A deep learning method for predicting knee osteoarthritis radiographic progression from MRI

Background The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs. Methods Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OA...

Full description

Saved in:

Bibliographic Details
Published in:	Arthritis research & therapy Vol. 23; no. 1; pp. 1 - 262
Main Authors:	Schiratti, Jean-Baptiste, Dubois, Rémy, Herent, Paul, Cahané, David, Dachary, Jocelyn, Clozel, Thomas, Wainrib, Gilles, Keime-Guibert, Florence, Lalande, Agnes, Pueyo, Maria, Guillier, Romain, Gabarroca, Christine, Moingeon, Philippe
Format:	Journal Article
Language:	English
Published:	London BioMed Central Ltd 18-10-2021 BioMed Central BMC
Subjects:	Arthritis Automation Cartilage Deep learning Development and progression Machine learning Magnetic resonance imaging Osteoarthritis Pain Patients Performance evaluation Prognosis Teaching methods X-rays France United States > US
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Background The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs. Methods Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OAI) database , we implemented a deep learning method to predict, from MR images and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months. Results Using COR IW TSE images, our classification model achieved a ROC AUC score of 65%. On a similar task, trained radiologists obtained a ROC AUC score of 58.7% highlighting the difficulty of the classification task. Additional analyses conducted in parallel to predict pain grade evaluated by the WOMAC pain index achieved a ROC AUC score of 72%. Attention maps provided evidence for distinct specific areas as being relevant in those two predictive models, including the medial joint space for JSN progression and the intra-articular space for pain prediction. Conclusions This feasibility study demonstrates the interest of deep learning applied to OA, with a potential to support even trained radiologists in the challenging task of identifying patients with a high-risk of disease progression.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1478-6362 1478-6354 1478-6362
DOI:	10.1186/s13075-021-02634-4