TY - JOUR
T1 - Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI
AU - Lin, Dana J.
AU - Schwier, Michael
AU - Geiger, Bernhard
AU - Raithel, Esther
AU - Von Busch, Heinrich
AU - Fritz, Jan
AU - Kline, Mitchell
AU - Brooks, Michael
AU - Dunham, Kevin
AU - Shukla, Mehool
AU - Alaia, Erin F.
AU - Samim, Mohammad
AU - Joshi, Vivek
AU - Walter, William R.
AU - Ellermann, Jutta M.
AU - Ilaslan, Hakan
AU - Rubin, David
AU - Winalski, Carl S.
AU - Recht, Michael P.
N1 - Publisher Copyright:
© Wolters Kluwer Health, Inc. All rights reserved.
PY - 2023/6/1
Y1 - 2023/6/1
N2 - 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.
AB - 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.
KW - MRI
KW - artificial intelligence
KW - classification
KW - convolutional neural network
KW - deep learning
KW - infraspinatus
KW - rotator cuff
KW - subscapularis
KW - supraspinatus
KW - tendons
UR - http://www.scopus.com/inward/record.url?scp=85159198839&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85159198839&partnerID=8YFLogxK
U2 - 10.1097/RLI.0000000000000951
DO - 10.1097/RLI.0000000000000951
M3 - Article
C2 - 36728041
AN - SCOPUS:85159198839
SN - 0020-9996
VL - 58
SP - 405
EP - 412
JO - Investigative Radiology
JF - Investigative Radiology
IS - 6
ER -