Automated measurement and grading of knee cartilage thickness: a deep learning-based approach

JaingRaong Guo; Pengfei Yan; Yong Qin; MeiNa Liu; Yingkai Ma; JaingQi Li; Ren Wang; Hao Luo; Songcen Lv

doi:10.3389/fmed.2024.1337993

Automated measurement and grading of knee cartilage thickness: a deep learning-based approach

Front Med (Lausanne). 2024 Feb 29:11:1337993. doi: 10.3389/fmed.2024.1337993. eCollection 2024.

Authors

JaingRaong Guo¹, Pengfei Yan², Yong Qin¹, MeiNa Liu³, Yingkai Ma¹, JaingQi Li², Ren Wang¹, Hao Luo², Songcen Lv¹

Affiliations

¹ Department of Orthopedics and Sports Medicine, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China.
² Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, Heilongjiang, China.
³ Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin, Heilongjiang, China.

Abstract

Background: Knee cartilage is the most crucial structure in the knee, and the reduction of cartilage thickness is a significant factor in the occurrence and development of osteoarthritis. Measuring cartilage thickness allows for a more accurate assessment of cartilage wear, but this process is relatively time-consuming. Our objectives encompass using various DL methods to segment knee cartilage from MRIs taken with different equipment and parameters, building a DL-based model for measuring and grading knee cartilage, and establishing a standardized database of knee cartilage thickness.

Methods: In this retrospective study, we selected a mixed knee MRI dataset consisting of 700 cases from four datasets with varying cartilage thickness. We employed four convolutional neural networks-UNet, UNet++, ResUNet, and TransUNet-to train and segment the mixed dataset, leveraging an extensive array of labeled data for effective supervised learning. Subsequently, we measured and graded the thickness of knee cartilage in 12 regions. Finally, a standard knee cartilage thickness dataset was established using 291 cases with ages ranging from 20 to 45 years and a Kellgren-Lawrence grading of 0.

Results: The validation results of network segmentation showed that TransUNet performed the best in the mixed dataset, with an overall dice similarity coefficient of 0.813 and an Intersection over Union of 0.692. The model's mean absolute percentage error for automatic measurement and grading after segmentation was 0.831. The experiment also yielded standard knee cartilage thickness, with an average thickness of 1.98 mm for the femoral cartilage and 2.14 mm for the tibial cartilage.

Conclusion: By selecting the best knee cartilage segmentation network, we built a model with a stronger generalization ability to automatically segment, measure, and grade cartilage thickness. This model can assist surgeons in more accurately and efficiently diagnosing changes in patients' cartilage thickness.

Keywords: cartilage thickness; convolutional neural network; deep learning; knee; osteoarthritis.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This study was supported by the National Orthopaedic and Exercise Rehabilitation Clinical Medical Research Center, China: 2021-NCRC-CXJJ-ZH-11 and the dual professor cooperation program from the Second Affiliated Hospital of Harbin Medical University. The name of the project is “Diagnosis of knee osteoarthritis based on deep learning measurement of cartilage thickness”.