Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Simultaneous MR knee image segmentation and bias field correction using deep learning and partial convolution
KTH, Skolan för kemi, bioteknologi och hälsa (CBH), Medicinteknik och hälsosystem. Novamia AB, Uppsala, Sweden.
KTH, Skolan för kemi, bioteknologi och hälsa (CBH), Medicinteknik och hälsosystem, Medicinsk avbildning. Novamia AB, Uppsala, Sweden.ORCID-id: 0000-0002-7750-1917
KTH, Skolan för kemi, bioteknologi och hälsa (CBH), Medicinteknik och hälsosystem, Medicinsk avbildning. Novamia AB, Uppsala, Sweden.ORCID-id: 0000-0002-0442-3524
2019 (engelsk)Inngår i: Medical Imaging 2019: Image Processing, SPIE - International Society for Optical Engineering, 2019, Vol. 10949, artikkel-id 1094909Konferansepaper, Publicerat paper (Fagfellevurdert)
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.

sted, utgiver, år, opplag, sider
SPIE - International Society for Optical Engineering, 2019. Vol. 10949, artikkel-id 1094909
Serie
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, ISSN 1605-7422 ; 10949
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-258892DOI: 10.1117/12.2512950ISI: 000483012700008Scopus ID: 2-s2.0-85068319000ISBN: 9781510625457 (tryckt)OAI: oai:DiVA.org:kth-258892DiVA, id: diva2:1350234
Konferanse
Medical Imaging 2019: Image Processing; San Diego; United States; 19 February 2019 through 21 February 2019
Merknad

QC 20190913

Tilgjengelig fra: 2019-09-11 Laget: 2019-09-11 Sist oppdatert: 2019-09-26bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Smedby, Örjan

Søk i DiVA

Av forfatter/redaktør
Wan, FengkaiSmedby, ÖrjanWang, Chunliang
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 90 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf