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

Quantifying Tendon Degeneration Using Magic Angle Insensitive Ultra-Short Echo Time Magnetization Transfer: A Phantom Study in Bovine Tendons

OBJECTIVES

The aim of this study was to qualitatively and quantitatively assess changes in bovine flexor tendons before and after collagen degradation and at different angles in relation to the static B 0 field using 3-dimensional ultra-short echo time (UTE) magnetization transfer (MT) imaging within a clinically feasible acquisition time.

MATERIALS AND METHODS

Eight bovine flexor tendons were examined at 3 T magnetic resonance imaging including 3-dimensional UTE MT and UTE T2* research application sequences (acquired within 4:04 and 6:38 minutes, respectively) before and after enzyme-induced degradation. The tendons were divided into 2 groups: group 1 (controls) treated with phosphate-buffered saline and group 2 treated with collagenase I to induce collagen degeneration. Magnetic resonance imaging was repeated at 0, 27, 55, and 90 degrees to the B 0 field. To calculate quantitative tissue properties, all tendons were semiautomatically segmented, and changes in quantitative UTE T2* and UTE MT ratios (MTRs) were compared at different angles and between groups. In addition to descriptive statistics, the coefficient of variation was calculated to compare UTE MT and UTE T2* imaging.

RESULTS

Ultra-short echo time MTR showed a significantly lower coefficient of variation compared with UTE T2* values, indicating a more robust imaging method (UTE MTR 9.64%-11.25%, UTE T2* 18.81%-24.06%, P < 0.001). Both methods showed good performance in detecting degenerated tendons using histopathology as reference standard, with UTE MT imaging having a better area under the curve than UTE T2* mapping (0.918 vs 0.865). Falsely high UTE T2* values were detected at the 55 degrees acquisition angle, whereas UTE MTR values were robust, that is, insensitive to the MAE.

CONCLUSIONS

Ultra-short echo time MT imaging is a reliable method for quantifying tendon degeneration that is robust to the MAE and can be acquired in a clinically reasonable time.

Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion

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.

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade

This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.

AI-Based Measurement of Lumbar Spinal Stenosis on MRI: External Evaluation of a Fully Automated Model

OBJECTIVES

The aim of this study was to clinically validate a fully automated AI model for magnetic resonance imaging (MRI)-based quantifications of lumbar spinal canal stenosis.

MATERIALS AND METHODS

This retrospective study included lumbar spine MRI of 100 consecutive clinical patients (56 ± 17 years; 43 females, 57 males) performed on clinical 1.5 (51 examinations) and 3 T MRI scanners (49 examinations) with heterogeneous clinical imaging protocols. The AI model performed segmentations of the thecal sac on axial T2-weighted sequences. Based on these segmentations, the anteroposterior (AP) and mediolateral (ML) distance, and the area of the thecal sac were measured in a fully automated manner. For comparison, 2 fellowship-trained musculoskeletal radiologists performed the same segmentations and measurements independently. Statistics included 1-sample t tests, the intraclass correlation coefficient (ICC), Bland-Altman plots, and Dice coefficients. A P value of <0.05 was considered statistically significant.

RESULTS

The average measurements of the AI model, reader 1, and reader 2 were 194 ± 72 mm 2 , 181 ± 71 mm 2 , and 179 ± 70 mm 2 for thecal sac area, 13 ± 3.3 mm, 12.6 ± 3.3 mm, and 12.6 ± 3.2 mm for AP distance, and 19.5 ± 3.9 mm, 20 ± 4.3 mm, and 19.4 ± 4 mm for ML distance, respectively. Significant differences existed for all pairwise comparisons, besides reader 1 versus AI model for the ML distance and reader 1 versus reader 2 for the AP distance ( P = 0.1 and P = 0.21, respectively). The pairwise mean absolute errors among reader 1, reader 2, and the AI model ranged from 0.59 mm and 0.75 mm for the AP distance, from 1.16 mm to 1.37 mm for the ML distance, and from 7.9 mm 2 to 15.54 mm 2 for the thecal sac area. Pairwise ICCs among reader 1, reader 2, and the AI model ranged from 0.91 and 0.94 for the AP distance and from 0.86 to 0.9 for the ML distance without significant differences. For the thecal sac area, the pairwise ICC between both readers and the AI model of 0.97 each was slightly, but significantly lower than the ICC between reader 1 and reader 2 of 0.99. Similarly, the Dice coefficient and Hausdorff distance between both readers and the AI model were significantly lower than the values between reader 1 and reader 2, overall ranging from 0.93 to 0.95 for the Dice coefficients and 1.1 to 1.44 for the Hausdorff distances.

CONCLUSIONS

The investigated AI model is reliable for assessing the AP and the ML thecal sac diameters with human level accuracies. The small differences for measurement and segmentation of the thecal sac area between the AI model and the radiologists are likely within a clinically acceptable range.

MRI-based automated multitask deep learning system to evaluate supraspinatus tendon injuries

OBJECTIVE

To establish an automated, multitask, MRI-based deep learning system for the detailed evaluation of supraspinatus tendon (SST) injuries.

METHODS

According to arthroscopy findings, 3087 patients were divided into normal, degenerative, and tear groups (groups 0-2). Group 2 was further divided into bursal-side, articular-side, intratendinous, and full-thickness tear groups (groups 2.1-2.4), and external validation was performed with 573 patients. Visual geometry group network 16 (VGG16) was used for preliminary image screening. Then, the rotator cuff multitask learning (RC-MTL) model performed multitask classification (classifiers 1-4). A multistage decision model produced the final output. Model performance was evaluated by receiver operating characteristic (ROC) curve analysis and calculation of related parameters. McNemar's test was used to compare the differences in the diagnostic effects between radiologists and the model. The intraclass correlation coefficient (ICC) was used to assess the radiologists' reliability. p < 0.05 indicated statistical significance.

RESULTS

In the in-group dataset, the area under the ROC curve (AUC) of VGG16 was 0.92, and the average AUCs of RC-MTL classifiers 1-4 were 0.99, 0.98, 0.97, and 0.97, respectively. The average AUC of the automated multitask deep learning system for groups 0-2.4 was 0.98 and 0.97 in the in-group and out-group datasets, respectively. The ICCs of the radiologists were 0.97-0.99. The automated multitask deep learning system outperformed the radiologists in classifying groups 0-2.4 in both the in-group and out-group datasets (p < 0.001).

CONCLUSION

The MRI-based automated multitask deep learning system performed well in diagnosing SST injuries and is comparable to experienced radiologists.

CLINICAL RELEVANCE STATEMENT

Our study established an automated multitask deep learning system to evaluate supraspinatus tendon (SST) injuries and further determine the location of SST tears. The model can potentially improve radiologists' diagnostic efficiency, reduce diagnostic variability, and accurately assess SST injuries.

KEY POINTS

• A detailed classification of supraspinatus tendon tears can help clinical decision-making. • Deep learning enables the detailed classification of supraspinatus tendon injuries. • The proposed automated multitask deep learning system is comparable to radiologists.

Application of Artificial Intelligence in Shoulder Pathology

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.

European Society for Surgery of the Shoulder and Elbow (SECEC) rotator cuff tear registry Delphi consensus

Background

The purpose of this study was to establish consensus statements via a Delphi process on the factors that should be included in a registry for those patients undergoing rotator cuff tear treatment.

Methods

A consensus process on the treatment of rotator cuff utilizing a modified Delphi technique was conducted. Fifty-seven surgeons completed these consensus statements and 9 surgeons declined. The participants were members of the European Society for Surgery of the Shoulder and Elbow committees representing 23 European countries. Thirteen questions were generated regarding the diagnosis and follow-up of rotator cuff tears were distributed, with 3 rounds of questionnaires and final voting occurring. Consensus was defined as achieving 80%-89% agreement, whereas strong consensus was defined as 90%-99% agreement, and unanimous consensus was defined by 100% agreement with a proposed statement.

Results

Of the 13 total questions and consensus statements on rotator cuff tears, 1 achieved unanimous consensus, 6 achieved strong consensus, 5 achieved consensus, and 1 did not achieve consensus. The statement that reached unanimous consensus was that the factors in the patient history that should be evaluated and recorded in the setting of suspected/known rotator cuff tear are age, gender, comorbidities, smoking, traumatic etiology, prior treatment including physical therapy/injections, pain, sleep disturbance, sports, occupation, workmen's compensation, hand dominance, and functional limitations. The statement that did not achieve consensus was related to the role of ultrasound in the initial diagnosis of patients with rotator cuff tears.

Conclusion

Nearly all questions reached consensus among 57 European Society for Surgery of the Shoulder and Elbow members representing 23 different European countries. We encourage surgeons to use this minimum set of variables to establish rotator cuff registries and multicenter studies. By adapting and using compatible variables, data can more easily be compared and eventually merged across countries.

Artificial intelligence powered advancements in upper extremity joint MRI: A review

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.

The Future of Artificial Intelligence in Sports Medicine and Return to Play

Artificial intelligence (AI) has shown tremendous growth over the last decade, with the more recent development of clinical applications in health care. The ability of AI to synthesize large amounts of complex data automatically allows health care providers to access previously unavailable metrics and thus enhance and personalize patient care. These innovations include AI-assisted diagnostic tools, prediction models for each treatment pathway, and various tools for workflow optimization. The extension of AI into sports medicine is still early, but numerous AI-driven algorithms, devices, and research initiatives have delved into predicting and preventing athlete injury, aiding in injury assessment, optimizing recovery plans, monitoring rehabilitation progress, and predicting return to play.

Medical Imaging Applications Developed Using Artificial Intelligence Demonstrate High Internal Validity Yet Are Limited in Scope and Lack External Validation

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.

Development and Clinical Application of Artificial Intelligence Assistant System for Rotator Cuff Ultrasound Scanning

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.

Supraspinatus extraction from MRI based on attention-dense spatial pyramid UNet network

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.

Enhancing prediction of supraspinatus/infraspinatus tendon complex injuries through integration of deep visual features and clinical information: a multicenter two-round assessment study

OBJECTIVE

Develop and evaluate an ensemble clinical machine learning-deep learning (CML-DL) model integrating deep visual features and clinical data to improve the prediction of supraspinatus/infraspinatus tendon complex (SITC) injuries.

METHODS

Patients with suspected SITC injuries were retrospectively recruited from two hospitals, with clinical data and shoulder x-ray radiographs collected. An ensemble CML-DL model was developed for diagnosing normal or insignificant rotator cuff abnormality (NIRCA) and significant rotator cuff tear (SRCT). All patients suspected with SRCT were confirmed by arthroscopy examination. The model's performance was evaluated using sensitivity, specificity, accuracy, and area under the curve (AUC) metrics, and a two-round assessment was conducted to authenticate its clinical applicability.

RESULTS

A total of 974 patients were divided into three cohorts: the training cohort (n = 828), the internal validation cohort (n = 89), and the external validation cohort (n = 57). The CML-DL model, which integrates clinical and deep visual features, demonstrated superior performance compared to individual models of either type. The model's sensitivity, specificity, accuracy, and area under curve (95% confidence interval) were 0.880, 0.812, 0.836, and 0.902 (0.858-0.947), respectively. The CML-DL model exhibited higher sensitivity and specificity compared to or on par with the physicians in all validation cohorts. Furthermore, the assistance of the ensemble CML-DL model resulted in a significant improvement in sensitivity for junior physicians in all validation cohorts, without any reduction in specificity.

CONCLUSIONS

The ensembled CML-DL model provides a solution to help physicians improve the diagnosis performance of SITC injury, especially for junior physicians with limited expertise.

CRITICAL RELEVANCE STATEMENT

The ensembled clinical machine learning-deep learning (CML-DL) model integrating deep visual features and clinical data provides a superior performance in the diagnosis of supraspinatus/infraspinatus tendon complex (SITC) injuries, particularly for junior physicians with limited expertise.

KEY POINTS

1. Integrating clinical and deep visual features improves diagnosing SITC injuries. 2. Ensemble CML-DL model validated for clinical use in two-round assessment. 3. Ensemble model boosts sensitivity in SITC injury diagnosis for junior physicians.

Artificial Intelligence and Machine Learning in Rotator Cuff Tears

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.

Development and clinical validation of deep learning for auto-diagnosis of supraspinatus tears

BACKGROUND

Accurately diagnosing supraspinatus tears based on magnetic resonance imaging (MRI) is challenging and time-combusting due to the experience level variability of the musculoskeletal radiologists and orthopedic surgeons. We developed a deep learning-based model for automatically diagnosing supraspinatus tears (STs) using shoulder MRI and validated its feasibility in clinical practice.

MATERIALS AND METHODS

A total of 701 shoulder MRI data (2804 images) were retrospectively collected for model training and internal test. An additional 69 shoulder MRIs (276 images) were collected from patients who underwent shoulder arthroplasty and constituted the surgery test set for clinical validation. Two advanced convolutional neural networks (CNN) based on Xception were trained and optimized to detect STs. The diagnostic performance of the CNN was evaluated according to its sensitivity, specificity, precision, accuracy, and F1 score. Subgroup analyses were performed to verify its robustness, and we also compared the CNN's performance with that of 4 radiologists and 4 orthopedic surgeons on the surgery and internal test sets.

RESULTS

Optimal diagnostic performance was achieved on the 2D model, from which F1-scores of 0.824 and 0.75, and areas under the ROC curves of 0.921 (95% confidence interval, 0.841-1.000) and 0.882 (0.817-0.947) were observed on the surgery and internal test sets. For the subgroup analysis, the 2D CNN model demonstrated a sensitivity of 0.33-1.000 and 0.625-1.000 for different degrees of tears on the surgery and internal test sets, and there was no significant performance difference between 1.5 and 3.0 T data. Compared with eight clinicians, the 2D CNN model exhibited better diagnostic performance than the junior clinicians and was equivalent to senior clinicians.

CONCLUSIONS

The proposed 2D CNN model realized the adequate and efficient automatic diagnoses of STs, which achieved a comparable performance of junior musculoskeletal radiologists and orthopedic surgeons. It might be conducive to assisting poor-experienced radiologists, especially in community scenarios lacking consulting experts.