Deep-learning based quantification model for hip bone marrow edema and synovitis in patients with spondyloarthritis based on magnetic resonance images

Yan Zheng; Chao Bai; Kui Zhang; Qing Han; Qingbiao Guan; Ying Liu; Zhaohui Zheng; Yong Xia; Ping Zhu

doi:10.3389/fphys.2023.1132214

Deep-learning based quantification model for hip bone marrow edema and synovitis in patients with spondyloarthritis based on magnetic resonance images

Front Physiol. 2023 Mar 3:14:1132214. doi: 10.3389/fphys.2023.1132214. eCollection 2023.

Authors

Yan Zheng^{1

2}, Chao Bai³, Kui Zhang^{1

2}, Qing Han^{1

2}, Qingbiao Guan³, Ying Liu⁴, Zhaohui Zheng^{1

2}, Yong Xia³, Ping Zhu^{1

2}

Affiliations

¹ Department of Clinical Immunology, Xijing Hospital, Fourth Military Medical University, Xi'an, China.
² National Translational Science Center for Molecular Medicine, Xi'an, China.
³ National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China.
⁴ Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi'an, China.

Abstract

Objectives: Hip inflammation is one of the most common complications in patients with spondyloarthritis (SpA). Herein, we employed use of a deep learning-based magnetic resonance imaging (MRI) evaluation model to identify irregular and multiple inflammatory lesions of the hip. Methods: All of the SpA patients were enrolled at the Xijing Hospital. The erythrocyte sediment rate (ESR), C-reactive protein (CRP), hip function Harris score, and disease activity were evaluated by clinicians. Manual MRI annotations including bone marrow edema (BME) and effusion/synovitis, and a hip MRI scoring system (HIMRISS) assessment was performed by experienced musculoskeletal radiologists. The segmentation accuracies of four deep learning models, including U-Net, UNet++, Attention-Unet, and HRNet, were compared using five-fold cross-validation. The clinical agreement of U-Net was evaluated with clinical symptoms and HIMRISS results. Results: A total of 1945 MRI slices of STIR/T2WI sequences were obtained from 195 SpA patients with hip involvement. After the five-fold cross-validation, U-Net achieved an average segmentation accuracy of 88.48% for the femoral head and 69.36% for inflammatory lesions, which are higher than those obtained by the other three models. The UNet-score, which was calculated based on the same MRI slices as HIMRISS, was significantly correlated with the HIMRISS scores and disease activity indexes (p values <0.05). Conclusion: This deep-learning based automatic MRI evaluation model could achieve similar quantification performance as an expert radiologist, and it has the potential to improve the accuracy and efficiency of clinical diagnosis for SpA patients with hip involvement.

Keywords: deep learning; hip; magnetic resonance imaging; spondyloarthritis; synovitis.

Grants and funding

KZ received funding from the National Natural Science Foundation of China (81871273). YX received funding from the Key Research and Development Program of Shaanxi Province (2022GY-084) and the National Natural Science Foundation of China (62171377). PZ received funding from the Major Research Plan of the National Natural Science Foundation of China (92169211). The funders had no role in the study design, data collection, analysis, decision to publish or preparation of the manuscript.