1
|
Saavedra JP, Droppelmann G, Jorquera C, Feijoo F. Automated segmentation and classification of supraspinatus fatty infiltration in shoulder magnetic resonance image using a convolutional neural network. Front Med (Lausanne) 2024; 11:1416169. [PMID: 39290391 PMCID: PMC11405335 DOI: 10.3389/fmed.2024.1416169] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2024] [Accepted: 08/20/2024] [Indexed: 09/19/2024] Open
Abstract
Background Goutallier's fatty infiltration of the supraspinatus muscle is a critical condition in degenerative shoulder disorders. Deep learning research primarily uses manual segmentation and labeling to detect this condition. Employing unsupervised training with a hybrid framework of segmentation and classification could offer an efficient solution. Aim To develop and assess a two-step deep learning model for detecting the region of interest and categorizing the magnetic resonance image (MRI) supraspinatus muscle fatty infiltration according to Goutallier's scale. Materials and methods A retrospective study was performed from January 1, 2019 to September 20, 2020, using 900 MRI T2-weighted images with supraspinatus muscle fatty infiltration diagnoses. A model with two sequential neural networks was implemented and trained. The first sub-model automatically detects the region of interest using a U-Net model. The second sub-model performs a binary classification using the VGG-19 architecture. The model's performance was computed as the average of five-fold cross-validation processes. Loss, accuracy, Dice coefficient (CI. 95%), AU-ROC, sensitivity, and specificity (CI. 95%) were reported. Results Six hundred and six shoulders MRIs were analyzed. The Goutallier distribution was presented as follows: 0 (66.50%); 1 (18.81%); 2 (8.42%); 3 (3.96%); 4 (2.31%). Segmentation results demonstrate high levels of accuracy (0.9977 ± 0.0002) and Dice score (0.9441 ± 0.0031), while the classification model also results in high levels of accuracy (0.9731 ± 0.0230); sensitivity (0.9000 ± 0.0980); specificity (0.9788 ± 0.0257); and AUROC (0.9903 ± 0.0092). Conclusion The two-step training method proposed using a deep learning model demonstrated strong performance in segmentation and classification tasks.
Collapse
Affiliation(s)
- Juan Pablo Saavedra
- School of Industrial Engineering, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile
| | - Guillermo Droppelmann
- Clínica MEDS, Santiago, Chile
- Harvard T.H. Chan School of Public Health, Boston, MA, United States
| | - Carlos Jorquera
- Facultad de Ciencias, Escuela de Nutrición y Dietética, Universidad Mayor, Santiago, Chile
| | - Felipe Feijoo
- School of Industrial Engineering, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile
| |
Collapse
|
2
|
Alzubaidi L, Al-Dulaimi K, Salhi A, Alammar Z, Fadhel MA, Albahri AS, Alamoodi AH, Albahri OS, Hasan AF, Bai J, Gilliland L, Peng J, Branni M, Shuker T, Cutbush K, Santamaría J, Moreira C, Ouyang C, Duan Y, Manoufali M, Jomaa M, Gupta A, Abbosh A, Gu Y. Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion. Artif Intell Med 2024; 155:102935. [PMID: 39079201 DOI: 10.1016/j.artmed.2024.102935] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Revised: 03/18/2024] [Accepted: 07/22/2024] [Indexed: 08/24/2024]
Abstract
Deep learning (DL) in orthopaedics has gained significant attention in recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation of osteoarthritis severity. The utilisation of DL is expected to increase, owing to its ability to present accurate diagnoses more efficiently than traditional methods in many scenarios. This reduces the time and cost of diagnosis for patients and orthopaedic surgeons. To our knowledge, no exclusive study has comprehensively reviewed all aspects of DL currently used in orthopaedic practice. This review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, and Web of Science between 2017 and 2023. The authors begin with the motivation for using DL in orthopaedics, including its ability to enhance diagnosis and treatment planning. The review then covers various applications of DL in orthopaedics, including fracture detection, detection of supraspinatus tears using MRI, osteoarthritis, prediction of types of arthroplasty implants, bone age assessment, and detection of joint-specific soft tissue disease. We also examine the challenges for implementing DL in orthopaedics, including the scarcity of data to train DL and the lack of interpretability, as well as possible solutions to these common pitfalls. Our work highlights the requirements to achieve trustworthiness in the outcomes generated by DL, including the need for accuracy, explainability, and fairness in the DL models. We pay particular attention to fusion techniques as one of the ways to increase trustworthiness, which have also been used to address the common multimodality in orthopaedics. Finally, we have reviewed the approval requirements set forth by the US Food and Drug Administration to enable the use of DL applications. As such, we aim to have this review function as a guide for researchers to develop a reliable DL application for orthopaedic tasks from scratch for use in the market.
Collapse
Affiliation(s)
- Laith Alzubaidi
- School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia; QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia.
| | - Khamael Al-Dulaimi
- Computer Science Department, College of Science, Al-Nahrain University, Baghdad, Baghdad 10011, Iraq; School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Asma Salhi
- QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia
| | - Zaenab Alammar
- School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Mohammed A Fadhel
- Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia
| | - A S Albahri
- Technical College, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq
| | - A H Alamoodi
- Institute of Informatics and Computing in Energy, Universiti Tenaga Nasional, Kajang 43000, Malaysia
| | - O S Albahri
- Australian Technical and Management College, Melbourne, Australia
| | - Amjad F Hasan
- Faculty of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA
| | - Jinshuai Bai
- School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia; QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Luke Gilliland
- QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia
| | - Jing Peng
- Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia
| | - Marco Branni
- QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia
| | - Tristan Shuker
- QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; St Andrew's War Memorial Hospital, Brisbane, QLD 4000, Australia
| | - Kenneth Cutbush
- QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; St Andrew's War Memorial Hospital, Brisbane, QLD 4000, Australia
| | - Jose Santamaría
- Department of Computer Science, University of Jaén, Jaén 23071, Spain
| | - Catarina Moreira
- Data Science Institute, University of Technology Sydney, Australia
| | - Chun Ouyang
- School of Information Systems, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Ye Duan
- School of Computing, Clemson University, Clemson, 29631, SC, USA
| | - Mohamed Manoufali
- CSIRO, Kensington, WA 6151, Australia; School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD 4067, Australia
| | - Mohammad Jomaa
- QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; St Andrew's War Memorial Hospital, Brisbane, QLD 4000, Australia
| | - Ashish Gupta
- School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia; QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia; Research and Development department, Akunah Med Technology Pty Ltd Co, Brisbane, QLD 4120, Australia
| | - Amin Abbosh
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD 4067, Australia
| | - Yuantong Gu
- School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia; QUASR/ARC Industrial Transformation Training Centre-Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia
| |
Collapse
|
3
|
Cheng C, Liang X, Guo D, Xie D. Application of Artificial Intelligence in Shoulder Pathology. Diagnostics (Basel) 2024; 14:1091. [PMID: 38893618 PMCID: PMC11171621 DOI: 10.3390/diagnostics14111091] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2024] [Revised: 05/16/2024] [Accepted: 05/20/2024] [Indexed: 06/21/2024] Open
Abstract
Artificial intelligence (AI) refers to the science and engineering of creating intelligent machines for imitating and expanding human intelligence. Given the ongoing evolution of the multidisciplinary integration trend in modern medicine, numerous studies have investigated the power of AI to address orthopedic-specific problems. One particular area of investigation focuses on shoulder pathology, which is a range of disorders or abnormalities of the shoulder joint, causing pain, inflammation, stiffness, weakness, and reduced range of motion. There has not yet been a comprehensive review of the recent advancements in this field. Therefore, the purpose of this review is to evaluate current AI applications in shoulder pathology. This review mainly summarizes several crucial stages of the clinical practice, including predictive models and prognosis, diagnosis, treatment, and physical therapy. In addition, the challenges and future development of AI technology are also discussed.
Collapse
Affiliation(s)
- Cong Cheng
- Department of Orthopaedics, People’s Hospital of Longhua, Shenzhen 518000, China;
- Department of Joint Surgery and Sports Medicine, Center for Orthopedic Surgery, Orthopedic Hospital of Guangdong Province, The Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China; (X.L.); (D.G.)
| | - Xinzhi Liang
- Department of Joint Surgery and Sports Medicine, Center for Orthopedic Surgery, Orthopedic Hospital of Guangdong Province, The Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China; (X.L.); (D.G.)
| | - Dong Guo
- Department of Joint Surgery and Sports Medicine, Center for Orthopedic Surgery, Orthopedic Hospital of Guangdong Province, The Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China; (X.L.); (D.G.)
| | - Denghui Xie
- Department of Joint Surgery and Sports Medicine, Center for Orthopedic Surgery, Orthopedic Hospital of Guangdong Province, The Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China; (X.L.); (D.G.)
- Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases, The Third Affiliated Hospital of Southern Medical University, Guangzhou 510630, China
| |
Collapse
|
4
|
Chen W, Lim LJR, Lim RQR, Yi Z, Huang J, He J, Yang G, Liu B. Artificial intelligence powered advancements in upper extremity joint MRI: A review. Heliyon 2024; 10:e28731. [PMID: 38596104 PMCID: PMC11002577 DOI: 10.1016/j.heliyon.2024.e28731] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2024] [Revised: 03/21/2024] [Accepted: 03/22/2024] [Indexed: 04/11/2024] Open
Abstract
Magnetic resonance imaging (MRI) is an indispensable medical imaging examination technique in musculoskeletal medicine. Modern MRI techniques achieve superior high-quality multiplanar imaging of soft tissue and skeletal pathologies without the harmful effects of ionizing radiation. Some current limitations of MRI include long acquisition times, artifacts, and noise. In addition, it is often challenging to distinguish abutting or closely applied soft tissue structures with similar signal characteristics. In the past decade, Artificial Intelligence (AI) has been widely employed in musculoskeletal MRI to help reduce the image acquisition time and improve image quality. Apart from being able to reduce medical costs, AI can assist clinicians in diagnosing diseases more accurately. This will effectively help formulate appropriate treatment plans and ultimately improve patient care. This review article intends to summarize AI's current research and application in musculoskeletal MRI, particularly the advancement of DL in identifying the structure and lesions of upper extremity joints in MRI images.
Collapse
Affiliation(s)
- Wei Chen
- Department of Hand Surgery, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Lincoln Jian Rong Lim
- Department of Medical Imaging, Western Health, Footscray Hospital, Victoria, Australia
- Department of Surgery, The University of Melbourne, Victoria, Australia
| | - Rebecca Qian Ru Lim
- Department of Hand & Reconstructive Microsurgery, Singapore General Hospital, Singapore
| | - Zhe Yi
- Department of Hand Surgery, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| | - Jiaxing Huang
- Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Jia He
- Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Ge Yang
- Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Bo Liu
- Department of Hand Surgery, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China
| |
Collapse
|
5
|
Oeding JF, Krych AJ, Pearle AD, Kelly BT, Kunze KN. Medical Imaging Applications Developed Using Artificial Intelligence Demonstrate High Internal Validity Yet Are Limited in Scope and Lack External Validation. Arthroscopy 2024:S0749-8063(24)00099-9. [PMID: 38325497 DOI: 10.1016/j.arthro.2024.01.043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Revised: 01/21/2024] [Accepted: 01/29/2024] [Indexed: 02/09/2024]
Abstract
PURPOSE To (1) review definitions and concepts necessary to interpret applications of deep learning (DL; a domain of artificial intelligence that leverages neural networks to make predictions on media inputs such as images) and (2) identify knowledge and translational gaps in the literature to provide insight into specific areas for improvement as adoption of this technology continues. METHODS A comprehensive search of the literature was performed in December 2023 for articles regarding the use of DL in sports medicine. For each study, information regarding the joint of focus, specific anatomic structure/pathology to which DL was applied, imaging modality utilized, source of images used for model training and testing, data set size, model performance, and whether the DL model was externally validated was recorded. A numerical scale was used to rate each DL model's clinical impact, with 1 corresponding to proof-of-concept studies with little to no direct clinical impact and 5 corresponding to practice-changing clinical impact and ready for clinical deployment. RESULTS Fifty-five studies were identified, all of which were published within the past 5 years, while 82% were published within the past 3 years. Of the DL models identified, 84% were developed for classification tasks, 9% for automated measurements, and 7% for segmentation. A total of 62% of studies utilized magnetic resonance imaging as the imaging modality, 25% radiographs, and 7% ultrasound, while 1 study each used computed tomography, arthroscopic images, or arthroscopic video. Sixty-five percent of studies focused on the detection of tears (anterior cruciate ligament [ACL], rotator cuff [RC], and meniscus). The diagnostic performance of ACL tears, as determined by the area under the receiver operator curve (AUROC), ranged from 0.81 to 0.99 for ACL tears (excellent to near perfect), 0.83 to 0.94 for RC tears (excellent), and from 0.75 to 0.96 for meniscus tears (acceptable to excellent). In addition, 3 studies focused on detection of cartilage lesions had AUROC ranging from 0.90 to 0.92 (excellent performance). However, only 4 (7%) studies externally validated their models, suggesting that they may not be generalizable or may not perform well when applied to populations other than that used to develop the model. Finally, the mean clinical impact score was 2 (range, 1-3) on scale of 1 to 5, corresponding to limited clinical applicability. CONCLUSIONS DL models in orthopaedic sports medicine show generally excellent performance (high internal validity) but require external validation to facilitate clinical deployment. In addition, current models have low clinical applicability and fail to advance the field due to a focus on routine tasks and a narrow conceptual framework. LEVEL OF EVIDENCE Level IV, scoping review of Level I to IV studies.
Collapse
Affiliation(s)
- Jacob F Oeding
- Mayo Clinic Alix School of Medicine, Rochester, Minnesota, U.S.A
| | - Aaron J Krych
- Department of Orthopaedic Surgery, Mayo Clinic, Rochester, Minnesota, U.S.A
| | - Andrew D Pearle
- Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York, U.S.A
| | - Bryan T Kelly
- Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York, U.S.A
| | - Kyle N Kunze
- Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York, U.S.A..
| |
Collapse
|
6
|
Zhan H, Teng F, Liu Z, Yi Z, He J, Chen Y, Geng B, Xia Y, Wu M, Jiang J. Artificial Intelligence Aids Detection of Rotator Cuff Pathology: A Systematic Review. Arthroscopy 2024; 40:567-578. [PMID: 37355191 DOI: 10.1016/j.arthro.2023.06.018] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 05/28/2023] [Accepted: 06/01/2023] [Indexed: 06/26/2023]
Abstract
PURPOSE To determine the model performance of artificial intelligence (AI) in detecting rotator cuff pathology using different imaging modalities and to compare capability with physicians in clinical scenarios. METHODS The review followed the PRISMA guidelines and was registered on PROSPERO. The criteria were as follows: 1) studies on the application of AI in detecting rotator cuff pathology using medical images, and 2) studies on smart devices for assisting in diagnosis were excluded. The following data were extracted and recorded: statistical characteristics, input features, AI algorithms used, sample sizes of training and testing sets, and model performance. The data extracted from the included studies were narratively reviewed. RESULTS A total of 14 articles, comprising 23,119 patients, met the inclusion and exclusion criteria. The pooled mean age of the patients was 56.7 years, and the female rate was 56.1%. The area under the curve (AUC) of the algorithmic model to detect rotator cuff pathology from ultrasound images, MRI images, and radiographic series ranged from 0.789 to 0.950, 0.844 to 0.943, and 0.820 to 0.830, respectively. Notably, 1 of the studies reported that AI models based on ultrasound images demonstrated a diagnostic performance similar to that of radiologists. Another comparative study demonstrated that AI models using MRI images exhibited greater accuracy and specificity compared to orthopedic surgeons in the diagnosis of rotator cuff pathology, albeit not in sensitivity. CONCLUSIONS The detection of rotator cuff pathology has been significantly aided by the exceptional performance of AI models. In particular, these models are equally adept as musculoskeletal radiologists in using ultrasound to diagnose rotator cuff pathology. Furthermore, AI models exhibit statistically superior levels of accuracy and specificity when using MRI to diagnose rotator cuff pathology, albeit with no marked difference in sensitivity, in comparison to orthopaedic surgeons. LEVEL OF EVIDENCE Level III, systematic review of Level III studies.
Collapse
Affiliation(s)
- Hongwei Zhan
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Fei Teng
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Zhongcheng Liu
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Zhi Yi
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Jinwen He
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Yi Chen
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Bin Geng
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Yayi Xia
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China.
| | - Meng Wu
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| | - Jin Jiang
- Lanzhou University Second Hospital, Orthopaedic Clinical Research Center of Gansu Province, Intelligent Orthopaedic Industry Technology Center of Gansu Province, Lanzhou Gansu, China
| |
Collapse
|
7
|
Tang R, Li Z, Jiang L, Jiang J, Zhao B, Cui L, Zhou G, Chen X, Jiang D. Development and Clinical Application of Artificial Intelligence Assistant System for Rotator Cuff Ultrasound Scanning. ULTRASOUND IN MEDICINE & BIOLOGY 2024; 50:251-257. [PMID: 38042717 DOI: 10.1016/j.ultrasmedbio.2023.10.010] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/22/2023] [Revised: 10/19/2023] [Accepted: 10/24/2023] [Indexed: 12/04/2023]
Abstract
OBJECTIVE We developed an intelligent assistance system for shoulder ultrasound imaging, incorporating deep-learning algorithms to facilitate standard plane recognition and automatic tissue segmentation of the rotator cuff and its surrounding structures. We evaluated the system's performance using a dedicated data set of rotator cuff ultrasound images to assess its feasibility in clinical practice. METHODS To fulfill the system's primary functions, we designed a standard plane recognition module based on the ResNet50 network and an automatic tissue segmentation module using the Mask R-CNN model. The modules were trained on carefully curated data sets. The standard plane recognition module automatically identifies a specific standard plane based on the ultrasound image characteristics. The automatic tissue segmentation module effectively delineates and segments anatomical structures within the identified standard plane. RESULTS With the use of 59,265 shoulder joint ultrasound images, the standard plane recognition model achieved an impressive recognition accuracy of 94.9% in the test set, with an average precision rate of 96.4%, recall rate of 95.4% and F1 score of 95.9%. The automatic tissue segmentation model, tested on 1886 images, exhibited a commendable average intersection over union value of 96.2%, indicating robustness and accuracy. The model achieved mean intersection over union values exceeding 90.0% for all standard planes, indicating its effectiveness in precisely delineating the anatomical structures. CONCLUSION Our shoulder joint musculoskeletal intelligence system swiftly and accurately identifies standard planes and performs automatic tissue segmentation.
Collapse
Affiliation(s)
- Rui Tang
- Department of Ultrasound, Peking University Third Hospital, Beijing, China; Peking University Health Science Center Institute of Medical Technology, Beijing, China
| | - Zhiqiang Li
- Department of Ultrasound, Peking University Third Hospital, Beijing, China
| | - Ling Jiang
- Department of Ultrasound, Peking University Third Hospital, Beijing, China
| | - Jie Jiang
- Department of Ultrasound, Peking University Third Hospital, Beijing, China
| | - Bo Zhao
- Department of Ultrasound, Peking University Third Hospital, Beijing, China
| | - Ligang Cui
- Department of Ultrasound, Peking University Third Hospital, Beijing, China.
| | - Guoyi Zhou
- Sonoscape Medical Corporation, Shenzhen, China
| | - Xin Chen
- Sonoscape Medical Corporation, Shenzhen, China
| | - Daimin Jiang
- Sonoscape Medical Corporation(Wuhan), Wuhan, China
| |
Collapse
|
8
|
Wang P, Liu Y, Zhou Z. Supraspinatus extraction from MRI based on attention-dense spatial pyramid UNet network. J Orthop Surg Res 2024; 19:60. [PMID: 38216968 PMCID: PMC10787409 DOI: 10.1186/s13018-023-04509-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Accepted: 12/23/2023] [Indexed: 01/14/2024] Open
Abstract
BACKGROUND With potential of deep learning in musculoskeletal image interpretation being explored, this paper focuses on the common site of rotator cuff tears, the supraspinatus. It aims to propose and validate a deep learning model to automatically extract the supraspinatus, verifying its superiority through comparison with several classical image segmentation models. METHOD Imaging data were retrospectively collected from 60 patients who underwent inpatient treatment for rotator cuff tears at a hospital between March 2021 and May 2023. A dataset of the supraspinatus from MRI was constructed after collecting, filtering, and manually annotating at the pixel level. This paper proposes a novel A-DAsppUnet network that can automatically extract the supraspinatus after training and optimization. The analysis of model performance is based on three evaluation metrics: precision, intersection over union, and Dice coefficient. RESULTS The experimental results demonstrate that the precision, intersection over union, and Dice coefficients of the proposed model are 99.20%, 83.38%, and 90.94%, respectively. Furthermore, the proposed model exhibited significant advantages over the compared models. CONCLUSION The designed model in this paper accurately extracts the supraspinatus from MRI, and the extraction results are complete and continuous with clear boundaries. The feasibility of using deep learning methods for musculoskeletal extraction and assisting in clinical decision-making was verified. This research holds practical significance and application value in the field of utilizing artificial intelligence for assisting medical decision-making.
Collapse
Affiliation(s)
- Peng Wang
- Third Clinical Medical School, Nanjing University of Chinese Medicine, Nanjing, 210023, People's Republic of China
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, No. 100 Maigaoqiao Cross Street, Qixia District, Nanjing City, 210028, Jiangsu Province, People's Republic of China
| | - Yang Liu
- School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing, 210044, People's Republic of China
| | - Zhong Zhou
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, No. 100 Maigaoqiao Cross Street, Qixia District, Nanjing City, 210028, Jiangsu Province, People's Republic of China.
| |
Collapse
|
9
|
Velasquez Garcia A, Hsu KL, Marinakis K. Advancements in the diagnosis and management of rotator cuff tears. The role of artificial intelligence. J Orthop 2024; 47:87-93. [PMID: 38059047 PMCID: PMC10696306 DOI: 10.1016/j.jor.2023.11.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Accepted: 11/03/2023] [Indexed: 12/08/2023] Open
Abstract
Background This review examined the role of artificial intelligence (AI) in the diagnosis and management of rotator cuff tears (RCTs). Methods A literature search was conducted in October 2023 using PubMed (MEDLINE), SCOPUS, and EMBASE databases, included only peer-reviewed studies. Relevant articles on AI technology in RCTs. A critical analysis of the relevant literature was conducted. Results AI is transforming RCTs management through faster and more precise identification and assessment using algorithms that facilitate segmentation, quantification, and classification of the RCTs across various imaging modalities. Precise algorithms focusing on preoperative factors to assess RCTs reparability have been developed for personalized treatment planning and outcome prediction. AI also aids in exercise classification and promotes patient adherence during at-home physiotherapy. Despite promising advancements, challenges in data quality and symptom integration persist. Future research should include refining AI algorithms, expanding their integration into various imaging techniques, and exploring their roles in postoperative care and surgical decision-making. Conclusions AI-driven solutions improve diagnostic accuracy and have the potential to influence treatment planning and postoperative outcomes through the automated RCTs analysis of medical imaging. Integration of high-quality datasets and clinical symptoms into AI models can enhance their reliability. Current AI algorithms can also be refined, integrated into other imaging techniques, and explored further in surgical decision-making and postoperative care.
Collapse
Affiliation(s)
- Ausberto Velasquez Garcia
- Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA
- Clínica Universidad de los Andes, Department of Orthopedic Surgery, Santiago, Chile
| | - Kai-Lan Hsu
- Department of Orthopaedic Surgery, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan
- Department of Biomedical Engineering, National Cheng Kung University, Tainan, Taiwan
| | | |
Collapse
|
10
|
Butowicz CM, Helgeson MD, Pisano AJ, Cook JW, Dearth CL, Hendershot BD. Lumbar Degenerative Disease and Muscle Morphology Before and After Lower Limb Loss in Four Military Patients. Mil Med 2023; 188:e3349-e3355. [PMID: 36564935 DOI: 10.1093/milmed/usac399] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2022] [Revised: 10/12/2022] [Accepted: 12/02/2022] [Indexed: 12/25/2022] Open
Abstract
INTRODUCTION Low back pain (LBP) is highly prevalent after lower limb amputation (LLA). Reports describing longitudinal changes in spine health before and after amputation are rare. This study describes lumbar spine pathology, muscle morphology, and the continuum of care for LBP before and after LLA. MATERIALS AND METHODS We queried electronic medical records of patients who sought care for LBP before and after unilateral LLA between January 2002 and April 2020 and who had documented lumbar imaging pre- and post-LLA. Patient demographics, muscle morphology, spinal pathology, premorbid and comorbid conditions, self-reported pain, and treatment interventions were assessed. RESULTS Four patients with LBP and imaging before and after LLA were identified. Intervertebral disc degeneration progressed after amputation in three patients, whereas facet arthrosis progressed in both female patients. The fat content of lumbar musculature generally increased after amputation. Conservative management of LBP before and after amputation was standard, with progression to steroidal injections. CONCLUSIONS Lumbar spine health may degrade after amputation. Here, lumbar muscle size did not change after LLA, yet the fat content increased in combination with increases in facet and intervertebral disc degeneration.
Collapse
Affiliation(s)
- Courtney M Butowicz
- Neuromusculoskeletal Outcomes Lead Walter Reed National Military Medical Center, Research and Surveillance Division, Extremity Trauma and Amputation Center of Excellence, Research & Engineering Directorate, Defense Health Agency, Building 19, Room B312, Bethesda, MD 20889, USA
- Department of Rehabilitation Medicine, Uniformed Services University of the Health Sciences, Bethesda, MD 20889, USA
| | - Melvin D Helgeson
- Department of Surgery, Uniformed Services University of the Health Sciences-Walter Reed National Military Medical Center, Bethesda, MD 20889, USA
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD 20889, USA
| | - Alfred J Pisano
- Department of Surgery, Uniformed Services University of the Health Sciences-Walter Reed National Military Medical Center, Bethesda, MD 20889, USA
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD 20889, USA
| | - John W Cook
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD 20889, USA
| | - Christopher L Dearth
- Neuromusculoskeletal Outcomes Lead Walter Reed National Military Medical Center, Research and Surveillance Division, Extremity Trauma and Amputation Center of Excellence, Research & Engineering Directorate, Defense Health Agency, Building 19, Room B312, Bethesda, MD 20889, USA
- Department of Rehabilitation Medicine, Uniformed Services University of the Health Sciences, Bethesda, MD 20889, USA
- Department of Surgery, Uniformed Services University of the Health Sciences-Walter Reed National Military Medical Center, Bethesda, MD 20889, USA
| | - Brad D Hendershot
- Neuromusculoskeletal Outcomes Lead Walter Reed National Military Medical Center, Research and Surveillance Division, Extremity Trauma and Amputation Center of Excellence, Research & Engineering Directorate, Defense Health Agency, Building 19, Room B312, Bethesda, MD 20889, USA
- Department of Rehabilitation Medicine, Uniformed Services University of the Health Sciences, Bethesda, MD 20889, USA
| |
Collapse
|
11
|
de Marinis R, Marigi EM, Atwan Y, Yang L, Oeding JF, Gupta P, Pareek A, Sanchez-Sotelo J, Sperling JW. Current clinical applications of artificial intelligence in shoulder surgery: what the busy shoulder surgeon needs to know and what's coming next. JSES REVIEWS, REPORTS, AND TECHNIQUES 2023; 3:447-453. [PMID: 37928999 PMCID: PMC10625013 DOI: 10.1016/j.xrrt.2023.07.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/07/2023]
Abstract
Background Artificial intelligence (AI) is a continuously expanding field with the potential to transform a variety of industries-including health care-by providing automation, efficiency, precision, accuracy, and decision-making support for simple and complex tasks. Basic knowledge of the key features as well as limitations of AI is paramount to understand current developments in this field and to successfully apply them to shoulder surgery. The purpose of the present review is to provide an overview of AI within orthopedics and shoulder surgery exploring current and forthcoming AI applications. Methods PubMed and Scopus databases were searched to provide a narrative review of the most relevant literature on AI applications in shoulder surgery. Results Despite the enormous clinical and research potential of AI, orthopedic surgery has been a relatively late adopter of AI technologies. Image evaluation, surgical planning, aiding decision-making, and facilitating patient evaluations over time are some of the current areas of development with enormous opportunities to improve surgical practice, research, and education. Furthermore, the advancement of AI-driven strategies has the potential to create a more efficient medical system that may reduce the overall cost of delivering and implementing quality health care for patients with shoulder pathology. Conclusion AI is an expanding field with the potential for broad clinical and research applications in orthopedic surgery. Many challenges still need to be addressed to fully leverage the potential of AI to clinical practice and research such as privacy issues, data ownership, and external validation of the proposed models.
Collapse
Affiliation(s)
- Rodrigo de Marinis
- Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA
- Department of Orthopedic Surgery, Pontificia Universidad Católica de Chile, Santiago, Chile
- Shoulder and Elbow Unit, Hospital Dr. Sótero del Rio, Santiago, Chile
| | - Erick M. Marigi
- Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA
| | - Yousif Atwan
- Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA
| | - Linjun Yang
- Orthopedic Surgery Artificial Intelligence Lab (OSAIL), Mayo Clinic, Rochester, MN, USA
| | - Jacob F. Oeding
- Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA
| | - Puneet Gupta
- Department of Orthopaedic Surgery, George Washington University School of Medicine and Health Sciences, Washington, DC, USA
| | - Ayoosh Pareek
- Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, NY, USA
| | | | - John W. Sperling
- Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN, USA
| |
Collapse
|
12
|
Lee KC, Cho Y, Ahn KS, Park HJ, Kang YS, Lee S, Kim D, Kang CH. Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI. Diagnostics (Basel) 2023; 13:3254. [PMID: 37892075 PMCID: PMC10606560 DOI: 10.3390/diagnostics13203254] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Revised: 10/06/2023] [Accepted: 10/16/2023] [Indexed: 10/29/2023] Open
Abstract
This study aimed to develop a screening model for rotator cuff tear detection in all three planes of routine shoulder MRI using a deep neural network. A total of 794 shoulder MRI scans (374 men and 420 women; aged 59 ± 11 years) were utilized. Three musculoskeletal radiologists labeled the rotator cuff tear. The YOLO v8 rotator cuff tear detection model was then trained; training was performed with all imaging planes simultaneously and with axial, coronal, and sagittal images separately. The performances of the models were evaluated and compared using receiver operating curves and the area under the curve (AUC). The AUC was the highest when using all imaging planes (0.94; p < 0.05). Among a single imaging plane, the axial plane showed the best performance (AUC: 0.71), followed by the sagittal (AUC: 0.70) and coronal (AUC: 0.68) imaging planes. The sensitivity and accuracy were also the highest in the model with all-plane training (0.98 and 0.96, respectively). Thus, deep-learning-based automatic rotator cuff tear detection can be useful for detecting torn areas in various regions of the rotator cuff in all three imaging planes.
Collapse
Affiliation(s)
- Kyu-Chong Lee
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea (C.H.K.)
| | - Yongwon Cho
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea (C.H.K.)
- Advanced Medical Imaging Institute, Korea University College of Medicine, Seoul 02841, Republic of Korea
- AI Center, Korea University Anam Hospital, Seoul 02841, Republic of Korea
| | - Kyung-Sik Ahn
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea (C.H.K.)
- Advanced Medical Imaging Institute, Korea University College of Medicine, Seoul 02841, Republic of Korea
- AI Center, Korea University Anam Hospital, Seoul 02841, Republic of Korea
| | - Hyun-Joon Park
- Institute for Healthcare Service Innovation, College of Medicine, Korea University, Seoul 02841, Republic of Korea; (H.-J.P.); (Y.-S.K.)
| | - Young-Shin Kang
- Institute for Healthcare Service Innovation, College of Medicine, Korea University, Seoul 02841, Republic of Korea; (H.-J.P.); (Y.-S.K.)
| | - Sungshin Lee
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea (C.H.K.)
| | | | - Chang Ho Kang
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea (C.H.K.)
- Advanced Medical Imaging Institute, Korea University College of Medicine, Seoul 02841, Republic of Korea
| |
Collapse
|
13
|
Rodriguez HC, Rust B, Hansen PY, Maffulli N, Gupta M, Potty AG, Gupta A. Artificial Intelligence and Machine Learning in Rotator Cuff Tears. Sports Med Arthrosc Rev 2023; 31:67-72. [PMID: 37976127 DOI: 10.1097/jsa.0000000000000371] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2023]
Abstract
Rotator cuff tears (RCTs) negatively impacts patient well-being. Artificial intelligence (AI) is emerging as a promising tool in medical decision-making. Within AI, deep learning allows to autonomously solve complex tasks. This review assesses the current and potential applications of AI in the management of RCT, focusing on diagnostic utility, challenges, and future perspectives. AI demonstrates promise in RCT diagnosis, aiding clinicians in interpreting complex imaging data. Deep learning frameworks, particularly convoluted neural networks architectures, exhibit remarkable diagnostic accuracy in detecting RCTs on magnetic resonance imaging. Advanced segmentation algorithms improve anatomic visualization and surgical planning. AI-assisted radiograph interpretation proves effective in ruling out full-thickness tears. Machine learning models predict RCT diagnosis and postoperative outcomes, enhancing personalized patient care. Challenges include small data sets and classification complexities, especially for partial thickness tears. Current applications of AI in RCT management are promising yet experimental. The potential of AI to revolutionize personalized, efficient, and accurate care for RCT patients is evident. The integration of AI with clinical expertise holds potential to redefine treatment strategies and optimize patient outcomes. Further research, larger data sets, and collaborative efforts are essential to unlock the transformative impact of AI in orthopedic surgery and RCT management.
Collapse
Affiliation(s)
- Hugo C Rodriguez
- Department of Orthopaedic Surgery, Larkin Community Hospital, South Miami
- Department of Orthopaedic Surgery, Hospital for Special Surgery Florida, West Palm Beach
| | - Brandon Rust
- Nova Southeastern University, Dr. Kiran Patel College of Osteopathic Medicine, Fort Lauderdale
| | - Payton Yerke Hansen
- Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, FL
| | - Nicola Maffulli
- Department of Musculoskeletal Disorders, School of Medicine and Surgery, University of Salerno, Fisciano
- San Giovanni di Dio e Ruggi D'Aragona Hospital "Clinica Ortopedica" Department, Hospital of Salerno, Salerno, Italy
- Barts and the London School of Medicine and Dentistry, Centre for Sports and Exercise Medicine, Queen Mary University of London, London
- School of Pharmacy and Bioengineering, Keele University School of Medicine, Stoke on Trent, UK
| | - Manu Gupta
- Polar Aesthetics Dental & Cosmetic Centre, Noida, Uttar Pradesh
| | - Anish G Potty
- South Texas Orthopaedic Research Institute (STORI Inc.), Laredo, TX
| | - Ashim Gupta
- Regenerative Orthopaedics, Noida, India
- South Texas Orthopaedic Research Institute (STORI Inc.), Laredo, TX
- Future Biologics
- BioIntegrate, Lawrenceville, GA
| |
Collapse
|
14
|
Cho SH, Kim YS. Prediction of Retear After Arthroscopic Rotator Cuff Repair Based on Intraoperative Arthroscopic Images Using Deep Learning. Am J Sports Med 2023; 51:2824-2830. [PMID: 37565449 DOI: 10.1177/03635465231189201] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 08/12/2023]
Abstract
BACKGROUND It is challenging to predict retear after arthroscopic rotator cuff repair (ARCR). The usefulness of arthroscopic intraoperative images as predictors of the ARCR prognosis has not been analyzed. PURPOSE To evaluate the usefulness of arthroscopic images for the prediction of retear after ARCR using deep learning (DL) algorithms. STUDY DESIGN Cohort study (Diagnosis); Level of evidence, 2. METHODS In total, 1394 arthroscopic intraoperative images were retrospectively obtained from 580 patients. Repaired tendon integrity was evaluated using magnetic resonance imaging performed within 2 years after surgery. Images obtained immediately after ARCR were included. We used 3 DL architectures to predict retear based on arthroscopic images. Three pretrained DL algorithms (VGG16, DenseNet, and Xception) were used for transfer learning. Training and test sets were split into 8:2. Threefold stratified validation was used to fine-tune the hyperparameters using the training data set. The validation results of each fold were evaluated. The performance of each model in the test set was evaluated in terms of accuracy, area under the receiver operating characteristic curve (AUC), F1-score, sensitivity, and specificity. RESULTS In total, 1138 and 256 arthroscopic images were obtained from 514 patients and 66 patients in the nonretear and retear groups, respectively. The mean validation accuracy of each model was 83% for VGG16, 89% for Xception, and 91% for DenseNet. The accuracy for the test set was 76% for VGG16, 87% for Xception, and 91% for DenseNet. The AUC was highest for DenseNet (0.92); it was 0.83 for VGG16 and 0.91 for Xception. For the test set, the specificity and sensitivity were 0.93 and 0.84 for DenseNet, 0.89 and 0.84 for Xception, and 0.70 and 0.80 for VGG16, respectively. CONCLUSION The application of DL algorithms to intraoperative arthroscopic images has demonstrated a high level of accuracy in predicting retear occurrences.
Collapse
Affiliation(s)
- Sung-Hyun Cho
- Department of Orthopedic Surgery, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, Republic of Korea
| | - Yang-Soo Kim
- Department of Orthopedic Surgery, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, Republic of Korea
| |
Collapse
|
15
|
Praetorius JP, Walluks K, Svensson CM, Arnold D, Figge MT. IMFSegNet: Cost-effective and objective quantification of intramuscular fat in histological sections by deep learning. Comput Struct Biotechnol J 2023; 21:3696-3704. [PMID: 37560127 PMCID: PMC10407270 DOI: 10.1016/j.csbj.2023.07.031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Revised: 07/21/2023] [Accepted: 07/22/2023] [Indexed: 08/11/2023] Open
Abstract
The assessment of muscle condition is of great importance in various research areas. In particular, evaluating the degree of intramuscular fat (IMF) in tissue sections is a challenging task, which today is still mostly performed qualitatively or quantitatively by a highly subjective and error-prone manual analysis. We here realize the mission to make automated IMF analysis possible that (i) minimizes subjectivity, (ii) provides accurate and quantitative results quickly, and (iii) is cost-effective using standard hematoxylin and eosin (H&E) stained tissue sections. To address all these needs in a deep learning approach, we utilized the convolutional encoder-decoder network SegNet to train the specialized network IMFSegNet allowing to accurately quantify the spatial distribution of IMF in histological sections. Our fully automated analysis was validated on 17 H&E-stained muscle sections from individual sheep and compared to various state-of-the-art approaches. Not only does IMFSegNet outperform all other approaches, but this neural network also provides fully automated and highly accurate results utilizing the most cost-effective procedures of sample preparation and imaging. Furthermore, we shed light on the opacity of black-box approaches such as neural networks by applying an explainable artificial intelligence technique to clarify that the success of IMFSegNet actually lies in identifying the hard-to-detect IMF structures. Embedded in our open-source visual programming language JIPipe that does not require programming skills, it can be expected that IMFSegNet advances muscle condition assessment in basic research across multiple areas as well as in research fields focusing on translational clinical applications.
Collapse
Affiliation(s)
- Jan-Philipp Praetorius
- Applied Systems Biology, Leibniz institute for natural Product Research and infection Biology – Hans Knöll institute (HKI), Jena, Germany
- Faculty of Biological Sciences, Friedrich Schiller University Jena, Jena, Germany
| | - Kassandra Walluks
- Applied Systems Biology, Leibniz institute for natural Product Research and infection Biology – Hans Knöll institute (HKI), Jena, Germany
- Faculty of Biological Sciences, Friedrich Schiller University Jena, Jena, Germany
- Institute of Zoology and Evolutionary Research, Faculty of Biological Sciences, Friedrich Schiller University Jena, Jena, Germany
| | - Carl-Magnus Svensson
- Applied Systems Biology, Leibniz institute for natural Product Research and infection Biology – Hans Knöll institute (HKI), Jena, Germany
| | - Dirk Arnold
- Department of Otorhinolaryngology, Jena University Hospital, Jena, Germany
- Facial-Nerve-Center Jena, Jena University Hospital, Jena, Germany
| | - Marc Thilo Figge
- Applied Systems Biology, Leibniz institute for natural Product Research and infection Biology – Hans Knöll institute (HKI), Jena, Germany
- Institute of Microbiology, Faculty of Biological Sciences, Friedrich Schiller University Jena, Jena, Germany
| |
Collapse
|
16
|
Saavedra JP, Droppelmann G, García N, Jorquera C, Feijoo F. High-accuracy detection of supraspinatus fatty infiltration in shoulder MRI using convolutional neural network algorithms. Front Med (Lausanne) 2023; 10:1070499. [PMID: 37305126 PMCID: PMC10248442 DOI: 10.3389/fmed.2023.1070499] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2022] [Accepted: 05/09/2023] [Indexed: 06/13/2023] Open
Abstract
Background The supraspinatus muscle fatty infiltration (SMFI) is a crucial MRI shoulder finding to determine the patient's prognosis. Clinicians have used the Goutallier classification to diagnose it. Deep learning algorithms have been demonstrated to have higher accuracy than traditional methods. Aim To train convolutional neural network models to categorize the SMFI as a binary diagnosis based on Goutallier's classification using shoulder MRIs. Methods A retrospective study was performed. MRI and medical records from patients with SMFI diagnosis from January 1st, 2019, to September 20th, 2020, were selected. 900 T2-weighted, Y-view shoulder MRIs were evaluated. The supraspinatus fossa was automatically cropped using segmentation masks. A balancing technique was implemented. Five binary classification classes were developed into two as follows, A: 0, 1 v/s 3, 4; B: 0, 1 v/s 2, 3, 4; C: 0, 1 v/s 2; D: 0, 1, 2, v/s 3, 4; E: 2 v/s 3, 4. The VGG-19, ResNet-50, and Inception-v3 architectures were trained as backbone classifiers. An average of three 10-fold cross-validation processes were developed to evaluate model performance. AU-ROC, sensitivity, and specificity with 95% confidence intervals were used. Results Overall, 606 shoulders MRIs were analyzed. The Goutallier distribution was presented as follows: 0 = 403; 1 = 114; 2 = 51; 3 = 24; 4 = 14. Case A, VGG-19 model demonstrated an AU-ROC of 0.991 ± 0.003 (accuracy, 0.973 ± 0.006; sensitivity, 0.947 ± 0.039; specificity, 0.975 ± 0.006). B, VGG-19, 0.961 ± 0.013 (0.925 ± 0.010; 0.847 ± 0.041; 0.939 ± 0.011). C, VGG-19, 0.935 ± 0.022 (0.900 ± 0.015; 0.750 ± 0.078; 0.914 ± 0.014). D, VGG-19, 0.977 ± 0.007 (0.942 ± 0.012; 0.925 ± 0.056; 0.942 ± 0.013). E, VGG-19, 0.861 ± 0.050 (0.779 ± 0.054; 0.706 ± 0.088; 0.831 ± 0.061). Conclusion Convolutional neural network models demonstrated high accuracy in MRIs SMFI diagnosis.
Collapse
Affiliation(s)
- Juan Pablo Saavedra
- School of Industrial Engineering, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile
| | - Guillermo Droppelmann
- Research Center on Medicine, Exercise, Sport and Health, MEDS Clinic, Santiago, Chile
- Health Sciences PhD Program, Universidad Católica de Murcia UCAM, Murcia, Spain
- Principles and Practice of Clinical Research (PPCR), Harvard T. H. Chan School of Public Health, Boston, MA, United States
| | - Nicolás García
- Research Center on Medicine, Exercise, Sport and Health, MEDS Clinic, Santiago, Chile
| | - Carlos Jorquera
- Facultad de Ciencias, Escuela de Nutrición y Dietética, Universidad Mayor, Santiago, Chile
| | - Felipe Feijoo
- School of Industrial Engineering, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile
| |
Collapse
|
17
|
Hess H, Ruckli AC, Bürki F, Gerber N, Menzemer J, Burger J, Schär M, Zumstein MA, Gerber K. Deep-Learning-Based Segmentation of the Shoulder from MRI with Inference Accuracy Prediction. Diagnostics (Basel) 2023; 13:diagnostics13101668. [PMID: 37238157 DOI: 10.3390/diagnostics13101668] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Revised: 05/02/2023] [Accepted: 05/05/2023] [Indexed: 05/28/2023] Open
Abstract
Three-dimensional (3D)-image-based anatomical analysis of rotator cuff tear patients has been proposed as a way to improve repair prognosis analysis to reduce the incidence of postoperative retear. However, for application in clinics, an efficient and robust method for the segmentation of anatomy from MRI is required. We present the use of a deep learning network for automatic segmentation of the humerus, scapula, and rotator cuff muscles with integrated automatic result verification. Trained on N = 111 and tested on N = 60 diagnostic T1-weighted MRI of 76 rotator cuff tear patients acquired from 19 centers, a nnU-Net segmented the anatomy with an average Dice coefficient of 0.91 ± 0.06. For the automatic identification of inaccurate segmentations during the inference procedure, the nnU-Net framework was adapted to allow for the estimation of label-specific network uncertainty directly from its subnetworks. The average Dice coefficient of segmentation results from the subnetworks identified labels requiring segmentation correction with an average sensitivity of 1.0 and a specificity of 0.94. The presented automatic methods facilitate the use of 3D diagnosis in clinical routine by eliminating the need for time-consuming manual segmentation and slice-by-slice segmentation verification.
Collapse
Affiliation(s)
- Hanspeter Hess
- School of Biomedical and Precision Engineering, Personalised Medicine Research, University of Bern, 3008 Bern, Switzerland
| | - Adrian C Ruckli
- School of Biomedical and Precision Engineering, Personalised Medicine Research, University of Bern, 3008 Bern, Switzerland
| | - Finn Bürki
- School of Biomedical and Precision Engineering, Personalised Medicine Research, University of Bern, 3008 Bern, Switzerland
| | - Nicolas Gerber
- School of Biomedical and Precision Engineering, Personalised Medicine Research, University of Bern, 3008 Bern, Switzerland
| | - Jennifer Menzemer
- Shoulder, Elbow and Orthopaedic Sports Medicine, Orthopädie Sonnenhof, 3006 Bern, Switzerland
| | - Jürgen Burger
- School of Biomedical and Precision Engineering, Personalised Medicine Research, University of Bern, 3008 Bern, Switzerland
| | - Michael Schär
- Department of Orthopaedic Surgery and Traumatology, Inselspital, University Hospital of Bern, 3010 Bern, Switzerland
| | - Matthias A Zumstein
- Shoulder, Elbow and Orthopaedic Sports Medicine, Orthopädie Sonnenhof, 3006 Bern, Switzerland
- Department of Orthopaedic Surgery and Traumatology, Inselspital, University Hospital of Bern, 3010 Bern, Switzerland
| | - Kate Gerber
- School of Biomedical and Precision Engineering, Personalised Medicine Research, University of Bern, 3008 Bern, Switzerland
| |
Collapse
|
18
|
Gupta P, Haeberle HS, Zimmer ZR, Levine WN, Williams RJ, Ramkumar PN. Artificial intelligence-based applications in shoulder surgery leaves much to be desired: a systematic review. JSES REVIEWS, REPORTS, AND TECHNIQUES 2023; 3:189-200. [PMID: 37588443 PMCID: PMC10426484 DOI: 10.1016/j.xrrt.2022.12.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/09/2023]
Abstract
Background Artificial intelligence (AI) aims to simulate human intelligence using automated computer algorithms. There has been a rapid increase in research applying AI to various subspecialties of orthopedic surgery, including shoulder surgery. The purpose of this review is to assess the scope and validity of current clinical AI applications in shoulder surgery literature. Methods A systematic literature review was conducted using PubMed for all articles published between January 1, 2010 and June 10, 2022. The search query used the terms as follows: (artificial intelligence OR machine learning OR deep learning) AND (shoulder OR shoulder surgery OR rotator cuff). All studies that examined AI application models in shoulder surgery were included and evaluated for model performance and validation (internal, external, or both). Results A total of 45 studies were included in the final analysis. Eighteen studies involved shoulder arthroplasty, 13 rotator cuff, and 14 other areas. Studies applying AI to shoulder surgery primarily involved (1) automated imaging analysis including identifying rotator cuff tears and shoulder implants (2) risk prediction analyses including perioperative complications, functional outcomes, and patient satisfaction. Highest model performance area under the curve ranged from 0.681 (poor) to 1.00 (perfect). Only 2 studies reported external validation. Conclusion Applications of AI in the field of shoulder surgery are expanding rapidly and offer patient-specific risk stratification for shared decision-making and process automation for resource preservation. However, model performance is modest and external validation remains to be demonstrated, suggesting increased scientific rigor is warranted prior to deploying AI-based clinical applications.
Collapse
Affiliation(s)
- Puneet Gupta
- Department of Orthopaedic Surgery, George Washington University School of Medicine and Health Sciences, Washington, DC, USA
- Department of Orthopaedic Surgery, Columbia University Irving Medical Center, New York, NY, USA
| | - Heather S. Haeberle
- Department of Orthopaedic Surgery, Columbia University Irving Medical Center, New York, NY, USA
| | - Zachary R. Zimmer
- Department of Orthopaedic Surgery, George Washington University School of Medicine and Health Sciences, Washington, DC, USA
| | - William N. Levine
- Department of Orthopaedic Surgery, Columbia University Irving Medical Center, New York, NY, USA
| | - Riley J. Williams
- Institute for Cartilage Repair, Hospital for Special Surgery, New York, NY, USA
| | - Prem N. Ramkumar
- Institute for Cartilage Repair, Hospital for Special Surgery, New York, NY, USA
- Long Beach Orthopaedic Institute, Long Beach, CA, USA
| |
Collapse
|
19
|
Wang F, Zhou S, Hou B, Santini F, Yuan L, Guo Y, Zhu J, Hilbert T, Kober T, Zhang Y, Wang Q, Zhao Y, Jin Z. Assessment of idiopathic inflammatory myopathy using a deep learning method for muscle T2 mapping segmentation. Eur Radiol 2023; 33:2350-2357. [PMID: 36396791 PMCID: PMC9672653 DOI: 10.1007/s00330-022-09254-9] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2022] [Revised: 09/19/2022] [Accepted: 10/09/2022] [Indexed: 11/19/2022]
Abstract
OBJECTIVE To investigate the utility of an automatic deep learning (DL) method for segmentation of T2 maps in patients with idiopathic inflammatory myopathy (IIM) against healthy controls, and also the association of quantitative T2 values in patients with laboratory and pulmonary findings. METHODS Structural MRI and T2 mapping of bilateral thigh muscles from patients with IIM and healthy volunteers were segmented using dedicated software based on a pre-trained convolutional neural network. Incremental and federated learning were implemented for continuous adaptation and improvement. Muscle T2 values derived from DL segmentation were compared between patients and healthy controls, and T2 values of patients were further analyzed with serum muscle enzymes, and interstitial lung disease (ILD) which was diagnosed and graded based on chest HRCT. RESULTS Overall, 64 patients (27 patients with dermatomyositis, 29 with polymyositis, and 8 with antisynthetase syndrome (ASS)) and 10 healthy controls were included. By using DL-based muscle segmentation, T2 values generated from T2 maps accurately differentiated patients from those of controls (p < 0.001) with a cutoff value of 36.4 ms (sensitivity 96.9%, and specificity 100%). In patients with IIM, muscle T2 values positively correlated with all the serum muscle enzymes (all p < 0.05). ILD score of patients with ASS was markedly higher than that of those without ASS (p = 0.011), while dissociation between the severity of muscular involvement and ILD was observed (p = 0.080). CONCLUSION Automatic DL could be used to segment thigh muscles and help quantitatively assess muscular inflammation of IIM through T2 mapping. KEY POINTS • Muscle T2 mapping automatically segmented by deep learning can differentiate IIM from healthy controls. • T2 value, an indicator of active muscle inflammation, positively correlates with serum muscle enzymes. • T2 mapping can detect muscle disease in patients with normal muscle enzyme levels.
Collapse
Affiliation(s)
- Fengdan Wang
- Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Shuang Zhou
- Department of Rheumatology and Clinical Immunology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Bo Hou
- Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Francesco Santini
- Department of Research & Analytic Services, University Hospital Basel, Petersgraben 4, CH-4031, Basel, Switzerland.
- Radiological Physics, University Hospital Basel, Basel, Switzerland.
- Department of Biomedical Engineering, University of Basel, Allschwil, Switzerland.
| | - Ling Yuan
- Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Ye Guo
- Department of Clinical Laboratory, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Jinxia Zhu
- MR Collaboration, Siemens Healthcare Ltd., Beijing, China
| | - Tom Hilbert
- Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland
- Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
| | - Tobias Kober
- Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland
- Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
| | - Yan Zhang
- Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Qian Wang
- Department of Rheumatology and Clinical Immunology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Yan Zhao
- Department of Rheumatology and Clinical Immunology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Zhengyu Jin
- Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
- Department of Radiology, Peking Union Medical College Hospital, No. 1 Shuaifuyuan, Dongcheng District, Beijing, China.
| |
Collapse
|
20
|
Familiari F, Galasso O, Massazza F, Mercurio M, Fox H, Srikumaran U, Gasparini G. Artificial Intelligence in the Management of Rotator Cuff Tears. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:16779. [PMID: 36554660 PMCID: PMC9779744 DOI: 10.3390/ijerph192416779] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/04/2022] [Revised: 12/08/2022] [Accepted: 12/12/2022] [Indexed: 06/17/2023]
Abstract
Technological innovation is a key component of orthopedic surgery. Artificial intelligence (AI), which describes the ability of computers to process massive data and "learn" from it to produce outputs that mirror human cognition and problem solving, may become an important tool for orthopedic surgeons in the future. AI may be able to improve decision making, both clinically and surgically, via integrating additional data-driven problem solving into practice. The aim of this article will be to review the current applications of AI in the management of rotator cuff tears. The article will discuss various stages of the clinical course: predictive models and prognosis, diagnosis, intraoperative applications, and postoperative care and rehabilitation. Throughout the article, which is a review in terms of study design, we will introduce the concept of AI in rotator cuff tears and provide examples of how these tools can impact clinical practice and patient care. Though many advancements in AI have been made regarding evaluating rotator cuff tears-particularly in the realm of diagnostic imaging-further advancements are required before they become a regular facet of daily clinical practice.
Collapse
Affiliation(s)
- Filippo Familiari
- Department of Orthopaedic and Trauma Surgery, “Mater Domini” University Hospital, “Magna Græcia” University, 88100 Catanzaro, Italy
| | - Olimpio Galasso
- Department of Orthopaedic and Trauma Surgery, “Mater Domini” University Hospital, “Magna Græcia” University, 88100 Catanzaro, Italy
| | - Federica Massazza
- Department of Orthopaedic and Trauma Surgery, “Mater Domini” University Hospital, “Magna Græcia” University, 88100 Catanzaro, Italy
| | - Michele Mercurio
- Department of Orthopaedic and Trauma Surgery, “Mater Domini” University Hospital, “Magna Græcia” University, 88100 Catanzaro, Italy
| | - Henry Fox
- Department of Orthopaedic Surgery, Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA
| | - Uma Srikumaran
- Department of Orthopaedic Surgery, Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA
| | - Giorgio Gasparini
- Department of Orthopaedic and Trauma Surgery, “Mater Domini” University Hospital, “Magna Græcia” University, 88100 Catanzaro, Italy
| |
Collapse
|
21
|
Three-Dimensional Software- and MR-Imaging-Based Muscle Volumetry Reveals Overestimation of Supraspinatus Muscle Atrophy Using Occupation Ratios in Full-Thickness Tendon Tears. Healthcare (Basel) 2022; 10:healthcare10101899. [PMID: 36292346 PMCID: PMC9601991 DOI: 10.3390/healthcare10101899] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Revised: 09/14/2022] [Accepted: 09/20/2022] [Indexed: 11/17/2022] Open
Abstract
Supraspinatus muscle atrophy is widely determined from oblique-sagittal MRI by calculating the occupation ratio. This ex vivo and clinical study aimed to validate the accuracy of 3D software- and MR-imaging-based muscle volumetry, as well as to assess the influence of the tear pattern on the occupation ratio. Ten porcine muscle specimens were volumetrized using the physical water displacement volumetry as a standard of reference. A total of 149 individuals with intact supraspinatus tendons, partial tears, and full-thickness tears had 3T MRI. Two radiologists independently determined occupation ratio values. An excellent correlation with a Pearson’s r of 0.95 for the variables physical volumetry using the water displacement method and MR-imaging-based muscle volumetry using the software was found and formed the standard of reference for the patient study. The inter-reader reliability was 0.92 for occupation ratios. The correlation between occupation ratios and software-based muscle volumes was good in patients with intact tendons (0.84) and partial tears (0.93) but considerably lower in patients with full-thickness tears (0.68). Three-dimensional-software- and MR-imaging-based muscle volumetry is reliable and accurate. Compared to 3D muscle volumetry, the occupation ratio method overestimates supraspinatus muscle atrophy in full-thickness tears, which is most likely due to the medial retraction of the myotendinous unit.
Collapse
|
22
|
Ma J, Sahoo S, Imrey PB, Jin Y, Baker AR, Entezari V, Ho JC, Schickendantz MS, Farrow LD, Serna A, Iannotti JP, Ricchetti ET, Polster JM, Winalski CS, Derwin KA. Agreement between intraoperative and MRI assessments of rotator cuff pathology and two MRI-based assessments of supraspinatus muscle atrophy. JSES Int 2022; 6:948-956. [PMID: 36353424 PMCID: PMC9637799 DOI: 10.1016/j.jseint.2022.08.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
Abstract
Background Magnetic resonance imaging (MRI)-based rotator cuff assessment is often qualitative and subjective; few studies have tried to validate such preoperative assessments. This study investigates relationships of preoperative MRI assessments made by conventional approaches to intraoperative findings of tear type, location, and size or MRI-assessed muscle occupation ratio. Methods Intraoperatively, surgeons assessed tear type, location, anterior-posterior (AP) width, and medial-lateral length in 102 rotator cuff repair patients. Two musculoskeletal radiologists independently assessed the preoperative MRI scans for these same parameters and supraspinatus muscle atrophy by both Warner classification and quantitative occupation ratio. Exact agreement proportions, kappa statistics, and correlation coefficients were used to quantify agreement relationships. Results Agreement between MRI readers’ and surgeons’ observations of tear status averaged 93% with κ = 0.38, and that of tear location averaged 77% with κ = 0.50. Concordance correlations of MRI and intraoperative measures of anterior-posterior and medial-lateral tear length averaged 0.59 and 0.56 across readers, respectively. Despite excellent interrater agreement on Warner classification (exact agreement proportion 0.91) and occupation ratio (concordance correlation 0.93) separately, correlations between these 2 measures were −0.54 and −0.64 for the 2 readers, respectively. Patients with Warner grade 0 had occupation ratios ranging from 0.5 to 1.5. Conclusion Correlations of preoperative MRI tear dimensions and muscle atrophy assessed by conventional approaches with intraoperatively measured tear dimensions and quantitative occupation ratio, respectively, were only fair. Since tear size and muscle atrophy are known strong predictors of outcomes following rotator cuff repair that may influence treatment decisions, surgeons need to be aware of the limitations of MRI methods. Continued development and validation of quantitative preoperative imaging methods to accurately assess these parameters are needed to improve surgical planning and prognosis.
Collapse
|
23
|
Yao J, Chepelev L, Nisha Y, Sathiadoss P, Rybicki FJ, Sheikh AM. Evaluation of a deep learning method for the automated detection of supraspinatus tears on MRI. Skeletal Radiol 2022; 51:1765-1775. [PMID: 35190850 DOI: 10.1007/s00256-022-04008-6] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/19/2021] [Revised: 01/30/2022] [Accepted: 01/30/2022] [Indexed: 02/02/2023]
Abstract
OBJECTIVE To evaluate if deep learning is a feasible approach for automated detection of supraspinatus tears on MRI. MATERIALS AND METHODS A total of 200 shoulder MRI studies performed between 2015 and 2019 were retrospectively obtained from our institutional database using a balanced random sampling of studies containing a full-thickness tear, partial-thickness tear, or intact supraspinatus tendon. A 3-stage pipeline was developed comprised of a slice selection network based on a pre-trained residual neural network (ResNet); a segmentation network based on an encoder-decoder network (U-Net); and a custom multi-input convolutional neural network (CNN) classifier. Binary reference labels were created following review of radiologist reports and images by a radiology fellow and consensus validation by two musculoskeletal radiologists. Twenty percent of the data was reserved as a holdout test set with the remaining 80% used for training and optimization under a fivefold cross-validation strategy. Classification and segmentation accuracy were evaluated using area under the receiver operating characteristic curve (AUROC) and Dice similarity coefficient, respectively. Baseline characteristics in correctly versus incorrectly classified cases were compared using independent sample t-test and chi-squared. RESULTS Test sensitivity and specificity of the classifier at the optimal Youden's index were 85.0% (95% CI: 62.1-96.8%) and 85.0% (95% CI: 62.1-96.8%), respectively. AUROC was 0.943 (95% CI: 0.820-0.991). Dice segmentation accuracy was 0.814 (95% CI: 0.805-0.826). There was no significant difference in AUROC between 1.5 T and 3.0 T studies. Sub-analysis showed superior sensitivity on full-thickness (100%) versus partial-thickness (72.5%) subgroups. DATA CONCLUSION Deep learning is a feasible approach to detect supraspinatus tears on MRI.
Collapse
Affiliation(s)
- Jason Yao
- Department of Radiology, University of Ottawa Faculty of Medicine, 501 Smyth Road, Box 232, Ottawa, ON, K1H 8L6, Canada.
| | - Leonid Chepelev
- Department of Radiology, University of Ottawa Faculty of Medicine, 501 Smyth Road, Box 232, Ottawa, ON, K1H 8L6, Canada
| | - Yashmin Nisha
- Department of Radiology, University of Ottawa Faculty of Medicine, 501 Smyth Road, Box 232, Ottawa, ON, K1H 8L6, Canada
| | - Paul Sathiadoss
- Department of Radiology, University of Ottawa Faculty of Medicine, 501 Smyth Road, Box 232, Ottawa, ON, K1H 8L6, Canada
| | - Frank J Rybicki
- Department of Radiology, University of Cincinnati College of Medicine, 234 Goodman Street, Box 670761, Cincinnati, OH, 45267-0761, USA
| | - Adnan M Sheikh
- Department of Radiology, The University of British Columbia Faculty of Medicine, 2775 Laurel Street, Vancouver, BC, V5Z 1M9, Canada
| |
Collapse
|
24
|
Choi KJ, Choi JE, Roh HC, Eun JS, Kim JM, Shin YK, Kang MC, Chung JK, Lee C, Lee D, Kang SW, Cho BH, Kim SJ. Deep learning models for screening of high myopia using optical coherence tomography. Sci Rep 2021; 11:21663. [PMID: 34737335 PMCID: PMC8568935 DOI: 10.1038/s41598-021-00622-x] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2021] [Accepted: 10/13/2021] [Indexed: 12/02/2022] Open
Abstract
This study aimed to validate and evaluate deep learning (DL) models for screening of high myopia using spectral-domain optical coherence tomography (OCT). This retrospective cross-sectional study included 690 eyes in 492 patients with OCT images and axial length measurement. Eyes were divided into three groups based on axial length: a “normal group,” a “high myopia group,” and an “other retinal disease” group. The researchers trained and validated three DL models to classify the three groups based on horizontal and vertical OCT images of the 600 eyes. For evaluation, OCT images of 90 eyes were used. Diagnostic agreements of human doctors and DL models were analyzed. The area under the receiver operating characteristic curve of the three DL models was evaluated. Absolute agreement of retina specialists was 99.11% (range: 97.78–100%). Absolute agreement of the DL models with multiple-column model was 100.0% (ResNet 50), 90.0% (Inception V3), and 72.22% (VGG 16). Areas under the receiver operating characteristic curves of the DL models with multiple-column model were 0.99 (ResNet 50), 0.97 (Inception V3), and 0.86 (VGG 16). The DL model based on ResNet 50 showed comparable diagnostic performance with retinal specialists. The DL model using OCT images demonstrated reliable diagnostic performance to identify high myopia.
Collapse
Affiliation(s)
- Kyung Jun Choi
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Jung Eun Choi
- Medical AI Research Center, Samsung Medical Center, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Hyeon Cheol Roh
- Department of Ophthalmology, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon, Republic of Korea
| | - Jun Soo Eun
- Department of Ophthalmology, Gil Medical Center, Gachon University, Incheon, Republic of Korea
| | | | - Yong Kyun Shin
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Min Chae Kang
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Joon Kyo Chung
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Chaeyeon Lee
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Dongyoung Lee
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Se Woong Kang
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Baek Hwan Cho
- Medical AI Research Center, Samsung Medical Center, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea. .,Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul, 06351, Republic of Korea.
| | - Sang Jin Kim
- Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, #81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea.
| |
Collapse
|