Learning osteoarthritis imaging biomarkers from bone surface spherical encoding
- 3 April 2020
- journal article
- research article
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 84 (4), 2190-2203
- https://doi.org/10.1002/mrm.28251
Abstract
Purpose To learn bone shape features from spherical bone map of knee MRI images using established convolutional neural networks (CNN) and use these features to diagnose and predict osteoarthritis (OA). Methods A bone segmentation model was trained on 25 manually annotated 3D MRI volumes to segment the femur, tibia, and patella from 47 078 3D MRI volumes. Each bone segmentation was converted to a 3D point cloud and transformed into spherical coordinates. Different fusion strategies were performed to merge spherical maps obtained by each bone. A total of 41 822 merged spherical maps with corresponding Kellgren‐Lawrence grades for radiographic OA were used to train a CNN classifier model to diagnose OA using bone shape learned features. Several OA Diagnosis models were tested and the weights for each trained model were transferred to the OA Incidence models. The OA incidence task consisted of predicting OA from a healthy scan within a range of eight time points, from 1 y to 8 y. The validation performance was compared and the test set performance was reported. Results The OA Diagnosis model had an area‐under‐the‐curve (AUC) of 0.905 on the test set with a sensitivity and specificity of 0.815 and 0.839. The OA Incidence models had an AUC ranging from 0.841 to 0.646 on the test set for the range from 1 y to 8 y. Conclusion Bone shape was successfully used as a predictive imaging biomarker for OA. This approach is novel in the field of deep learning applications for musculoskeletal imaging and can be expanded to other OA biomarkers.Funding Information
- National Institute of Arthritis and Musculoskeletal and Skin Diseases (R00AR070902, R61AR073552)
This publication has 32 references indexed in Scilit:
- The global burden of hip and knee osteoarthritis: estimates from the Global Burden of Disease 2010 studyAnnals Of The Rheumatic Diseases, 2014
- A novel method for bone area measurement provides new insights into osteoarthritis and its progressionAnnals Of The Rheumatic Diseases, 2013
- Statistical shape modeling of proximal femoral shape deformities in Legg–Calvé–Perthes disease and slipped capital femoral epiphysisOsteoarthritis and Cartilage, 2013
- Variant alleles of the Wnt antagonist FRZB are determinants of hip shape and modify the relationship between hip shape and osteoarthritisArthritis & Rheumatism, 2012
- Unsupervised learning of hierarchical representations with convolutional deep belief networksCommunications of the ACM, 2011
- Statistical shape modeling describes variation in tibia and femur surface geometry between Control and Incidence groups from the Osteoarthritis Initiative databaseJournal of Biomechanics, 2010
- The association of proximal femoral shape and incident radiographic hip OA in elderly womenOsteoarthritis and Cartilage, 2009
- The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the kneeOsteoarthritis and Cartilage, 2008
- Projections of US prevalence of arthritis and associated activity limitationsArthritis & Rheumatism, 2005
- Computed tomography-osteoabsorptiometry for assessing the density distribution of subchondral bone as a measure of long-term mechanical adaptation in individual jointsSkeletal Radiology, 1989