Associating Knee Osteoarthritis Progression with Temporal-Regional Graph Convolutional Network Analysis on MR Images

Jiaping Hu; Junyi Peng; Zidong Zhou; Tianyun Zhao; Lijie Zhong; Keyan Yu; Kexin Jiang; Tzak Sing Lau; Chuan Huang; Lijun Lu; Xiaodong Zhang

doi:10.1002/jmri.29412

Associating Knee Osteoarthritis Progression with Temporal-Regional Graph Convolutional Network Analysis on MR Images

J Magn Reson Imaging. 2024 Apr 30. doi: 10.1002/jmri.29412. Online ahead of print.

Authors

Jiaping Hu¹, Junyi Peng^{2

3}, Zidong Zhou^{2

3}, Tianyun Zhao^{4

5}, Lijie Zhong¹, Keyan Yu⁶, Kexin Jiang¹, Tzak Sing Lau⁷, Chuan Huang^{4

7}, Lijun Lu^{2

3

8}, Xiaodong Zhang¹

Affiliations

¹ Department of Medical Imaging, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics· Guangdong Province), Guangzhou, China.
² School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, China.
³ Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, China.
⁴ Department of Radiology and Imaging Sciences, Emory University, Atlanta, Georgia, USA.
⁵ Department of Biomedical Engineering, Stony Brook University, Stony Brook, New York, USA.
⁶ Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China.
⁷ Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA.
⁸ Pazhou Lab, Guangzhou, China.

PMID: 38686707
DOI: 10.1002/jmri.29412

Abstract

Background: Artificial intelligence shows promise in assessing knee osteoarthritis (OA) progression on MR images, but faces challenges in accuracy and interpretability.

Purpose: To introduce a temporal-regional graph convolutional network (TRGCN) on MR images to study the association between knee OA progression status and network outcome.

Study type: Retrospective.

Population: 194 OA progressors (mean age, 62 ± 9 years) and 406 controls (mean age, 61 ± 9 years) from the OA Initiative were randomly divided into training (80%) and testing (20%) cohorts.

Field strength/sequence: Sagittal 2D IW-TSE-FS (IW) and 3D-DESS-WE (DESS) at 3T.

Assessment: Anatomical subregions of cartilage, subchondral bone, meniscus, and the infrapatellar fat pad at baseline, 12-month, and 24-month were automatically segmented and served as inputs to form compartment-based graphs for a TRGCN model, which containing both regional and temporal information. The performance of models based on (i) clinical variables alone, (ii) radiologist score alone, (iii) combined features (containing i and ii), (iv) composite TRGCN (combining TRGCN, i and ii), (v) radiomics features, (vi) convolutional neural network based on Densenet-169 were compared.

Statistical tests: DeLong test was performed to compare the areas under the ROC curve (AUC) of all models. Additionally, interpretability analysis was done to evaluate the contributions of individual regions. A P value <0.05 was considered significant.

Results: The composite TRGCN outperformed all other models with AUCs of 0.841 (DESS) and 0.856 (IW) in the testing cohort (all P < 0.05). Interpretability analysis highlighted cartilage's importance over other structures (42%-45%), tibiofemoral joint's (TFJ) dominance over patellofemoral joint (PFJ) (58%-67% vs. 12%-37%), and importance scores changes in compartments over time (TFJ vs. PFJ: baseline: 44% vs. 43%, 12-month: 52% vs. 39%, 24-month: 31% vs. 48%).

Data conclusion: The composite TRGCN, capturing temporal and regional information, demonstrated superior discriminative ability compared with other methods, providing interpretable insights for identifying knee OA progression.

Technical efficacy: Stage 2.

Keywords: graph convolutional network; knee osteoarthritis; progression.

Grants and funding

2024A1515010352/The Guang Dong Basic and Applied Basic Research Foundation