Automatic quantification of osteoarthritis features in MRI using deep learning methods

Simple item page
dc.contributor.advisorRonsky, Janet L.
dc.contributor.authorFelfeliyan, Banafshe
dc.contributor.committeememberJaremko, Jacob L.
dc.contributor.committeememberLebel, Marc R.
dc.contributor.committeememberLi, Matthew D.
dc.contributor.committeememberWong, Andy K.
dc.contributor.committeememberFar, Behrouz
dc.contributor.committeememberForkert, Nils D.
dc.date2023-06
dc.date.accessioned2023-03-22T17:13:40Z
dc.date.available2023-03-22T17:13:40Z
dc.date.issued2023-03-20
dc.description.abstractOsteoarthritis (OA) is a progressive irreversible disease that affects the whole joint involving various tissues including cartilage, bone, and synovium. Accurate OA diagnosis and management requires a thorough understanding of its pathogenesis, along with precise monitoring of its trajectories and changes associated with treatment. Magnetic resonance imaging (MRI) is an excellent tool for understanding OA progression and diagnosis. However, its assessment relies on reader-dependent semiquantitative scores, which are subjective, laborious, and insensitive to small changes. An automated OA assessment pipeline using deep learning (DL) can overcome limitations but faces challenges, including low generalizability, label scarcity, and noisy clinical labels with high variability. Therefore, this thesis’s objective is to overcome challenges associated with automated OA assessment by developing DL methods for the quantitative assessment of predominant OA biomarkers (cartilage, effusion-synovitis, and bone marrow lesion (BML)). This thesis proposed ImprovedMaskRCNN (iMaskRCNN), an accurate DL algorithm for multiscale segmentation of tissues involved in OA (femur, tibia, femoral and tibial cartilages, and hip effusion), which improves Dice score by 1-7%. Algorithm outputs are used to quantify cartilage thickness and hip effusion volume. An unsupervised domain adaptation pipeline using iMaskRCNN and CycleGAN was proposed to overcome DL’s low generalizability across MRI sequences. Therefore, a weakly supervised training strategy was proposed for BML segmentation, using soft labels obtained from clinical scoring and a noise-robust loss, which increased the Dice score and recall by 8% and 22%, respectively. Effusion segmentation was achieved using a self-supervised learning approach to pretrain the iMaskRCNN algorithm for training with a few-labeled dataset and improved the Dice by more than 8%. Following validation of the developed methods, results were compared with patient outcomes indicating strong associations of the extracted BML and effusion features (Δpain vs. ΔDL-effusion r =0.59, and Δpain vs. Δtibial BML r=0.49). This research provides an efficient integrated tool for quantifying OA features from MRI to accurately monitor OA progression and structural changes. This tool enables large population analyses and the extraction of more sensitive measures for clinicians to understand OA. The proposed methods have strong potential to apply to other joints, tissues, and medical image analysis problems.en_US
dc.identifier.citationFelfeliyan, B. (2023). Automatic quantification of osteoarthritis features in MRI using deep learning methods (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.en_US
dc.identifier.urihttp://hdl.handle.net/1880/115953
dc.identifier.urihttps://dx.doi.org/10.11575/PRISM/40802
dc.language.isoengen_US
dc.publisher.facultySchulich School of Engineeringen_US
dc.publisher.institutionUniversity of Calgaryen
dc.rightsUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.en_US
dc.subjectMRIen_US
dc.subjectDeep-Learningen_US
dc.subjectImage segmentationen_US
dc.subjectMachine Learningen_US
dc.subjectMedical Imagingen_US
dc.subjectSelf Supervised Learningen_US
dc.subjectWeakly Supervised Learningen_US
dc.subjectDomain Adaptationen_US
dc.subjectBoneen_US
dc.subjectCartilageen_US
dc.subjectBone marrow lesionen_US
dc.subjectEffusion-synovitisen_US
dc.subjectOsteoarthritisen_US
dc.subject.classificationEducation--Healthen_US
dc.subject.classificationRadiologyen_US
dc.subject.classificationComputer Scienceen_US
dc.subject.classificationEngineering--Biomedicalen_US
dc.titleAutomatic quantification of osteoarthritis features in MRI using deep learning methodsen_US
dc.typedoctoral thesisen_US
thesis.degree.disciplineEngineering – Biomedicalen_US
thesis.degree.grantorUniversity of Calgaryen_US
thesis.degree.nameDoctor of Philosophy (PhD)en_US
ucalgary.item.requestcopyfalseen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ucalgary_2023_felfeliyan_banafshe.pdf
Size:
57.04 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.62 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Open Theses and Dissertations