Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI

Abstract

Background: Detection of rotator cuff tears, a common cause of shoulder disability, can be time-consuming and subject to reader variability. Deep learning (DL) has the potential to increase radiologist accuracy and consistency. Purpose: The aim of this study was to develop a prototype DL model for detection and classification of rotator cuff tears on shoulder magnetic resonance imaging into no tear, partial-thickness tear, or full-thickness tear. Materials and Methods: This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included a total of 11,925 noncontrast shoulder magnetic resonance imaging scans from 2 institutions, with 11,405 for development and 520 dedicated for final testing. A DL ensemble algorithm was developed that used 4 series as input from each examination: fluid-sensitive sequences in 3 planes and a sagittal oblique T1-weighted sequence. Radiology reports served as ground truth for training with categories of no tear, partial tear, or full-thickness tear. A multireader study was conducted for the test set ground truth, which was determined by the majority vote of 3 readers per case. The ensemble comprised 4 parallel 3D ResNet50 convolutional neural network architectures trained via transfer learning and then adapted to the targeted domain. The final tear-type prediction was determined as the class with the highest probability, after averaging the class probabilities of the 4 individual models. Results: The AUC overall for supraspinatus, infraspinatus, and subscapularis tendon tears was 0.93, 0.89, and 0.90, respectively. The model performed best for full-thickness supraspinatus, infraspinatus, and subscapularis tears with AUCs of 0.98, 0.99, and 0.95, respectively. Multisequence input demonstrated higher AUCs than single-sequence input for infraspinatus and subscapularis tendon tears, whereas coronal oblique fluid-sensitive and multisequence input showed similar AUCs for supraspinatus tendon tears. Model accuracy for tear types and overall accuracy were similar to that of the clinical readers. Conclusions: Deep learning diagnosis of rotator cuff tears is feasible with excellent diagnostic performance, particularly for full-thickness tears, with model accuracy similar to subspecialty-trained musculoskeletal radiologists.

Artificial Intelligence and Machine Learning in Rotator Cuff Tears

“…The model achieved excellent diagnostic performance, with high area under the curve (AUC) values for different tear types. Specifically, the AUCs for full-thickness tears of supraspinatus, infraspinatus, and subscapularis (SSC) tendons were 0.98, 0.99, and 0.95, respectively 31 . Separate authors present a computer-aided diagnostic system based on an optimized CNN for diagnosing RCTs using MRI images.…”

“…Specifically, the AUCs for full-thickness tears of supraspinatus, infraspinatus, and subscapularis (SSC) tendons were 0.98, 0.99, and 0.95, respectively. 31 Separate authors present a computer-aided diagnostic system based on an optimized CNN for diagnosing RCTs using MRI images. The computeraided diagnostic system used DL techniques to automatically diagnose shoulder injuries, providing a fast and automated approach while reducing medical errors.…”

Fat Fractions of the Rotator Cuff Muscles Acquired With 2-Point Dixon MRI

“…However, the performance of the algorithm in predicting retears of the RC tendons was not evaluated. 36 Similar to Wieser et al, 7 a quantitative 3D analysis of the segmented SSP, ISP, and SSC muscles was performed in this study to obtain more reliable FF and muscle volumes. In the current study, the muscle volume of the intact RC repair group did not change significantly between baseline and follow-up, indicating that successful RC repair halted further progression of fatty infiltration and atrophy.…”

“…The application of new machine learning–based analytical models, multifactorial correlations, and classifiers allows the processing of large data sets and testing thousands of features to identify the relevant markers 35 . Lin et al 36 reported a convolutional neural network for RC tear assessment that achieved excellent performance in detecting full thickness RC tears (AUC, 0.95–0.99). The network was trained on a data set of nearly 12,000 noncontrast shoulder MRIs, using the radiological reports as ground truth.…”

“…The network was trained on a data set of nearly 12,000 noncontrast shoulder MRIs, using the radiological reports as ground truth. However, the performance of the algorithm in predicting retears of the RC tendons was not evaluated 36 …”