Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
01 06 2023
01 06 2023
Historique:
medline:
8
5
2023
pubmed:
3
2
2023
entrez:
2
2
2023
Statut:
ppublish
Résumé
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. 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. 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. 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. 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.
Sections du résumé
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.
Identifiants
pubmed: 36728041
doi: 10.1097/RLI.0000000000000951
pii: 00004424-202306000-00005
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
405-412Informations de copyright
Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: Industry collaboration with Siemens (authors' expertise as above), provision of funding for multireader study ground truth research reads.
Références
Tashjian RZ. Epidemiology, natural history, and indications for treatment of rotator cuff tears. Clin Sports Med . 2012;31:589–604.
Morag Y, Jacobson JA, Miller B, et al. MR imaging of rotator cuff injury: what the clinician needs to know. Radiographics . 2006;26:1045–1065.
Spencer EE Jr., Dunn WR, Wright RW, et al. Interobserver agreement in the classification of rotator cuff tears using magnetic resonance imaging. Am J Sports Med . 2008;36:99–103.
Robertson PL, Schweitzer ME, Mitchell DG, et al. Rotator cuff disorders: interobserver and intraobserver variation in diagnosis with MR imaging. Radiology . 1995;194:831–835.
Malavolta EA, Assunção JH, Gracitelli MEC, et al. Accuracy of magnetic resonance imaging (MRI) for subscapularis tear: a systematic review and meta-analysis of diagnostic studies. Arch Orthop Trauma Surg . 2019;139:659–667.
Malavolta EA, Assunção JH, Guglielmetti CLB, et al. Accuracy of preoperative MRI in the diagnosis of subscapularis tears. Arch Orthop Trauma Surg . 2016;136:1425–1430.
Kim HJ, Park JS, Kim JY, et al. Interstitial tears of the rotator cuff: difficulty in preoperative diagnosis. J Shoulder Elbow Surg . 2018;27:487–492.
Brockmeyer M, Schmitt C, Haupert A, et al. Limited diagnostic accuracy of magnetic resonance imaging and clinical tests for detecting partial-thickness tears of the rotator cuff. Arch Orthop Trauma Surg . 2017;137:1719–1724.
Bien N, Rajpurkar P, Ball RL, et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet. PLoS Med . 2018;15:e1002699.
Fritz J, Kijowski R, Recht MP. Artificial intelligence in musculoskeletal imaging: a perspective on value propositions, clinical use, and obstacles. Skeletal Radiol . 2022;51:239–243.
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal . 2017;42:60–88.
Lin DJ, Walter SS, Fritz J. Artificial intelligence-driven ultra-fast superresolution MRI: 10-fold accelerated musculoskeletal turbo spin echo MRI within reach. Invest Radiol . 2022;58:28–42.
Germann C, Marbach G, Civardi F, et al. Deep convolutional neural network-based diagnosis of anterior cruciate ligament tears: performance comparison of homogenous versus heterogeneous knee MRI cohorts with different pulse sequence protocols and 1.5-T and 3-T magnetic field strengths. Invest Radiol . 2020;55:499–506.
Niemeyer F, Galbusera F, Tao Y, et al. A deep learning model for the accurate and reliable classification of disc degeneration based on MRI data. Invest Radiol . 2021;56:78–85.
Fritz B, Fritz J. Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches. Skeletal Radiol . 2022;51:315–329.
Fritz B, Yi PH, Kijowski R, et al. Radiomics and deep learning for disease detection in musculoskeletal radiology: an overview of novel MRI- and CT-based approaches. Invest Radiol . 2022;58:3–13.
Lindsey R, Daluiski A, Chopra S, et al. Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A . 2018;115:11591–11596.
Urakawa T, Tanaka Y, Goto S, et al. Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal Radiol . 2019;48:239–244.
Liu F, Guan B, Zhou Z, et al. Fully automated diagnosis of anterior cruciate ligament tears on knee MR images by using deep learning. Radiol Artif Intell . 2019;1:180091.
Chang PD, Wong TT, Rasiej MJ. Deep learning for detection of complete anterior cruciate ligament tear. J Digit Imaging . 2019;32:980–986.
Liu F, Zhou Z, Samsonov A, et al. Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection. Radiology . 2018;289:160–169.
Gyftopoulos S, Lin D, Knoll F, et al. Artificial intelligence in musculoskeletal imaging: current status and future directions. Am J Roentgenol . 2019;213:506–513.
Chea P, Mandell JC. Current applications and future directions of deep learning in musculoskeletal radiology. Skeletal Radiol . 2020;49:183–197.
Shim E, Kim JY, Yoon JP, et al. Automated rotator cuff tear classification using 3D convolutional neural network. Sci Rep . 2020;10:15632.
Kim M, Park HM, Kim JY, et al. MRI-based diagnosis of rotator cuff tears using deep learning and weighted linear combinations. Machine Learning for Healthcare Conference PMLR . 2020. Available at: https://proceedings.mlr.press/v126/kim20a.html . Accessed January 21, 2021.
Yao J, Chepelev L, Nisha Y, et al. Evaluation of a deep learning method for the automated detection of supraspinatus tears on MRI. Skeletal Radiol . 2022;51:1765–1775.
Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data . 2019;6:1–48.
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 2016:770–778.
Yosinski J, Clune J, Bengio Y, et al. How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems . 2014. Available at: https://proceedings.neurips.cc/paper/2014/hash/375c71349b295fbe2dcdca9206f20a06-Abstract.html . Accessed January 21, 2021.
Weiss K, Khoshgoftaar TM, Wang DD. A survey of transfer learning. J Big Data . 2016;3:1–40.
Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng . 2010;22:1345–1359.
Hara K, Kataoka H, Satoh Y. Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 2018:6546–6555.
Kay W, Carreira J, Simonyan K, et al. The kinetics human action video dataset. arXiv preprint arXiv . 2017;1705.06950. Available at: https://arxiv.org/abs/1705.06950 . Accessed January 21, 2021.
McKinney W. Data structures for statistical computing in Python. In: Proceedings of the 9th Python in Science Conference . 2010;445:51–56.
Seabold S, Perktold J. Statsmodels: econometric and statistical modeling with Python. In: Proceedings of the 9th Python in Science Conference . 2010. Available at: https://pdfs.semanticscholar.org/3a27/6417e5350e29cb6bf04ea5a4785601d5a215.pdf . Accessed January 21, 2021.