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
Quantitative MRI Biomarkers of Neurodegeneration in Multiple Sclerosis
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging. Karolinska Institutet. (Smedby / Granberg)
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Background: Multiple sclerosis (MS) is a chronic neuroinflammatory and neurodegenerative disease that targets myelin in the brain and spinal cord. The corpus callosum connects the cerebral hemispheres and is composed of heavily myelinated axons. Atrophy of the corpus callosum has been explored as a more sensitive marker of disease status and neurodegeneration relative to other neuroanatomical structures. However, development of more accurate, precise and less labor demanding tools for characterizing callosal atrophy would increase its potential as a proxy marker of MS evolution.

Purpose: The primary objective of this thesis was to evaluate and develop quantitative methods for measuring neurodegeneration in MS with a focus on the corpus callosum. This was achieved through the comparison of the accuracy and precision of manual delineation, conventional volumetric methods, and machine learning approaches.

Study I: In a prospective study, 9 MS patients underwent scan/re-scanning with and without repositioning to measure the precision and accuracy of manual versus volumetric cross-sectional and longitudinal FreeSurfer analyses. While the longitudinal stream of FreeSurfer revealed the highest precision, the overall limitations on accuracy warrants caution.

Study II: In a prospective study, 553 MS patients with 704 2D T2-weighted MRI acquisitions were used to train and validate a machine learning algorithm for segmenting a marker of neurodegeneration. The algorithm quickly produced highly accurate segmentations of the corpus callosum and brain (Dice Coefficient: 89% and 98%, respectively). The algorithm had numerically higher correlations to neurologic disability as compared to FreeSurfer.

Study III: Analogous to Study II, in a prospective study, 631 MS patients with 3D T1-weighted and T2-weighted FLAIR acquisitions were used to train and validate a machine learning algorithm for segmenting the mid-sagittal normalized corpus callosum area. The algorithm performed better with T1-weighted scans and less atrophied patients. Scanner parameters had no significant effect on the T1-weighted output. The algorithm produced segmentations in less than a minute per scan, with similar correlations to neurologic disability, as compared to FreeSurfer.

Study IV: In a prospective study, 92 MS patients acquired both 3 and 7 Tesla brain MRI scans to reveal the lobe-specific lesion volumes’ association to corpus callosum atrophy, where lesion burden was found to be greatest in the frontal and parietal lobes. In addition, the posterior portions of the corpus callosum provided the strongest fit linear regression models, with a combination of white matter lesions and intracortical lesions predicting atrophy.

Conclusions: Creating and evaluating novel tools for measuring neurodegeneration over time is important both for monitoring disease progression and to evaluate therapeutic responses with current drugs. As novel therapeutic strategies appear, it may also help in assessing neuroregenerative approaches.

Abstract [sv]

Bakgrund: Multipel skleros (MS) är en kronisk inflammatorisk och neurodegenerativ sjukdom som drabbar hjärnan och ryggmärgen. Corpus callosum är en anatomisk struktur som förbinder de två hjärnhalvorna. Storleksminskning, så kallad atrofi, av corpus callosum är en etablerad skademarkör vid MS eftersom corpus callosum innehåller stor mängd myelin; det isoleringsskikt kring nervtrådarna som skadas vid MS. Atrofi är kopplat till sämre sjukdomsprognos vid MS och det är därför viktigt att ha robusta och exakta verktyg för att mäta detta.

Syfte: Huvudsyftet med denna doktorsavhandling var att utvärdera och utveckla kvantitativa metoder för att mäta atrofi i corpus callosum vid MS. Detta uppnåddes genom jämförelse av manuella metoder, tidigare utvecklade automatiska metoder samt egen utveckling av nya mätmetoder baserade på artificiell intelligens.

Studie I: 9 MS-patienter undersöktes upprepade gånger, utan och med omplacering, i tre olika magnetkameror (MR) för att jämföra precision och riktighet i manuella kontra volymetriska FreeSurfer-analyser. Medan FreeSurfer resulterade i hög precision, finns det begränsningar i dess riktighet, varför vi manar till försiktighet vid användning.

Studie II: 553 MS-patienter med 704 T2-viktade MR-undersökningar undersöktes för att utveckla, träna, och validera en maskininlärningsalgoritm för att mäta tvärsnittsarean av corpus callosum och intrakraniella ytan. Algoritmen producerade snabba och exakta segmenteringar av corpus callosum (Dice-koefficient: 89%) och intrakraniella ytan (Dice-koefficient: 98%). Algoritmen visade numeriskt högre korrelationer till klinisk neurologisk funktionsnedsättning jämfört med FreeSurfer.

Studie III: Analogt med Studie II, skannades 631 MS-patienter med 3D T1-viktade och T2-viktade FLAIR bilder från tre olika MR-kameror som användes för att utveckla, träna och validera en maskininlärningsalgoritm för att segmentera corpus callosum och intrakraniella ytan. Algoritmen fungerade bättre på T1-viktade bilder och bland patienter med mindre atrofi. Algoritmen hade kliniska korrelationer i paritet med FreeSurfer. 

Studie IV: 92 MS-patienter skannades med både 3 och 7 Tesla MR-kameror för att utvärdera sambandet mellan hjärnlobernas lesionsbörda med neurodegeneration. Studien fann att lesionsbördan var högst i frontal- och parietalloberna. De bakre delarna av corpus callosum, som har fler lobspecifika nervbanor, hade bättre regressionsmodeller jämfört med de främre delarna.

Slutsatser: Corpus callosum är en robust markör för neurodegeneration vid MS. Därför är utvärdering och skapande av nya verktyg för att mäta dess utveckling över tid värdefull. Allteftersom nya terapier utvecklas blir rollen av dessa verktyg desto viktigare. Förhoppningen är att kunna utvärdera terapiernas förebyggande av neurodegeneration samt dess potentiella neuro-regenerering.

Place, publisher, year, edition, pages
Stockholm: KTH , 2022. , p. 70
Series
TRITA-CBH-FOU ; 2022:10
Keywords [en]
Machine learning, Multiple sclerosis, Corpus callosum, Neurodegeneration
National Category
Neurosciences
Research subject
Medical Technology
Identifiers
URN: urn:nbn:se:kth:diva-309100ISBN: 978-91-8016-476-4 (print)OAI: oai:DiVA.org:kth-309100DiVA, id: diva2:1639434
Public defence
2022-03-25, Rappesalen, Alfred Nobels Allé 10, Huddinge, 09:00 (English)
Opponent
Supervisors
Note

Two Ph.D. titles are award: Medical Technology and Medical Sciences. Through the joint degree program between KI and KTH

QC 2022-02-22

Available from: 2022-02-22 Created: 2022-02-21 Last updated: 2022-06-25Bibliographically approved
List of papers
1. MRI-Based Manual versus Automated Corpus Callosum Volumetric Measurements in Multiple Sclerosis
Open this publication in new window or tab >>MRI-Based Manual versus Automated Corpus Callosum Volumetric Measurements in Multiple Sclerosis
Show others...
2019 (English)In: Journal of Neuroimaging, ISSN 1051-2284, E-ISSN 1552-6569Article in journal (Refereed) Published
Abstract [en]

BACKGROUND AND PURPOSE

Corpus callosum atrophy is a neurodegenerative biomarker in multiple sclerosis (MS). Manual delineations are gold standard but subjective and labor intensive. Novel automated methods are promising but require validation. We aimed to compare the robustness of manual versus automatic corpus callosum segmentations based on FreeSurfer.

METHODS

Nine MS patients (6 females, age 38 ± 13 years, disease duration 7.3 ± 5.2 years) were scanned twice with repositioning using 3‐dimensional T1‐weighted magnetic resonance imaging on three scanners (two 1.5 T and one 3.0 T), that is, six scans/patient, on the same day. Normalized corpus callosum areas were measured independently by a junior doctor and neuroradiologist. The cross‐sectional and longitudinal streams of FreeSurfer were used to segment the corpus callosum volume.

RESULTS

Manual measurements had high intrarater (junior doctor .96 and neuroradiologist .96) and interrater agreement (.94), by intraclass correlation coefficient (P < .001). The coefficient of variation was lowest for longitudinal FreeSurfer (.96% within scanners; 2.0% between scanners) compared to cross‐sectional FreeSurfer (3.7%, P = .001; 3.8%, P = .058) and the neuroradiologist (2.3%, P = .005; 2.4%, P = .33). Longitudinal FreeSurfer was also more accurate than cross‐sectional (Dice scores 83.9 ± 7.5% vs. 78.9 ± 8.4%, P < .01 relative to manual segmentations). The corpus callosum measures correlated with physical disability (longitudinal FreeSurfer r = –.36, P < .01; neuroradiologist r = –.32, P < .01) and cognitive disability (longitudinal FreeSurfer r = .68, P < .001; neuroradiologist r = .64, P < .001).

CONCLUSIONS

FreeSurfer's longitudinal stream provides corpus callosum measures with better repeatability than current manual methods and with similar clinical correlations. However, due to some limitations in accuracy, caution is warranted when using FreeSurfer with clinical data.

Place, publisher, year, edition, pages
John Wiley & Sons, 2019
National Category
Medical Laboratory and Measurements Technologies
Identifiers
urn:nbn:se:kth:diva-268294 (URN)10.1111/jon.12676 (DOI)000520615500009 ()31750599 (PubMedID)2-s2.0-85075375287 (Scopus ID)
Note

QC 20200313

Available from: 2020-03-13 Created: 2020-03-13 Last updated: 2024-03-15Bibliographically approved
2. 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
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. Cortical and white matter lesion topology influences focal corpus callosum atrophy in multiple sclerosis
Open this publication in new window or tab >>Cortical and white matter lesion topology influences focal corpus callosum atrophy 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
Neurosciences Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:kth:diva-308855 (URN)10.1111/jon.12977 (DOI)000754871600001 ()35165979 (PubMedID)2-s2.0-85124713998 (Scopus ID)
Note

QC 20220222

Available from: 2022-02-15 Created: 2022-02-15 Last updated: 2023-07-17Bibliographically approved

Open Access in DiVA

fulltext(17572 kB)646 downloads
File information
File name FULLTEXT03.pdfFile size 17572 kBChecksum SHA-512
f740cb4e0bccc5b0eb4f1c3526957abf9409f62d7118467ca6ec3f5017bd02dcbfb27d4550b52000d2ee00ab8700041e836b733ecc719e10f507908820b81e86
Type fulltextMimetype application/pdf

Authority records

Platten, Michael

Search in DiVA

By author/editor
Platten, Michael
By organisation
Medical Imaging
Neurosciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 650 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: 695 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