Fully Automated Diagnosis of Anterior Cruciate Ligament Tears on Knee MR Images by Using Deep Learning

Abstract

To investigate the feasibility of using a deep learning-based approach to detect an anterior cruciate ligament (ACL) tear within the knee joint at MRI by using arthroscopy as the reference standard. Materials and Methods: A fully automated deep learning-based diagnosis system was developed by using two deep convolutional neural networks (CNNs) to isolate the ACL on MR images followed by a classification CNN to detect structural abnormalities within the isolated ligament. With institutional review board approval, sagittal proton density-weighted and fat-suppressed T2-weighted fast spinecho MR images of the knee in 175 subjects with a full-thickness ACL tear (98 male subjects and 77 female subjects; average age, 27.5 years) and 175 subjects with an intact ACL (100 male subjects and 75 female subjects; average age, 39.4 years) were retrospectively analyzed by using the deep learning approach. Sensitivity and specificity of the ACL tear detection system and five clinical radiologists for detecting an ACL tear were determined by using arthroscopic results as the reference standard. Receiver operating characteristic (ROC) analysis and two-sided exact binomial tests were used to further assess diagnostic performance. Results: The sensitivity and specificity of the ACL tear detection system at the optimal threshold were 0.96 and 0.96, respectively. In comparison, the sensitivity of the clinical radiologists ranged between 0.96 and 0.98, while the specificity ranged between 0.90 and 0.98. There was no statistically significant difference in diagnostic performance between the ACL tear detection system and clinical radiologists at P < .05. The area under the ROC curve for the ACL tear detection system was 0.98, indicating high overall diagnostic accuracy. Conclusion: There was no significant difference between the diagnostic performance of the ACL tear detection system and clinical radiologists for determining the presence or absence of an ACL tear at MRI.

The Use of Artificial Intelligence in the Evaluation of Knee Pathology

“…32 Liu et al developed a fully automated deep learning-based diagnosis system for the diagnosis of a complete ACL tear that achieved a similar level of specificity and sensitivity when compared with a cohort of radiologists with varying levels of training. 33 Their deep learning-based diagnosis system was composed of CNNs to (1) select the MR images containing the ACL, (2) isolate the intercondylar notch region containing the ACL, and (3) determine the presence of a tear. The images used by the ACL tear diagnosis system included sagittal PD-weighted and T2-weighted sequences.…”

“…There was no statistically significant difference in the diagnostic performance between the ACL tear diagnosis system and radiologists in the diagnosis of a complete ACL tear. 33…”

Improving Quantitative Magnetic Resonance Imaging Using Deep Learning

“…Later, the same group used a similar cascaded system to detect ACL tears on MRI with an AUC of 0.98 and sensitivity and specificity of 96% and 98%, respectively. 54 Pedoia et al used a UNet to segment patellar cartilage that was then analyzed by a custom-made classification CNN to detect cartilage lesions. 55 The machine Fig.…”

Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease

“…6). 17,18,21,22 In an alternative approach, Bien et al 23 used a single custom-made "MRNet" classification CNN to analyze nonsegmented axial fatsuppressed proton density-weighted 2D FSE, coronal T 1weighted 2D FSE, and sagittal fat-suppressed T 2 -weighted 2D FSE images in 1370 subjects with 319 ACL tears and 508 meniscal tears to determine the presence or absence of ACL and meniscal tears using the interpretation of experienced radiologists as the reference standard ( Fig. 7).…”