A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities

Multi-atlas based segmentation techniques constitute an effective approach in the automatic segmentation of medical images. Existing methods usually rely on single spectral descriptors extracted from a specific imaging modality. In this paper, we propose the Multi-View Knee Cartilage Segmentation (M...

Full description

Saved in:
Bibliographic Details
Main Authors: Christos G. Chadoulos, Dimitrios E. Tsaopoulos, Serafeim P. Moustakidis, John B. Theocharis
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21681163.2024.2332398
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846149851874590720
author Christos G. Chadoulos
Dimitrios E. Tsaopoulos
Serafeim P. Moustakidis
John B. Theocharis
author_facet Christos G. Chadoulos
Dimitrios E. Tsaopoulos
Serafeim P. Moustakidis
John B. Theocharis
author_sort Christos G. Chadoulos
collection DOAJ
description Multi-atlas based segmentation techniques constitute an effective approach in the automatic segmentation of medical images. Existing methods usually rely on single spectral descriptors extracted from a specific imaging modality. In this paper, we propose the Multi-View Knee Cartilage Segmentation (MV-KCS) approach, for segmenting the knee joint articular cartilage from MR images. Operating under the Semi-supervised learning framework, MV-KCS leverages spectral content from multiple feature spaces by constructing sparse graphs for each view individually, and aggregating them via optimisation to obtain a common data graph. In We consider two multi-view scenarios: in the former case views correspond to multiple feature descriptors, while on the latter, the views correspond to multiple image modalities. We propose two effective labelling schemes, implementing label propagation from the atlas library to the target image. The proposed methodology is applied to the publicly available Osteoarthritis Initiative repository. We devise a comprehensive experimental design to validate different test cases, comparing single-feature vs multi-features, multi-features vs feature stacking and multi-features vs multi-modalities. Comparative results and statistical analysis reveal that the proposed MV-KCS provides enhanced performance ([Formula: see text]), outperforming a series of patch-based approaches, six recent state-of-the-art deep supervised models and three deep semi-supervised ones, in terms of both classification and volumetric measures.
format Article
id doaj-art-9f26fce1968d410d9b527f519b16f4b4
institution Kabale University
issn 2168-1163
2168-1171
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
spelling doaj-art-9f26fce1968d410d9b527f519b16f4b42024-11-29T10:29:55ZengTaylor & Francis GroupComputer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization2168-11632168-11712024-12-0112110.1080/21681163.2024.2332398A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalitiesChristos G. Chadoulos0Dimitrios E. Tsaopoulos1Serafeim P. Moustakidis2John B. Theocharis3Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceInstitute for Bio-Economy and Agri-Technology, Centre for Research and Technology – Hellas, Volos, GreeceDepartment of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceMulti-atlas based segmentation techniques constitute an effective approach in the automatic segmentation of medical images. Existing methods usually rely on single spectral descriptors extracted from a specific imaging modality. In this paper, we propose the Multi-View Knee Cartilage Segmentation (MV-KCS) approach, for segmenting the knee joint articular cartilage from MR images. Operating under the Semi-supervised learning framework, MV-KCS leverages spectral content from multiple feature spaces by constructing sparse graphs for each view individually, and aggregating them via optimisation to obtain a common data graph. In We consider two multi-view scenarios: in the former case views correspond to multiple feature descriptors, while on the latter, the views correspond to multiple image modalities. We propose two effective labelling schemes, implementing label propagation from the atlas library to the target image. The proposed methodology is applied to the publicly available Osteoarthritis Initiative repository. We devise a comprehensive experimental design to validate different test cases, comparing single-feature vs multi-features, multi-features vs feature stacking and multi-features vs multi-modalities. Comparative results and statistical analysis reveal that the proposed MV-KCS provides enhanced performance ([Formula: see text]), outperforming a series of patch-based approaches, six recent state-of-the-art deep supervised models and three deep semi-supervised ones, in terms of both classification and volumetric measures.https://www.tandfonline.com/doi/10.1080/21681163.2024.2332398Osteoarthritis (OA)magnetic resonance imaging (MRI) segmentationmulti-view learningmulti-atlas patch-basedsemi-supervised learning (SSL)
spellingShingle Christos G. Chadoulos
Dimitrios E. Tsaopoulos
Serafeim P. Moustakidis
John B. Theocharis
A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Osteoarthritis (OA)
magnetic resonance imaging (MRI) segmentation
multi-view learning
multi-atlas patch-based
semi-supervised learning (SSL)
title A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
title_full A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
title_fullStr A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
title_full_unstemmed A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
title_short A Multi-View Semi-supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
title_sort multi view semi supervised learning method for knee joint cartilage segmentation combining multiple feature descriptors and image modalities
topic Osteoarthritis (OA)
magnetic resonance imaging (MRI) segmentation
multi-view learning
multi-atlas patch-based
semi-supervised learning (SSL)
url https://www.tandfonline.com/doi/10.1080/21681163.2024.2332398
work_keys_str_mv AT christosgchadoulos amultiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT dimitriosetsaopoulos amultiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT serafeimpmoustakidis amultiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT johnbtheocharis amultiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT christosgchadoulos multiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT dimitriosetsaopoulos multiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT serafeimpmoustakidis multiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities
AT johnbtheocharis multiviewsemisupervisedlearningmethodforkneejointcartilagesegmentationcombiningmultiplefeaturedescriptorsandimagemodalities