1
|
Iio R, Ueda D, Matsumoto T, Manaka T, Nakazawa K, Ito Y, Hirakawa Y, Yamamoto A, Shiba M, Nakamura H. Deep learning-based screening tool for rotator cuff tears on shoulder radiography. J Orthop Sci 2023:S0949-2658(23)00132-X. [PMID: 37236873 DOI: 10.1016/j.jos.2023.05.004] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Revised: 02/06/2023] [Accepted: 05/09/2023] [Indexed: 05/28/2023]
Abstract
BACKGROUND Early diagnosis of rotator cuff tears is essential for appropriate and timely treatment. Although radiography is the most used technique in clinical practice, it is difficult to accurately rule out rotator cuff tears as an initial imaging diagnostic modality. Deep learning-based artificial intelligence has recently been applied in medicine, especially diagnostic imaging. This study aimed to develop a deep learning algorithm as a screening tool for rotator cuff tears based on radiography. METHODS We used 2803 shoulder radiographs of the true anteroposterior view to develop the deep learning algorithm. Radiographs were labeled 0 and 1 as intact or low-grade partial-thickness rotator cuff tears and high-grade partial or full-thickness rotator cuff tears, respectively. The diagnosis of rotator cuff tears was determined based on arthroscopic findings. The diagnostic performance of the deep learning algorithm was assessed by calculating the area under the curve (AUC), sensitivity, negative predictive value (NPV), and negative likelihood ratio (LR-) of test datasets with a cutoff value of expected high sensitivity determination based on validation datasets. Furthermore, the diagnostic performance for each rotator cuff tear size was evaluated. RESULTS The AUC, sensitivity, NPV, and LR- with expected high sensitivity determination were 0.82, 84/92 (91.3%), 102/110 (92.7%), and 0.16, respectively. The sensitivity, NPV, and LR- for full-thickness rotator cuff tears were 69/73 (94.5%), 102/106 (96.2%), and 0.10, respectively, while the diagnostic performance for partial-thickness rotator cuff tears was low at 15/19 (78.9%), NPV of 102/106 (96.2%) and LR- of 0.39. CONCLUSIONS Our algorithm had a high diagnostic performance for full-thickness rotator cuff tears. The deep learning algorithm based on shoulder radiography helps screen rotator cuff tears by setting an appropriate cutoff value. LEVEL OF EVIDENCE Level III: Diagnostic Study.
Collapse
Affiliation(s)
- Ryosuke Iio
- Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka City University, Osaka, Japan; Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Daiju Ueda
- Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, Japan; Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Toshimasa Matsumoto
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Tomoya Manaka
- Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan.
| | - Katsumasa Nakazawa
- Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka City University, Osaka, Japan; Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Yoichi Ito
- Ito Clinic, Osaka Shoulder Center, Osaka, Japan
| | - Yoshihiro Hirakawa
- Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Akira Yamamoto
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Masatsugu Shiba
- Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, Japan; Department of Medical Statistics, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Hiroaki Nakamura
- Department of Orthopaedic Surgery, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| |
Collapse
|
2
|
Abstract
Background: In the last years, basic research and arthroscopic surgery, have improved our understanding of shoulder anatomy and pathology. It is a fact that arthroscopic treatment of shoulder instability has evolved considerably over the past decades. The aim of this paper is to present the variety of pathologies that should be identified and treated during shoulder arthroscopy when dealing with anterior shoulder instability cases. Methods: A review of the current literature regarding arthroscopic shoulder anatomy, anatomic variants, and arthroscopic findings in anterior shoulder instability, is presented. In addition, correlation of arthroscopic findings with physical examination and advanced imaging (CT and MRI) in order to improve our understanding in anterior shoulder instability pathology is discussed. Results: Shoulder instability represents a broad spectrum of disease and a thorough understanding of the pathoanatomy is the key for a successful treatment of the unstable shoulder. Patients can have a variety of pathologies concomitant with a traditional Bankart lesion, such as injuries of the glenoid (bony Bankart), injuries of the glenoid labrum, superiorly (SLAP) or anteroinferiorly (e.g. anterior labroligamentous periosteal sleeve avulsion, and Perthes), capsular lesions (humeral avulsion of the glenohumeral ligament), and accompanying osseous-cartilage lesions (Hill-Sachs, glenolabral articular disruption). Shoulder arthroscopy allows for a detailed visualization and a dynamic examination of all anatomic structures, identification of pathologic findings, and treatment of all concomitant lesions. Conclusion: Surgeons must be well prepared and understanding the normal anatomy of the glenohumeral joint, including its anatomic variants to seek for the possible pathologic lesions in anterior shoulder instability during shoulder arthroscopy. Patient selection criteria, improved surgical techniques, and implants available have contributed to the enhancement of clinical and functional outcomes to the point that arthroscopic treatment is considered nowadays the standard of care.
Collapse
Affiliation(s)
- Michael Hantes
- Department of Orthopaedic Surgery and Musculoskeletal Trauma, Faculty of Medicine, School of Health Sciences, University of Thessalia, Larissa, Greece
| | - Vasilios Raoulis
- Department of Orthopaedic Surgery and Musculoskeletal Trauma, Faculty of Medicine, School of Health Sciences, University of Thessalia, Larissa, Greece
| |
Collapse
|