Automatic Detection of Meniscus Tears Using Backbone Convolutional Neural Networks on Knee MRI

• Published in: Journal of magnetic resonance imaging Vol. 57; no. 3; pp. 740 - 749
• Main Authors: Hung, Truong Nguyen Khanh, Vy, Vu Pham Thao, Tri, Nguyen Minh, Hoang, Le Ngoc, Tuan, Le Van, Ho, Quang Thai, Le, Nguyen Quoc Khanh, Kang, Jiunn‐Horng
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.03.2023; Wiley Subscription Services, Inc
• Subjects: Accuracy; Arthroscopy; Artificial neural networks; Darknet53; Datasets; Deep learning; Humans; Injuries; Injury prevention; Knee; Knee Joint - pathology; knee MR image; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Menisci, Tibial; Meniscus; meniscus tear; Morbidity; Neural networks; Neural Networks, Computer; object detection; Performance evaluation; Proton density (concentration); Rank tests; Retrospective Studies; Saturation; Sensitivity; Sensitivity and Specificity; Sequences; Statistical analysis; Statistical tests; Tibial Meniscus Injuries - diagnostic imaging; Tibial Meniscus Injuries - pathology; Variance analysis; YOLOv4; object detection; YOLOv4; knee MR image; meniscus tear; Darknet53
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.28284

Background Timely diagnosis of meniscus injuries is key for preventing knee joint dysfunction and improving patient outcomes because it decreases morbidity and facilitates treatment planning. Purpose To train and evaluate a deep learning model for automated detection of meniscus tears on knee magnetic resonance imaging (MRI). Study type Bicentric retrospective study. Subjects In total, 584 knee MRI studies, divided among training (n = 234), testing (n = 200), and external validation (n = 150) data sets, were used in this study. The public data set MRNet was used as a second external validation data set to evaluate the performance of the model. Sequence A 3 T, coronal, and sagittal images from T1‐weighted proton density (PD) fast spin‐echo (FSE) with fat saturation and T2‐weighted FSE with fat saturation sequences. Assessment The detection system for meniscus tear was based on the improved YOLOv4 model with Darknet‐53 as the backbone. The performance of the model was also compared with that of three radiologists of varying levels of experience. The determination of the presence of a meniscus tear from surgery reports was used as the ground truth for the images. Statistical Tests Sensitivity, specificity, prevalence, positive predictive value, negative predictive value, accuracy, and receiver operating characteristic curve were used to evaluate the performance of the detection model. Two‐way analysis of variance, Wilcoxon signed‐rank test, and Tukey's multiple tests were used to evaluate differences in performance between the model and radiologists. Results The overall accuracies for detecting meniscus tears using our model on the internal testing, internal validation, and external validation data sets were 95.4%, 95.8%, and 78.8%, respectively. One radiologist had significantly lower performance than our model in detecting meniscal tears (accuracy: 0.9025 ± 0.093 vs. 0.9580 ± 0.025). Data Conclusion The proposed model had high sensitivity, specificity, and accuracy for detecting meniscus tears on knee MRIs. Evidence Level 3 Technical Efficacy Stage 2