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Gustafsson, Torbjorn
    Carleberg, Per
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Superficial vessel reconstruction with a Multiview camera system (vol 3, 015001, 2016)2016In: Journal of Medical Imaging, ISSN 2329-4302, E-ISSN 2329-4310, Vol. 3, no 1, article id 019801Article in journal (Refereed)
  • 26. Marreiros, Filipe M. M.
    et al.
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping Univ, Sweden.
    Rossitti, Sandro
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping Univ, Sweden.
    Non-rigid point set registration of curves: registration of the superficial vessel centerlines of the brain2016In: MEDICAL IMAGING 2016: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, SPIE - International Society for Optical Engineering, 2016, article id UNSP 978611Conference paper (Refereed)
    Abstract [en]

    In this study we present a non-rigid point set registration for 3D curves (composed by 3D set of points). The method was evaluated in the task of registration of 3D superficial vessels of the brain where it was used to match vessel centerline points. It consists of a combination of the Coherent Point Drift (CPD) and the Thin-Plate Spline (TPS) semilandmarks. The CPD is used to perform the initial matching of centerline 3D points, while the semilandmark method iteratively relaxes/slides the points. For the evaluation, a Magnetic Resonance Angiography (MRA) dataset was used. Deformations were applied to the extracted vessels centerlines to simulate brain bulging and sinking, using a TPS deformation where a few control points were manipulated to obtain the desired transformation (T-1). Once the correspondences are known, the corresponding points are used to define a new TPS deformation(T-2). The errors are measured in the deformed space, by transforming the original points using T-1 and T-2 and measuring the distance between them. To simulate cases where the deformed vessel data is incomplete, parts of the reference vessels were cut and then deformed. Furthermore, anisotropic normally distributed noise was added. The results show that the error estimates (root mean square error and mean error) are below 1 mm, even in the presence of noise and incomplete data.

  • 27. Medrano-Gracia, Pau
    et al.
    Ormiston, John
    Webster, Mark
    Beier, Susann
    Ellis, Chris
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. KTH, School of Technology and Health (STH), Medical Engineering, Medical Imaging.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Young, Alistair
    Cowan, Brett
    A Study of Coronary Bifurcation Shape in a Normal Population2017In: Journal of Cardiovascular Translational Research, ISSN 1937-5387, E-ISSN 1937-5395, Vol. 10, no 1, p. 82-90Article in journal (Refereed)
    Abstract [en]

    During percutaneous coronary intervention, stents are placed in narrowings of the arteries to restore normal blood flow. Despite improvements in stent design, deployment techniques and drug-eluting coatings, restenosis and stent thrombosis remain a significant problem. Population stent design based on statistical shape analysis may improve clinical outcomes. Computed tomographic (CT) coronary angiography scans from 211 patients with a zero calcium score, no stenoses and no intermediate artery, were used to create statistical shape models of 446 major coronary artery bifurcations (left main, first diagonal and obtuse marginal and right coronary crux). Coherent point drift was used for registration. Principal component analysis shape scores were tested against clinical risk factors, quantifying the importance of recognised shape features in intervention including size, angles and curvature. Significant differences were found in (1) vessel size and bifurcation angle between the left main and other bifurcations; (2) inlet and curvature angle between the right coronary crux and other bifurcations; and (3) size and bifurcation angle by sex. Hypertension, smoking history and diabetes did not appear to have an association with shape. Physiological diameter laws were compared, with the Huo-Kassab model having the best fit. Bifurcation coronary anatomy can be partitioned into clinically meaningful modes of variation showing significant shape differences. A computational atlas of normal coronary bifurcation shape, where disease is common, may aid in the design of new stents and deployment techniques, by providing data for bench-top testing and computational modelling of blood flow and vessel wall mechanics.

  • 28. Medrano-Gracia, Pau
    et al.
    Ormiston, John
    Webster, Mark
    Beier, Susann
    Ellis, Chris
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Young, Alistair A
    Cowan, Brett R
    Construction of a coronary artery atlas from CT angiography2014Conference paper (Refereed)
  • 29. Medrano-Gracia, Pau
    et al.
    Ormiston, John
    Webster, Mark
    Beier, Susann
    Ellis, Chris
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Young, Alistair
    Cowan, Brett
    A Statistical Model of the Main Bifurcation of the Left Coronary Artery using Coherent Point Drift2015Conference paper (Refereed)
  • 30. Medrano-Gracia, Pau
    et al.
    Ormiston, John
    Webster, Mark
    Beier, Susann
    Young, Alistair
    Ellis, Chris
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization.
    Cowan, Brett
    A computational atlas of normal coronary artery anatomy2016In: EuroIntervention, ISSN 1774-024X, E-ISSN 1969-6213, Vol. 12, no 7, p. 845-854Article in journal (Refereed)
    Abstract [en]

    Aims: The aim of this study was to define the shape variations, including diameters and angles, of the major coronary artery bifurcations. Methods and results: Computed tomographic angiograms from 300 adults with a zero calcium score and no stenoses were segmented for centreline and luminal models. A computational atlas was constructed enabling automatic quantification of 3D angles, diameters and lengths of the coronary tree. The diameter (mean +/- SD) of the left main coronary was 3.5 +/- 0.8 mm and the length 10.5 +/- 5.3 mm. The left main bifurcation angle (distal angle or angle B) was 89 +/- 21 degrees for cases with, and 75 +/- 23 degrees for those without an intermediate artery (p<0.001). Analogous measurements of diameter and angle were tabulated for the other major bifurcations (left anterior descending/diagonal, circumflex/obtuse marginal and right coronary crux). Novel 3D angle definitions are proposed and analysed. Conclusions: A computational atlas of normal coronary artery anatomy provides distributions of diameter, lengths and bifurcation angles as well as more complex shape analysis. These data define normal anatomical variation, facilitating stent design, selection and optimal treatment strategy. These population models are necessary for accurate computational flow dynamics, can be 3D printed for bench testing bifurcation stents and deployment strategies, and can aid in the discussion of different approaches to the treatment of coronary bifurcations.

  • 31. Mendrik, AM
    et al.
    Vincken, KL
    Kuijf, HJ
    Breeuwer, M
    Bouvy, W
    de Bresser, J
    Alansary, A
    de Bruijne, M
    Caras, A
    El-Baz, A
    Jogh, A
    Katyal, AR
    Khan, AR
    van der Lijn, F
    Mahmood, Q
    Mukherjee, R
    van Opbroek, A
    Paneri, S
    Pereira, S
    Persson, M
    Rajch, M
    Sarikaya, D
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping University.
    Silval, CA
    Vrooman, HA
    Vyas, S
    Wang, Chunliang
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping University.
    Zhao, L
    Biessels, GJ
    Viergever, MA
    MRBrainS Challenge: Online Evaluation Framework for Brain Image Segmentation in 3T MRI Scans2015In: Computational Intelligence and Neuroscience, ISSN 1687-5265, E-ISSN 1687-5273, Vol. 2015, article id 813696Article in journal (Refereed)
    Abstract [en]

    Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.

  • 32. Moreno, Rodrigo
    et al.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Smedby, Örjan
    Vessel wall segmentation using implicit models and total curvature penalizers2013Conference paper (Refereed)
  • 33. Mårtensson, Gustav
    et al.
    Ferreira, Daniel
    Cavallin, Lena
    Muehlboeck, J-Sebastian
    Wahlund, Lars-Olof
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Westman, Eric
    Initiative, Alzheimer’s Disease Neuroimaging
    AVRA: Automatic visual ratings of atrophy from MRI images using recurrent convolutional neural networks2019In: NeuroImage: Clinical, Vol. 23Article in journal (Refereed)
  • 34. Petersson, Helge
    et al.
    Sinkvist, David
    Wang, Chunliang
    Linköping University, SE-581 85 Linköping, Sweden.
    Smedby, Örjan
    Linköping University, SE-581 85 Linköping, Sweden.
    Web-based interactive 3D visualization as a tool for improved anatomy learning2009In: Anatomical Sciences Education, ISSN 1935-9772, Vol. 2, no 2, p. 61-68Article in journal (Refereed)
    Abstract [en]

    Despite a long tradition, conventional anatomy education based on dissection is declining. This study tested a new virtual reality (VR) technique for anatomy learning based on virtual contrast injection. The aim was to assess whether students value this new three-dimensional (3D) visualization method as a learning tool and what value they gain from its use in reaching their anatomical learning objectives. Several 3D vascular VR models were created using an interactive segmentation tool based on the "virtual contrast injection" method. This method allows users, with relative ease, to convert computer tomography or magnetic resonance images into vivid 3D VR movies using the OsiriX software equipped with the CMIV CTA plug-in. Once created using the segmentation tool, the image series were exported in Quick Time Virtual Reality (QTVR) format and integrated within a web framework of the Educational Virtual Anatomy (EVA) program. A total of nine QTVR movies were produced encompassing most of the major arteries of the body. These movies were supplemented with associated information, color keys, and notes. The results indicate that, in general, students' attitudes towards the EVA-program were positive when compared with anatomy textbooks, but results were not the same with dissections. Additionally, knowledge tests suggest a potentially beneficial effect on learning.

  • 35.
    Qin, Chunxia
    et al.
    Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai, Peoples R China.;Shanghai Jiao Tong Univ, Sch Mech Engn, Room 805,Dongchuan Rd 800, Shanghai 200240, Peoples R China..
    Cao, Zhenggang
    Shanghai Jiao Tong Univ, Sch Mech Engn, Room 805,Dongchuan Rd 800, Shanghai 200240, Peoples R China..
    Fan, Shengchi
    Shanghai Jiao Tong Univ, Shanghai Peoples Hosp 9, Sch Med, Shanghai, Peoples R China..
    Wu, Yiqun
    Shanghai Jiao Tong Univ, Shanghai Peoples Hosp 9, Sch Med, Shanghai, Peoples R China..
    Sun, Yi
    Katholieke Univ Leuven, Fac Med, Dept Imaging & Pathol, OMFS IMPATH Res Grp, Louvain, Belgium.;Univ Hosp Leuven, Dept Oral & Maxillofacial Surg, Louvain, Belgium..
    Politis, Constantinus
    Katholieke Univ Leuven, Fac Med, Dept Imaging & Pathol, OMFS IMPATH Res Grp, Louvain, Belgium.;Univ Hosp Leuven, Dept Oral & Maxillofacial Surg, Louvain, Belgium..
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Chen, Xiaojun
    Shanghai Jiao Tong Univ, Sch Mech Engn, Room 805,Dongchuan Rd 800, Shanghai 200240, Peoples R China..
    An oral and maxillofacial navigation system for implant placement with automatic identification of fiducial points2019In: International Journal of Computer Assisted Radiology and Surgery, ISSN 1861-6410, E-ISSN 1861-6429, Vol. 14, no 2, p. 281-289Article in journal (Refereed)
    Abstract [en]

    PurposeSurgical navigation system (SNS) has been an important tool in surgery. However, the complicated and tedious manual selection of fiducial points on preoperative images for registration affects operational efficiency to large extent. In this study, an oral and maxillofacial navigation system named BeiDou-SNS with automatic identification of fiducial points was developed and demonstrated.MethodsTo solve the fiducial selection problem, a novel method of automatic localization for titanium screw markers in preoperative images is proposed on the basis of a sequence of two local mean-shift segmentation including removal of metal artifacts. The operation of the BeiDou-SNS consists of the following key steps: The selection of fiducial points, the calibration of surgical instruments, and the registration of patient space and image space. Eight cases of patients with titanium screws as fiducial markers were carried out to analyze the accuracy of the automatic fiducial point localization algorithm. Finally, a complete phantom experiment of zygomatic implant placement surgery was performed to evaluate the whole performance of BeiDou-SNS. Results and conclusionThe coverage of Euclidean distances between fiducial marker positions selected automatically and those selected manually by an experienced dentist for all eight cases ranged from 0.373 to 0.847mm. Four implants were inserted into the 3D-printed model under the guide of BeiDou-SNS. And the maximal deviations between the actual and planned implant were 1.328mm and 2.326mm, respectively, for the entry and end point while the angular deviation ranged from 1.094 degrees to 2.395 degrees. The results demonstrate that the oral surgical navigation system with automatic identification of fiducial points can meet the requirements of the clinical surgeries.

  • 36. Schaap, Michiel
    et al.
    Metz, Coert T
    van Walsum, Theo
    van der Giessen, Alina G
    Weustink, Annick C
    Mollet, Nico R
    Bauer, Christian
    Bogunović, Hrvoje
    Castro, Carlos
    Deng, Xiang
    Wang, Chunliang
    Linköping Univ., Linköping, Sweden.
    Niessen, Wiro J.
    Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms2009In: Medical Image Analysis, ISSN 1361-8415, E-ISSN 1361-8423, Vol. 13, no 5, p. 701-714Article in journal (Refereed)
    Abstract [en]

    Efficiently obtaining a reliable coronary artery centerline from computed tomography angiography data is relevant in clinical practice. Whereas numerous methods have been presented for this purpose, up to now no standardized evaluation methodology has been published to reliably evaluate and compare the performance of the existing or newly developed coronary artery centerline extraction algorithms. This paper describes a standardized evaluation methodology and reference database for the quantitative evaluation of coronary artery centerline extraction algorithms. The contribution of this work is fourfold: (1) a method is described to create a consensus centerline with multiple observers, (2) well-defined measures are presented for the evaluation of coronary artery centerline extraction algorithms, (3) a database containing 32 cardiac CTA datasets with corresponding reference standard is described and made available. and (4) 13 coronary artery centerline extraction algorithms, implemented by different research groups, are quantitatively evaluated and compared. The presented evaluation framework is made available to the medical imaging community for benchmarking existing or newly developed coronary centerline extraction algorithms.

  • 37. Steigner, Michael L.
    et al.
    Mitsouras, Dimitrios
    Whitmore, Amanda G.
    Otero, Hansel J.
    Wang, Chunliang
    Linköping University, Sweden.
    Buckley, Orla
    Levit, Noah A.
    Hussain, Alia Z.
    Cai, Tianxi
    Mather, Richard T.
    Iodinated contrast opacification gradients in normal coronary arteries imaged with prospectively ECG-gated single heart beat 320-detector row computed tomography2010In: Circulation Cardiovascular Imaging, ISSN 1941-9651, E-ISSN 1942-0080, Vol. 3, no 2, p. 179-186Article in journal (Refereed)
    Abstract [en]

    Methods and Results-Thirty-six patients with normal coronary arteries determined by 320 x 0.5-mm detector row coronary CTA were retrospectively evaluated with customized image postprocessing software to measure Hounsfield Units at 1-mm intervals orthogonal to the artery center line. Linear regression determined correlation between mean Hounsfield Units and distance from the coronary ostium (regression slope defined as the distance gradient G(d)), lumen cross-sectional area (G(a)), and lumen short-axis diameter (G(s)). For each gradient, differences between the 3 coronary arteries were analyzed with ANOVA. Linear regression determined correlations between measured gradients, heart rate, body mass index, and cardiac phase. To determine feasibility in lesions, all 3 gradients were evaluated in 22 consecutive patients with left anterior descending artery lesions >= 50% stenosis. For all 3 coronary arteries in all patients, the gradients G(a) and G(s) were significantly different from zero (P < 0.0001), highly linear (Pearson r values, 0.77 to 0.84), and had no significant difference between the left anterior descending, left circumflex, and right coronary arteries (P > 0.503). The distance gradient G(d) demonstrated nonlinearities in a small number of vessels and was significantly smaller in the right coronary artery when compared with the left coronary system (P < 0.001). Gradient variations between cardiac phases, heart rates, body mass index, and readers were low. Gradients in patients with lesions were significantly different (P < 0.021) than in patients considered normal by CTA. Conclusions-Measurement of contrast opacification gradients from temporally uniform coronary CTA demonstrates feasibility and reproducibility in patients with normal coronary arteries. For all patients, the gradients defined with respect to the coronary lumen cross-sectional area and short-axis diameters are highly linear, not significantly influenced by the coronary artery (left anterior descending artery versus left circumflex versus right coronary artery), and have only small variation with respect to patient parameters. Preliminary evaluation of gradients across coronary artery lesions is promising but requires additional study. (Circ Cardiovasc Imaging. 2010;3:179-186.)

  • 38.
    Wan, Fengkai
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems. Novamia AB, Uppsala, Sweden.
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging. Novamia AB, Uppsala, Sweden.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging. Novamia AB, Uppsala, Sweden.
    Simultaneous MR knee image segmentation and bias field correction using deep learning and partial convolution2019In: Medical Imaging 2019: Image Processing, SPIE - International Society for Optical Engineering, 2019, Vol. 10949, article id 1094909Conference paper (Refereed)
    Abstract [en]

    Intensity inhomogeneity is a great challenge for automated organ segmentation in magnetic resonance (MR) images. Many segmentation methods fail to deliver satisfactory results when the images are corrupted by a bias field. Although inhomogeneity correction methods exist, they often fail to remove the bias field completely in knee MR images. We present a new iterative approach that simultaneously predicts the segmentation mask of knee structures using a 3D U-net and estimates the bias field in 3D MR knee images using partial convolution operations. First, the test images run through a trained 3D U-net to generate a preliminary segmentation result, which is then fed to the partial convolution filter to create a preliminary estimation of the bias field using the segmented bone mask. Finally, the estimated bias field is then used to produce bias field corrected images as the new inputs to the 3D U-net. Through this loop, the segmentation results and bias field correction are iteratively improved. The proposed method was evaluated on 20 proton-density (PD)-weighted knee MRI scans with manually created segmentation ground truth using 10 fold cross-validation. In our preliminary experiments, the proposed methods outperformed conventional inhomogeneity-correction-plus-segmentation setup in terms of both segmentation accuracy and speed.

  • 39.
    Wang, Chunliang
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Connolly, Bryan
    de Oliveira Lopes, Pedro Filipe
    Frangi, Alejandro F.
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Pelvis segmentation using multi-pass U-Net and iterative shape estimation2018In: Computational Methods and Clinical Applications in Musculoskeletal Imaging, Springer, 2018, Vol. 11404, p. 49-57Conference paper (Refereed)
    Abstract [en]

    In this report, an automatic method for segmentation of the pelvis in three-dimensional (3D) computed tomography (CT) images is proposed. The method is based on a 3D U-net which has as input the 3D CT image and estimated volumetric shape models of the targeted structures and which returns the probability maps of each structure. During training, the 3D U-net is initially trained using blank shape context inputs to generate the segmentation masks, i.e. relying only on the image channel of the input. The preliminary segmentation results are used to estimate a new shape model, which is then fed to the same network again, with the input images. With the additional shape context information, the U-net is trained again to generate better segmentation results. During the testing phase, the input image is fed through the same 3D U-net multiple times, first with blank shape context channels and then with iteratively re-estimated shape models. Preliminary results show that the proposed multi-pass U-net with iterative shape estimation outperforms both 2D and 3D conventional U-nets without the shape model.

  • 40.
    Wang, Chunliang
    et al.
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping University.
    Dahlström, Nils
    Fransson, Sven-Göran
    Lundström, Claes
    Smedby, Örjan
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Image Processing and Visualization. Linköping University, Sweden.
    Real-Time Interactive 3D Tumor Segmentation Using a Fast Level-Set Algorithm2015In: Journal of Medical Imaging and Health Informatics, ISSN 2156-7018, E-ISSN 2156-7026, Vol. 5, no 8, p. 1998-2002Article in journal (Refereed)
    Abstract [en]

    A new level-set based interactive segmentation framework is introduced, where the algorithm learns the intensity distributions of the tumor and surrounding tissue from a line segment drawn by the user from the middle of the lesion towards the border. This information is used to design a likelihood function, which is then incorporated into the level-set framework as an external speed function guiding the segmentation. The endpoint of the input line segment sets a limit to the propagation of 3D region, i.e., when the zero-level-set crosses this point, the propagation is forced to stop. Finally, a fast level set algorithm with coherent propagation is used to solve the level set equation in real time. This allows the user to instantly see the 3D result while adjusting the position of the line segment to tune the parameters implicitly. The &#8220;fluctuating&#8221; character of the coherent propagation also enables the contour to coherently follow the mouse cursor&#8217;s motion when the user tries to fine-tune the position of the contour on the boundary, where the learned likelihood function may not necessarily change much. Preliminary results suggest that radiologists can easily learn how to use the proposed segmentation tool and perform relatively accurate segmentation with much less time than the conventional slice-by-slice based manual procedure.

  • 41.
    Wang, Chunliang
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging. Linköping University, Sweden.
    Forsberg, Daniel
    Segmentation of intervertebral discs in 3D MRI data using multi-atlas based registration2015In: Computational Methods and Clinical Applications for Spine Imaging, Springer, 2015, Vol. 9402, p. 107-116Conference paper (Refereed)
    Abstract [en]

    This paper presents one of the participating methods to the intervertebral disc segmentation challenge organized in conjunction with the 3rd MICCAI Workshop & Challenge on Computational Methods and Clinical Applications for Spine Imaging - MICCAI-CSI2015. The presented method consist of three steps. In the first step, vertebral bodies are detected and labeled using integral channel features and a graphical parts model. The second step consists of image registration, where a set of image volumes with corresponding intervertebral disc atlases are registered to the target volume using the output from the first step as initialization. In the final step, the registered atlases are combined using label fusion to derive the final segmentation. The pipeline was evaluated using a set of 15 + 10 T2-weighted image volumes provided as training and test data respectively for the segmentation challenge. For the training data, a mean disc centroid distance of 0.86 mm and an average DICE score of 91% was achieved, and for the test data the corresponding results were 0.90 mm and 90%.

  • 42.
    Wang, Chunliang
    et al.
    Linköping University Hospital, Sweden.
    Frimmel, Hans
    Persson, Anders
    Smedby, Örjan
    Linköping University Hospital, Sweden.
    An interactive software module for visualizing coronary arteries in CT angiography2008In: International Journal of Computer Assisted Radiology and Surgery, ISSN 1861-6410, E-ISSN 1861-6429, Vol. 3, no 1-2, p. 11-18Article in journal (Refereed)
    Abstract [en]

    Object: A new software module for coronary artery segmentation and visualization in CT angiography (CTA) datasets is presented, which aims to interactively segment coronary arteries and visualize them in 3D with maximum intensity projection (MIP) and volume rendering (VRT). Materials and Methods: The software was built as a plug-in for the open-source PACS workstation OsiriX. The main segmentation function is based an optimized "virtual contrast injection" algorithm, which uses fuzzy connectedness of the vessel lumen to separate the contrast-filled structures from each other. The software was evaluated in 42 clinical coronary CTA datasets acquired with 64-slice CT using isotropic voxels of 0.3-10.5 mm. Results: The median processing time was 6.4 min, and 100% of main branches (right coronary artery, left circumflex artery and left anterior descending artery) and 86.9% (219/252) of visible minor branches were intact. Visually correct centerlines were obtained automatically in 94.7% (321/339) of the intact branches. Conclusion: The new software is a promising tool for coronary CTA post-processing providing good overviews of the coronary artery with limited user interaction on low-end hardware, and the coronary CTA diagnosis procedure could potentially be more time-efficient than using thin-slab technique.

  • 43.
    Wang, Chunliang
    et al.
    Linköping University, Sweden.
    Frimmel, Hans
    Smedby, Örjan
    Linköping University, Sweden.
    Fast level-set based image segmentation using coherent propagation2014In: Medical physics (Lancaster), ISSN 0094-2405, Vol. 41, no 7, article id 073501Article in journal (Refereed)
    Abstract [en]

    Purpose: The level-set method is known to require long computation time for 3D image segmentation, which limits its usage in clinical workflow. The goal of this study was to develop a fast level-set algorithm based on the coherent propagation method and explore its character using clinical datasets. Methods: The coherent propagation algorithm allows level set functions to converge faster by forcing the contour to move monotonically according to a predicted developing trend. Repeated temporary backwards propagation, caused by noise or numerical errors, is then avoided. It also makes it possible to detect local convergence, so that the parts of the boundary that have reached their final position can be excluded in subsequent iterations, thus reducing computation time. To compensate for the overshoot error, forward and backward coherent propagation is repeated periodically. This can result in fluctuations of great magnitude in parts of the contour. In this paper, a new gradual convergence scheme using a damping factor is proposed to address this problem. The new algorithm is also generalized to non-narrow band cases. Finally, the coherent propagation approach is combined with a new distance-regularized level set, which eliminates the needs of reinitialization of the distance. Results: Compared with the sparse field method implemented in the widely available ITKSnap software, the proposed algorithm is about 10 times faster when used for brain segmentation and about 100 times faster for aorta segmentation. Using a multiresolution approach, the new method achieved 50 times speed-up in liver segmentation. The Dice coefficient between the proposed method and the sparse field method is above 99% in most cases. Conclusions: A generalized coherent propagation algorithm for level set evolution yielded substantial improvement in processing time with both synthetic datasets and medical images.

  • 44.
    Wang, Chunliang
    et al.
    Linköping University, Sweden.
    Frimmel, Hans
    Smedby, Örjan
    Linköping University, Sweden.
    Level set based vessel segmentation accelerated with periodic monotonic speed function2011In: MEDICAL IMAGING 2011:: IMAGE PROCESSING, SPIE - International Society for Optical Engineering, 2011, Vol. 7962, article id UNSP 79621MConference paper (Refereed)
    Abstract [en]

    To accelerate level-set based abdominal aorta segmentation on CTA data, we propose a periodic monotonic speed function, which allows segments of the contour to expand within one period and to shrink in the next period, i.e., coherent propagation. This strategy avoids the contour's local wiggling behavior which often occurs during the propagating when certain points move faster than the neighbors, as the curvature force will move them backwards even though the whole neighborhood will eventually move forwards. Using coherent propagation, these faster points will, instead, stay in their places waiting for their neighbors to catch up. A period ends when all the expanding/shrinking segments can no longer expand/shrink, which means that they have reached the border of the vessel or stopped by the curvature force. Coherent propagation also allows us to implement a modified narrow band level set algorithm that prevents the endless computation in points that have reached the vessel border. As these points' expanding/shrinking trend changes just after several iterations, the computation in the remaining iterations of one period can focus on the actually growing parts. Finally, a new convergence detection method is used to permanently stop updating the local level set function when the 0-level set is stationary in a voxel for several periods. The segmentation stops naturally when all points on the contour are stationary. In our preliminary experiments, significant speedup (about 10 times) was achieved on 3D data with almost no loss of segmentation accuracy.

  • 45.
    Wang, Chunliang
    et al.
    KTH, School of Technology and Health (STH), Medical Engineering, Medical Imaging. Linköping University, Sweden; Sectra AB, Sweden.
    Lundström, C.
    CT scan range estimation using multiple body parts detection: let PACS learn the CT image content2016In: International Journal of Computer Assisted Radiology and Surgery, ISSN 1861-6410, E-ISSN 1861-6429, Vol. 11, no 2, p. 317-325Article in journal (Refereed)
    Abstract [en]

    Purpose: The aim of this study was to develop an efficient CT scan range estimation method that is based on the analysis of image data itself instead of metadata analysis. This makes it possible to quantitatively compare the scan range of two studies. Methods: In our study, 3D stacks are first projected to 2D coronal images via a ray casting-like process. Trained 2D body part classifiers are then used to recognize different body parts in the projected image. The detected candidate regions go into a structure grouping process to eliminate false-positive detections. Finally, the scale and position of the patient relative to the projected figure are estimated based on the detected body parts via a structural voting. The start and end lines of the CT scan are projected to a standard human figure. The position readout is normalized so that the bottom of the feet represents 0.0, and the top of the head is 1.0. Results: Classifiers for 18 body parts were trained using 184 CT scans. The final application was tested on 136 randomly selected heterogeneous CT scans. Ground truth was generated by asking two human observers to mark the start and end positions of each scan on the standard human figure. When compared with the human observers, the mean absolute error of the proposed method is 1.2 % (max: 3.5 %) and 1.6 % (max: 5.4 %) for the start and end positions, respectively. Conclusion: We proposed a scan range estimation method using multiple body parts detection and relative structure position analysis. In our preliminary tests, the proposed method delivered promising results.

  • 46.
    Wang, Chunliang
    et al.
    Center for Medical Imaging Science and Visualization (CMIV),Department of Medical and Health Sciences (IMH).
    Moreno, Rodrigo
    Smedby, Örjan
    Linkönping University, Campus US.
    Vessel segmentation using implicit model-guided level sets2012In: : a MICCAI segmentation Challenge", Nice France, 1st of October 2012., 2012Conference paper (Refereed)
  • 47.
    Wang, Chunliang
    et al.
    Linköping University, Sweden.
    Persson, Anders
    Engvall, Jan
    De Geer, Jakob
    Czekierda, Waldemar
    Björkholm, Anders
    Fransson, Sven-Göran
    Smedby, Örjan
    Linköping University, Sweden.
    Can segmented 3D images be used for stenosis evaluation in coronary CT angiography?2012In: Acta Radiologica, ISSN 0284-1851, E-ISSN 1600-0455, Vol. 53, no 8, p. 845-851Article in journal (Refereed)
    Abstract [en]

    Background: Thanks to the development of computed tomography (CT) scanners and computer software, accurate coronary artery segmentation can be achieved with minimum user interaction. However, the question remains whether we can use these segmented images for reliable diagnosis. Purpose: To retrospectively evaluate the diagnostic accuracy of coronary CT angiography (CCTA) using segmented 3D data for the detection of significant stenosis. Material and Methods: CCTA data-sets from 30 patients were acquired with a 64-slice CT scanner and segmented using the region growing (RG) method and the "virtual contrast injection" (VC) method. Three types of images of each patient were reviewed by different reviewers for the presence of stenosis with diameter reduction of 50% or more. The evaluation was performed on four main arteries of each patient (120 arteries in total). For the original series, the reviewer was allowed to use all the 2D and 3D visualization tools available (conventional method). For the segmented results from RG and VC, only maximum intensity projection was used. Evaluation results were compared with catheter angiography (CA) for each artery in a blinded fashion. Results: Overall, 34 arteries with significant stenosis were identified by CA. The percentage of evaluable arteries, accuracy and negative predictive value for detecting stenosis were, respectively, 86%, 74%, and 93% for the conventional method, 83%, 71%, and 92% for VC, and 64%, 56%, and 93% for RG. Accuracy was significantly lower for the RG method than for the other two methods (P < 0.01), whereas there was no significant difference in accuracy between the VC method and the conventional method (P = 0.22). Conclusion: The diagnostic accuracy for the RG-segmented 3D data is lower than those with access to 2D images, whereas the VC method shows diagnostic accuracy similar to the conventional method.

  • 48.
    Wang, Chunliang
    et al.
    Linköping University, Sweden.
    Ritter, Felix
    Smedby, Örjan
    Linköping University, Sweden.
    Making the PACS workstation a browser of image processing software: a feasibility study using inter-process communication techniques2010In: International Journal of Computer Assisted Radiology and Surgery, ISSN 1861-6410, E-ISSN 1861-6429, Vol. 5, no 4, p. 411-419Article in journal (Refereed)
    Abstract [en]

    Purpose To enhance the functional expandability of a picture archiving and communication systems (PACS) workstation and to facilitate the integration of third-part image-processing modules, we propose a browser-server style method. Methods In the proposed solution, the PACS workstation shows the front-end user interface defined in an XML file while the image processing software is running in the background as a server. Inter-process communication (IPC) techniques allow an efficient exchange of image data, parameters, and user input between the PACS workstation and stand-alone image-processing software. Using a predefined communication protocol, the PACS workstation developer or image processing software developer does not need detailed information about the other system, but will still be able to achieve seamless integration between the two systems and the IPC procedure is totally transparent to the final user. Results A browser-server style solution was built between OsiriX (PACS workstation software) and MeVisLab (Image-Processing Software). Ten example image-processing modules were easily added to OsiriX by converting existing MeVisLab image processing networks. Image data transfer using shared memory added <10 ms of processing time while the other IPC methods cost 1-5 s in our experiments. Conclusion The browser-server style communication based on IPC techniques is an appealing method that allows PACS workstation developers and image processing software developers to cooperate while focusing on different interests.

  • 49.
    Wang, Chunliang
    et al.
    Dept. of Radiology (IMH) and Center for Medical Image Science and Visualization (CMIV), Linköping University.
    Smedby, Örjan
    Dept. of Radiology (IMH) and Center for Medical Image Science and Visualization (CMIV), Linköping University.
    An automatic seeding method for coronary artery segmentation and skeletonization in CTA2008In: MIDAS Journal, Vol. 43, p. 1-8Article in journal (Refereed)
    Abstract [en]

    An automatic seeding method for coronary artery segmentation and skeletonization is presented. The new method includes automatic removal of the rib cage, tracing of the ascending aorta and initial planting of seeds for the coronary arteries. The automatic seeds are then passed on to a �virtual contrast injection� algorithm performing segmentation and skeletonization. In preliminary experiments, most main branches of the coronary tree were segmented and skeletonized without any user interaction.

  • 50.
    Wang, Chunliang
    et al.
    Linköping University, Linköping, Sweden.
    Smedby, Örjan
    Linköping University, Linköping, Sweden.
    Automatic multi-organ segmentation in non-enhanced CT datasets using hierarchical shape priors2014In: 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), IEEE Computer Society, 2014, Vol. 6977285, p. 3327-3332Conference paper (Refereed)
    Abstract [en]

    An automatic multi-organ segmentation method using hierarchical-shape-prior guided level sets is proposed. The hierarchical shape priors are organized according to the anatomical hierarchy of the human body, so that major structures with less population variety are at the top and smaller structures with higher irregularities are linked at a lower level. The segmentation is performed in a top-down fashion, where major structures are first segmented with higher confidence, and their location information is then passed down to the lower level to initialize the segmentation, while boundary information from higher-level structures also provides extra cues to guide the segmentation of the lower-level structures. The proposed method was combined with a novel coherent propagating level set method, which is capable to detect local convergence and skip calculation in those parts, therefore significantly reducing computation time. Preliminary experiment results on a small number of clinical datasets are encouraging; the proposed method yielded a Dice coefficient above 90% for most major organs within a reasonable processing time without any user intervention.

12 1 - 50 of 59
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf