kth.sePublications
Planned maintenance
A system upgrade is planned for 10/12-2024, at 12:00-13:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Methods for the analysis and characterization of brain morphology from MRI images
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.ORCID iD: 0000-0003-3479-4243
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Brain magnetic resonance imaging (MRI) is an imaging modality that produces detailed images of the brain without using any ionizing radiation. From a structural MRI scan, it is possible to extract morphological properties of different brain regions, such as their volume and shape. These measures can both allow a better understanding of how the brain changes due to multiple factors (e.g., environmental and pathological) and contribute to the identification of new imaging biomarkers of neurological and psychiatric diseases. The overall goal of the present thesis is to advance the knowledge on how brain MRI image processing can be effectively used to analyze and characterize brain structure.

The first two works presented in this thesis are animal studies that primarily aim to use MRI data for analyzing differences between groups of interest. In Paper I, MRI scans from wild and domestic rabbits were processed to identify structural brain differences between these two groups. Domestication was found to significantly reshape brain structure in terms of both regional gray matter volume and white matter integrity. In Paper II, rat brain MRI scans were used to train a brain age prediction model. This model was then tested on both controls and a group of rats that underwent long-term environmental enrichment and dietary restriction. This healthy lifestyle intervention was shown to significantly affect the predicted brain age trajectories by slowing the rats' aging process compared to controls. Furthermore, brain age predicted on young adult rats was found to have a significant effect on survival.

Papers III to V are human studies that propose deep learning-based methods for segmenting brain structures that can be severely affected by neurodegeneration. In particular, Papers III and IV focus on U-Net-based 2D segmentation of the corpus callosum (CC) in multiple sclerosis (MS) patients. In both studies, good segmentation accuracy was obtained and a significant correlation was found between CC area and the patient's level of cognitive and physical disability. Additionally, in Paper IV, shape analysis of the segmented CC revealed a significant association between disability and both CC thickness and bending angle. Conversely, in Paper V, a novel method for automatic segmentation of the hippocampus is proposed, which consists of embedding a statistical shape prior as context information into a U-Net-based framework. The inclusion of shape information was shown to significantly improve segmentation accuracy when testing the method on a new unseen cohort (i.e., different from the one used for training). Furthermore, good performance was observed across three different diagnostic groups (healthy controls, subjects with mild cognitive impairment and Alzheimer's patients) that were characterized by different levels of hippocampal atrophy.

In summary, the studies presented in this thesis support the great value of MRI image analysis for the advancement of neuroscientific knowledge, and their contribution is mostly two-fold. First, by applying well-established processing methods on datasets that had not yet been explored in the literature, it was possible to characterize specific brain changes and disentangle relevant problems of a clinical or biological nature. Second, a technical contribution is provided by modifying and extending already-existing brain image processing methods to achieve good performance on new datasets.

Abstract [sv]

Magnetresonansbilder (MR-bilder) används för att framställa detaljerade bilder av hjärnan utan joniserande strålning. Från en strukturell MR-bild är det möjligt att extrahera morfologiska egenskaper hos hjärnans olika regioner, såsom deras volym och form. Dessa egenskaper kan ge bättre förståelse för förändringar som hjärnan utsätts för på grund av en mängd faktorer (exempelvis miljö eller sjukdom) samt bidra till att identifiera nya bildbaserade biomarkörer för neurologiska och psykiatriska sjukdomar. Den här avhandlingens huvudsakliga mål är att bidra till kunskapen om hur bildbehandling av MR-bilder kan användas för att analysera och karaktärisera hjärnstrukturer.

De två första delarbetena som ingår i avhandlingen är djurstudier som primärt avser att använda MR-data för att analysera skillnaderna mellan två kohorter. I Artikel I behandlas MR-bilder från domesticerade och vilda kaniner för att identifiera skillnader i hjärnstruktur mellan de två grupperna. Domesticering visade sig förändra hjärnstrukturen signifikant, både den gråa hjärnsubstansens volym och den vita hjärnsubstansens integritet. I Artikel II användes MR-bilder på råttor för att träna en datadriven modell att predicera hjärnålder. Modellen testades sedan på en kontrollgrupp och en grupp råttor som under flera månader utsattes för en mer stimulerande miljö samt fick en diet med restriktioner. Den mer hälsosamma livsstilen visade sig bidra till en lägre predicerad hjärnålder genom att sakta ner råttornas åldringsprocess, jämfört med kontrollgruppen. Hjärnåldern hos unga, vuxna råttor visade sig signifikant påverka råttornas överlevnad.

Artikel III, IV och V är människostudier som föreslår djupinlärningsbaserade metoder för att segmentera (avgränsa) hjärnstrukturer som kan påverkas av neurodegeneration. Artikel III och IV i synnerhet fokuserar på U-Net-baserad 2D-segmentering av corpus callosum (CC) hos patienter med multipel skleros. I båda studierna uppmättes god träffsäkerhet för segmenteringsalgoritmen och signifikant korrelation mellan CC:s area och patientens kognitiva och fysiska nedsättning. Utöver detta visar Artikel IV genom geometrisk analys av den segmenterade CC ett signifikant samband mellan sjukdom och CC:s tjocklek och böjvinkel. I Artikel V introduceras en ny metod för automatisk segmentering av hippocampus. Metoden kombinerar U-Net-baserad segmentering med en inbyggd statistisk representation av hippocampus’ form. Metoden visade sig ge en signifikant förbättring av segmenteringskvaliteten när metoden utvärderades på en ny, tidigare osedd, kohort. Goda resultat uppmättes även i tre olika diagnosgrupper (en frisk kontrollgrupp, patienter med milda kognitiva symptom och en grupp patienter med Alzheimers sjukdom) som särskilde sig genom tre olika nivåer av atrofi av hippocampus.

Sammanfattningsvis bidrar studierna som ingår i avhandlingen till att förstärka värdet av MR-bildanalys för framsteg inom neurovetenskapen, och detta på två sätt. Genom att applicera väletablerade bildbehandlingsmetoder på dataset som ännu inte utforskats i litteraturen var det möjligt att karaktärisera specifika förändringar i hjärnans geometri och därmed lösa relevanta kliniska eller biologiska utmaningar. Vidare har studierna  bidragit till den teknologiska metodutvecklingen genom att modifiera och utvidga existerande bildbehandlingsmetoder för hjärnbilder för att uppnå goda resultat på nya dataset.

Place, publisher, year, edition, pages
Stockholm, Sweden: KTH Royal Institute of Technology, 2022. , p. 129
Series
TRITA-CBH-FOU ; 2022:9
Keywords [en]
Brain MRI, Image Segmentation, Machine Learning, Deep Learning, Shape Analysis, Aging, Neurodegeneration
Keywords [sv]
MRT av hjärnan, Bildsegmentering, Maskininlärning, Djupinlärning, Formanalys, Åldrande, Neurodegeneration
National Category
Medical Image Processing Neurosciences Radiology, Nuclear Medicine and Medical Imaging
Research subject
Medical Technology
Identifiers
URN: urn:nbn:se:kth:diva-309321ISBN: 978-91-8040-138-8 (print)OAI: oai:DiVA.org:kth-309321DiVA, id: diva2:1640734
Public defence
2022-03-25, T2 (Jacobssonsalen) and via Zoom (https://kth-se.zoom.us/j/68019515028), Hälsovägen 11C, vån 5, Huddinge, 13:00 (English)
Opponent
Supervisors
Note

QC 2022-02-28

Available from: 2022-02-28 Created: 2022-02-25 Last updated: 2022-06-25Bibliographically approved
List of papers
1. Changes in brain architecture are consistent with altered fear processing in domestic rabbits
Open this publication in new window or tab >>Changes in brain architecture are consistent with altered fear processing in domestic rabbits
Show others...
2018 (English)In: 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) Published
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.

Place, publisher, year, edition, pages
National Academy of Sciences, 2018
Keywords
rabbit, domestication, brain morphology, magnetic resonance imaging, fear
National Category
Neurosciences
Identifiers
urn:nbn:se:kth:diva-232773 (URN)10.1073/pnas.1801024115 (DOI)000438050900076 ()29941556 (PubMedID)2-s2.0-85049643502 (Scopus ID)
Funder
Knut and Alice Wallenberg FoundationSwedish Research CouncilThe Swedish Brain Foundation
Note

QC 20180807

Available from: 2018-08-07 Created: 2018-08-07 Last updated: 2024-03-15Bibliographically approved
2. MRI-derived brain age as a biomarker of ageing in rats: validation using a healthy lifestyle intervention
Open this publication in new window or tab >>MRI-derived brain age as a biomarker of ageing in rats: validation using a healthy lifestyle intervention
Show others...
2022 (English)In: Neurobiology of Aging, ISSN 0197-4580, E-ISSN 1558-1497, Vol. 109, p. 204-215Article in journal (Refereed) Published
Abstract [en]

The difference between brain age predicted from MRI and chronological age (the so-called BrainAGE) has been proposed as an ageing biomarker. We analyse its cross-species potential by testing it on rats undergoing an ageing modulation intervention. Our rat brain age prediction model combined Gaussian process regression with a classifier and achieved a mean absolute error (MAE) of 4.87 weeks using cross-validation on a longitudinal dataset of 31 normal ageing rats. It was then tested on two groups of 24 rats (MAE = 9.89 weeks, correlation coefficient = 0.86): controls vs. a group under long-term environmental enrichment and dietary restriction (EEDR). Using a linear mixed-effects model, BrainAGE was found to increase more slowly with chronological age in EEDR rats ( p = 0 . 015 for the interaction term). Cox re-gression showed that older BrainAGE at 5 months was associated with higher mortality risk ( p = 0 . 03 ). Our findings suggest that lifestyle-related prevention approaches may help to slow down brain ageing in rodents and the potential of BrainAGE as a predictor of age-related health outcomes.

Place, publisher, year, edition, pages
Elsevier BV, 2022
Keywords
Brain ageing, Rat models, BrainAGE, Neuroimaging, Biomarker, Machine learning
National Category
Neurology Neurosciences
Identifiers
urn:nbn:se:kth:diva-305624 (URN)10.1016/j.neurobiolaging.2021.10.004 (DOI)000719182000004 ()34775211 (PubMedID)2-s2.0-85118834103 (Scopus ID)
Note

QC 20211206

Available from: 2021-12-06 Created: 2021-12-06 Last updated: 2022-06-25Bibliographically approved
3. Automatic deep learning multicontrast corpus callosum segmentation in multiple sclerosis
Open this publication in new window or tab >>Automatic deep learning multicontrast corpus callosum segmentation in multiple sclerosis
Show others...
2022 (English)In: Journal of Neuroimaging, ISSN 1051-2284, E-ISSN 1552-6569Article in journal (Refereed) Published
Place, publisher, year, edition, pages
Wiley, 2022
National Category
Medical Image Processing
Identifiers
urn:nbn:se:kth:diva-308582 (URN)10.1111/jon.12972 (DOI)000747288000001 ()35083815 (PubMedID)2-s2.0-85123723211 (Scopus ID)
Funder
Stockholm County CouncilSwedish Society for Medical Research (SSMF)
Note

QC 20220214

Available from: 2022-02-11 Created: 2022-02-11 Last updated: 2022-06-25Bibliographically approved
4. Deep Learning Corpus Callosum Segmentation as a Neurodegenerative Marker in Multiple Sclerosis.
Open this publication in new window or tab >>Deep Learning Corpus Callosum Segmentation as a Neurodegenerative Marker in Multiple Sclerosis.
Show others...
2021 (English)In: Journal of Neuroimaging, ISSN 1051-2284, E-ISSN 1552-6569, Vol. 31, no 3, p. 493-500Article in journal (Refereed) Published
Abstract [en]

BACKGROUND AND PURPOSE: Corpus callosum atrophy is a sensitive biomarker of multiple sclerosis (MS) neurodegeneration but typically requires manual 2D or volumetric 3D-based segmentations. We developed a supervised machine learning algorithm, DeepnCCA, for corpus callosum segmentation and relate callosal morphology to clinical disability using conventional MRI scans collected in clinical routine.

METHODS: In a prospective study of 553 MS patients with 704 acquisitions, 200 unique 2D T2 -weighted MRI scans were delineated to develop, train, and validate DeepnCCA. Comparative FreeSurfer segmentations were obtained in 504 3D T1 -weighted scans. Both FreeSurfer and DeepnCCA outputs were correlated with clinical disability. Using principal component analysis of the DeepnCCA output, the morphological changes were explored in relation to clinical disease burden.

RESULTS: .76%, for intracranial and corpus callosum area, respectively through 10-fold cross-validation). DeepnCCA had numerically stronger correlations with cognitive and physical disability as compared to FreeSurfer: Expanded disability status scale (EDSS) ±6 months (r = -.22 P = .002; r = -.17, P = .013), future EDSS (r = -.26, P<.001; r = -.17, P = .012), and future symbol digit modalities test (r = .26, P = .001; r = .24, P = .003). The corpus callosum became thinner with increasing cognitive and physical disability. Increasing physical disability, additionally, significantly correlated with a more angled corpus callosum.

CONCLUSIONS: DeepnCCA (https://github.com/plattenmichael/DeepnCCA/) is an openly available tool that can provide fast and accurate corpus callosum measurements applicable to large MS cohorts, potentially suitable for monitoring disease progression and therapy response.

Place, publisher, year, edition, pages
Wiley, 2021
Keywords
Multiple sclerosis, artificial intelligence, corpus callosum, deep learning, magnetic resonance imaging
National Category
Medical Image Processing Neurology
Identifiers
urn:nbn:se:kth:diva-294607 (URN)10.1111/jon.12838 (DOI)000618033600001 ()33587820 (PubMedID)2-s2.0-85101425445 (Scopus ID)
Note

QC 20210527

Available from: 2021-05-18 Created: 2021-05-18 Last updated: 2022-12-16Bibliographically approved
5. Shape Information Improves the Cross-Cohort Performance of Deep Learning-Based Segmentation of the Hippocampus
Open this publication in new window or tab >>Shape Information Improves the Cross-Cohort Performance of Deep Learning-Based Segmentation of the Hippocampus
Show others...
2020 (English)In: Frontiers in Neuroscience, ISSN 1662-4548, E-ISSN 1662-453X, Vol. 14, article id 15Article in journal (Refereed) Published
Abstract [en]

Performing an accurate segmentation of the hippocampus from brain magnetic resonance images is a crucial task in neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, including Alzheimer's disease (AD). Some automatic segmentation tools are already being used, but, in recent years, new deep learning (DL)-based methods have been proven to be much more accurate in various medical image segmentation tasks. In this work, we propose a DL-based hippocampus segmentation framework that embeds statistical shape of the hippocampus as context information into the deep neural network (DNN). The inclusion of shape information is achieved with three main steps: (1) a U-Net-based segmentation, (2) a shape model estimation, and (3) a second U-Net-based segmentation which uses both the original input data and the fitted shape model. The trained DL architectures were tested on image data of three diagnostic groups [AD patients, subjects with mild cognitive impairment (MCI) and controls] from two cohorts (ADNI and AddNeuroMed). Both intra-cohort validation and cross-cohort validation were performed and compared with the conventional U-net architecture and some variations with other types of context information (i.e., autocontext and tissue-class context). Our results suggest that adding shape information can improve the segmentation accuracy in cross-cohort validation, i.e., when DNNs are trained on one cohort and applied to another. However, no significant benefit is observed in intra-cohort validation, i.e., training and testing DNNs on images from the same cohort. Moreover, compared to other types of context information, the use of shape context was shown to be the most successful in increasing the accuracy, while keeping the computational time in the order of a few minutes.

Place, publisher, year, edition, pages
Frontiers Media S.A., 2020
Keywords
hippocampus, brain MRI, Alzheimer's disease, image segmentation, deep learning, statistical shape model
National Category
Medical Engineering
Identifiers
urn:nbn:se:kth:diva-272919 (URN)10.3389/fnins.2020.00015 (DOI)000525602400001 ()32226359 (PubMedID)2-s2.0-85082698631 (Scopus ID)
Note

QC 20210607

Available from: 2020-05-27 Created: 2020-05-27 Last updated: 2024-03-18Bibliographically approved

Open Access in DiVA

Kappa_IreneBrusini(19219 kB)1446 downloads
File information
File name FULLTEXT01.pdfFile size 19219 kBChecksum SHA-512
67a1f3e4f4fad151e33ca758d1accf00a250aa2e54b4326d27f68d4bd4acae642385e02fab378e2457f0cf01cf335634afc9ba6d5177c7dd82ac15db620e4728
Type fulltextMimetype application/pdf

Authority records

Brusini, Irene

Search in DiVA

By author/editor
Brusini, Irene
By organisation
Medical Imaging
Medical Image ProcessingNeurosciencesRadiology, Nuclear Medicine and Medical Imaging

Search outside of DiVA

GoogleGoogle Scholar
Total: 1446 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1027 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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