Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference

MRI deep learning models for assisted diagnosis of knee pathologies: a systematic review

OBJECTIVES

Despite showing encouraging outcomes, the precision of deep learning (DL) models using different convolutional neural networks (CNNs) for diagnosis remains under investigation. This systematic review aims to summarise the status of DL MRI models developed for assisting the diagnosis of a variety of knee abnormalities.

MATERIALS AND METHODS

Five databases were systematically searched, employing predefined terms such as 'Knee AND 3D AND MRI AND DL'. Selected inclusion criteria were used to screen publications by title, abstract, and full text. The synthesis of results was performed by two independent reviewers.

RESULTS

Fifty-four articles were included. The studies focused on anterior cruciate ligament injuries (n = 19, 36%), osteoarthritis (n = 9, 17%), meniscal injuries (n = 13, 24%), abnormal knee appearance (n = 11, 20%), and other (n = 2, 4%). The DL models in this review primarily used the following CNNs: ResNet (n = 11, 21%), VGG (n = 6, 11%), DenseNet (n = 4, 8%), and DarkNet (n = 3, 6%). DL models showed high-performance metrics compared to ground truth. DL models for the detection of a specific injury outperformed those by up to 4.5% for general abnormality detection.

CONCLUSION

Despite the varied study designs used among the reviewed articles, DL models showed promising outcomes in the assisted detection of selected knee pathologies by MRI. This review underscores the importance of validating these models with larger MRI datasets to close the existing gap between current DL model performance and clinical requirements.

KEY POINTS

Question What is the status of DL model availability for knee pathology detection in MRI and their clinical potential? Findings Pathology-specific DL models reported higher accuracy compared to DL models for the detection of general abnormalities of the knee. DL model performance was mainly influenced by the quantity and diversity of data available for model training. Clinical relevance These findings should encourage future developments to improve patient care, support personalised diagnosis and treatment, optimise costs, and advance artificial intelligence-based medical imaging practices.

Deep learning-assisted detection of meniscus and anterior cruciate ligament combined tears in adult knee magnetic resonance imaging: a crossover study with arthroscopy correlation

AIM

We aimed to compare the diagnostic performance of physicians in the detection of arthroscopically confirmed meniscus and anterior cruciate ligament (ACL) tears on knee magnetic resonance imaging (MRI), with and without assistance from a deep learning (DL) model.

METHODS

We obtained preoperative MR images from 88 knees of patients who underwent arthroscopic meniscal repair, with or without ACL reconstruction. Ninety-eight MR images of knees without signs of meniscus or ACL tears were obtained from a publicly available database after matching on age and ACL status (normal or torn), resulting in a global dataset of 186 MRI examinations. The Keros® (Incepto, Paris) DL algorithm, previously trained for the detection and characterization of meniscus and ACL tears, was used for MRI assessment. Magnetic resonance images were individually, and blindly annotated by three physicians and the DL algorithm. After three weeks, the three human raters repeated image assessment with model assistance, performed in a different order.

RESULTS

The Keros® algorithm achieved an area under the curve (AUC) of 0.96 (95% CI 0.93, 0.99), 0.91 (95% CI 0.85, 0.96), and 0.99 (95% CI 0.98, 0.997) in the detection of medial meniscus, lateral meniscus and ACL tears, respectively. With model assistance, physicians achieved higher sensitivity (91% vs. 83%, p = 0.04) and similar specificity (91% vs. 87%, p = 0.09) in the detection of medial meniscus tears. Regarding lateral meniscus tears, sensitivity and specificity were similar with/without model assistance. Regarding ACL tears, physicians achieved higher specificity when assisted by the algorithm (70% vs. 51%, p = 0.01) but similar sensitivity with/without model assistance (93% vs. 96%, p = 0.13).

CONCLUSIONS

The current model consistently helped physicians in the detection of medial meniscus and ACL tears, notably when they were combined.

LEVEL OF EVIDENCE

Diagnostic study, Level III.

Evaluating potential for AI automation of quantitative and semi-quantitative MRI scoring in arthritis, especially at the knee: a systematic literature review

OBJECTIVE

This systematic review explores key quantitative and semi-quantitative MRI-based scoring systems for arthritis biomarkers, focusing on their potential for automation through AI.

METHODS

A systematic review of Medline, PubMed, and Scopus from 2014 to 2024. Keywords included MRI, arthritis, and quantitative/semi-quantitative. From the initial retrieval of 3321 papers, after exclusions, we evaluated the full-text for 129 studies from the past decade, 74 of which related specifically to knee osteoarthritis.

RESULTS

Publications on MRI arthritis scoring systems peaked in 2021 and have declined in recent years, likely due to a shift toward AI-driven automation. We assessed scoring systems for biomarkers including cartilage thickness, bone marrow edema, effusion/synovitis, erosions, osteophytes, intraosseous and periarticular fat metaplasia, and connective tissue integrity (meniscus/labrum), each varying in suitability for AI. Effusion, due to its high MRI T2 contrast, appears relatively straightforward to automate, while cartilage loss remains difficult to accurately quantify and localize despite heavy research interest. AI demonstrates suitability in meniscal tear detection and the potential to automate other biomarkers like BMEs, bone erosion, and osteophyte formation.

CONCLUSION

AI is increasingly being used to automatically evaluate MRI for arthritis. This review identifies opportunities for AI to enhance longitudinal disease tracking and enable early intervention in arthritis by providing detailed scoring of inflammatory lesions and high-resolution evaluation of structural abnormalities.

Multitask learning for automatic detection of meniscal injury on 3D knee MRI

Magnetic resonance imaging (MRI) of the knee is the recommended diagnostic method before invasive arthroscopy surgery. Nevertheless, interpreting knee MRI scans is a time-consuming process that is vulnerable to inaccuracies and inconsistencies. We proposed a multitask learning network MCSNetatt which efficiently introduces segmentation prior features and enhances classification results through multiscale feature fusion and spatial attention modules. The MRI studies and subsequent arthroscopic diagnosis of 259 knees were collected retrospectively. Models were trained based on multitask loss with coronal and sagittal sequences and fused using logistic regression (LR). We visualized the network's interpretability by the gradient-weighted class activation mapping method. The LR model achieved higher area under the curve and mean average precision of medial and lateral menisci than models trained on a single sagittal or coronal sequence. Our multitask model MCSNetat outperformed the single-task model CNet and two clinicians in classification, with accuracy, precision, recall, F1-score of 0.980, 1.000, 0.952, 0.976 for medial and 0.920, 0.905, 0.905, 0.905 for the lateral, respectively. With the assistance of model results and visualized saliency maps, both clinicians showed improvement in their diagnostic performance. Compared to the baseline segmentation model, our model improved dice similarity coefficient and the 95% Hausdorff distance (HD95) of the lateral meniscus for 2.3% and 0.860 mm in coronal images and 4.4% and 2.253 mm in sagittal images. Our multitask learning network quickly generated accurate clinicopathological classification and segmentation of knee MRI, demonstrating its potential to assist doctors in a clinical setting.

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.

Fully and Weakly Supervised Deep Learning for Meniscal Injury Classification, and Location Based on MRI

Meniscal injury is a common cause of knee joint pain and a precursor to knee osteoarthritis (KOA). The purpose of this study is to develop an automatic pipeline for meniscal injury classification and localization using fully and weakly supervised networks based on MRI images. In this retrospective study, data were from the osteoarthritis initiative (OAI). The MR images were reconstructed using a sagittal intermediate-weighted fat-suppressed turbo spin-echo sequence. (1) We used 130 knees from the OAI to develop the LGSA-UNet model which fuses the features of adjacent slices and adjusts the blocks in Siam to enable the central slice to obtain rich contextual information. (2) One thousand seven hundred and fifty-six knees from the OAI were included to establish segmentation and classification models. The segmentation model achieved a DICE coefficient ranging from 0.84 to 0.93. The AUC values ranged from 0.85 to 0.95 in the binary models. The accuracy for the three types of menisci (normal, tear, and maceration) ranged from 0.60 to 0.88. Furthermore, 206 knees from the orthopedic hospital were used as an external validation data set to evaluate the performance of the model. The segmentation and classification models still performed well on the external validation set. To compare the diagnostic performances between the deep learning (DL) models and radiologists, the external validation sets were sent to two radiologists. The binary classification model outperformed the diagnostic performance of the junior radiologist (0.82-0.87 versus 0.74-0.88). This study highlights the potential of DL in knee meniscus segmentation and injury classification which can help improve diagnostic efficiency.

Evaluating the Quality and Readability of Generative Artificial Intelligence (AI) Chatbot Responses in the Management of Achilles Tendon Rupture

INTRODUCTION

The rise of artificial intelligence (AI), including generative chatbots like ChatGPT (OpenAI, San Francisco, CA, USA), has revolutionized many fields, including healthcare. Patients have gained the ability to prompt chatbots to generate purportedly accurate and individualized healthcare content. This study analyzed the readability and quality of answers to Achilles tendon rupture questions from six generative AI chatbots to evaluate and distinguish their potential as patient education resources.

METHODS

The six AI models used were ChatGPT 3.5, ChatGPT 4, Gemini 1.0 (previously Bard; Google, Mountain View, CA, USA), Gemini 1.5 Pro, Claude (Anthropic, San Francisco, CA, USA) and Grok (xAI, Palo Alto, CA, USA) without prior prompting. Each was asked 10 common patient questions about Achilles tendon rupture, determined by five orthopaedic surgeons. The readability of generative responses was measured using Flesch-Kincaid Reading Grade Level, Gunning Fog, and SMOG (Simple Measure of Gobbledygook). The response quality was subsequently graded using the DISCERN criteria by five blinded orthopaedic surgeons.

RESULTS

Gemini 1.0 generated statistically significant differences in ease of readability (closest to average American reading level) than responses from ChatGPT 3.5, ChatGPT 4, and Claude. Additionally, mean DISCERN scores demonstrated significantly higher quality of responses from Gemini 1.0 (63.0±5.1) and ChatGPT 4 (63.8±6.2) than ChatGPT 3.5 (53.8±3.8), Claude (55.0±3.8), and Grok (54.2±4.8). However, the overall quality (question 16, DISCERN) of each model was averaged and graded at an above-average level (range, 3.4-4.4).

DISCUSSION AND CONCLUSION

Our results indicate that generative chatbots can potentially serve as patient education resources alongside physicians. Although some models lacked sufficient content, each performed above average in overall quality. With the lowest readability and highest DISCERN scores, Gemini 1.0 outperformed ChatGPT, Claude, and Grok and potentially emerged as the simplest and most reliable generative chatbot regarding management of Achilles tendon rupture.

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.

Artificial intelligence applied to magnetic resonance imaging reliably detects the presence, but not the location, of meniscus tears: a systematic review and meta-analysis

OBJECTIVES

To review and compare the accuracy of convolutional neural networks (CNN) for the diagnosis of meniscal tears in the current literature and analyze the decision-making processes utilized by these CNN algorithms.

MATERIALS AND METHODS

PubMed, MEDLINE, EMBASE, and Cochrane databases up to December 2022 were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) statement. Risk of analysis was used for all identified articles. Predictive performance values, including sensitivity and specificity, were extracted for quantitative analysis. The meta-analysis was divided between AI prediction models identifying the presence of meniscus tears and the location of meniscus tears.

RESULTS

Eleven articles were included in the final review, with a total of 13,467 patients and 57,551 images. Heterogeneity was statistically significantly large for the sensitivity of the tear identification analysis (I2 = 79%). A higher level of accuracy was observed in identifying the presence of a meniscal tear over locating tears in specific regions of the meniscus (AUC, 0.939 vs 0.905). Pooled sensitivity and specificity were 0.87 (95% confidence interval (CI) 0.80-0.91) and 0.89 (95% CI 0.83-0.93) for meniscus tear identification and 0.88 (95% CI 0.82-0.91) and 0.84 (95% CI 0.81-0.85) for locating the tears.

CONCLUSIONS

AI prediction models achieved favorable performance in the diagnosis, but not location, of meniscus tears. Further studies on the clinical utilities of deep learning should include standardized reporting, external validation, and full reports of the predictive performances of these models, with a view to localizing tears more accurately.

CLINICAL RELEVANCE STATEMENT

Meniscus tears are hard to diagnose in the knee magnetic resonance images. AI prediction models may play an important role in improving the diagnostic accuracy of clinicians and radiologists.

KEY POINTS

• Artificial intelligence (AI) provides great potential in improving the diagnosis of meniscus tears. • The pooled diagnostic performance for artificial intelligence (AI) in identifying meniscus tears was better (sensitivity 87%, specificity 89%) than locating the tears (sensitivity 88%, specificity 84%). • AI is good at confirming the diagnosis of meniscus tears, but future work is required to guide the management of the disease.

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.

Orthopaedic surgeons display a positive outlook towards artificial intelligence: A survey among members of the AGA Society for Arthroscopy and Joint Surgery

Purpose

The purpose of this study was to evaluate the perspective of orthopaedic surgeons on the impact of artificial intelligence (AI) and to evaluate the influence of experience, workplace setting and familiarity with digital solutions on views on AI.

Methods

Orthopaedic surgeons of the AGA Society for Arthroscopy and Joint Surgery were invited to participate in an online, cross-sectional survey designed to gather information on professional background, subjective AI knowledge, opinion on the future impact of AI, openness towards different applications of AI, and perceived advantages and disadvantages of AI. Subgroup analyses were performed to examine the influence of experience, workplace setting and openness towards digital solutions on perspectives towards AI.

Results

Overall, 360 orthopaedic surgeons participated. The majority indicated average (43.6%) or rudimentary (38.1%) AI knowledge. Most (54.5%) expected AI to substantially influence orthopaedics within 5-10 years, predominantly as a complementary tool (91.1%). Preoperative planning (83.8%) was identified as the most likely clinical use case. A lack of consensus was observed regarding acceptable error levels. Time savings in preoperative planning (62.5%) and improved documentation (81%) were identified as notable advantages while declining skills of the next generation (64.5%) were rated as the most substantial drawback. There were significant differences in subjective AI knowledge depending on participants' experience (p = 0.021) and familiarity with digital solutions (p < 0.001), acceptable error levels depending on workplace setting (p = 0.004), and prediction of AI impact depending on familiarity with digital solutions (p < 0.001).

Conclusion

The majority of orthopaedic surgeons in this survey anticipated a notable positive impact of AI on their field, primarily as an assistive technology. A lack of consensus on acceptable error levels of AI and concerns about declining skills among future surgeons were observed.

Level of Evidence

Level IV, cross-sectional study.

A Comprehensive Evaluation of Deep Learning Models on Knee MRIs for the Diagnosis and Classification of Meniscal Tears: A Systematic Review and Meta-Analysis

OBJECTIVES

This study delves into the cutting-edge field of deep learning techniques, particularly deep convolutional neural networks (DCNNs), which have demonstrated unprecedented potential in assisting radiologists and orthopedic surgeons in precisely identifying meniscal tears. This research aims to evaluate the effectiveness of deep learning models in recognizing, localizing, describing, and categorizing meniscal tears in magnetic resonance images (MRIs).

MATERIALS AND METHODS

This systematic review was rigorously conducted, strictly following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Extensive searches were conducted on MEDLINE (PubMed), Web of Science, Cochrane Library, and Google Scholar. All identified articles underwent a comprehensive risk of bias analysis. Predictive performance values were either extracted or calculated for quantitative analysis, including sensitivity and specificity. The meta-analysis was performed for all prediction models that identified the presence and location of meniscus tears.

RESULTS

This study's findings underscore that a range of deep learning models exhibit robust performance in detecting and classifying meniscal tears, in one case surpassing the expertise of musculoskeletal radiologists. Most studies in this review concentrated on identifying tears in the medial or lateral meniscus and even precisely locating tears-whether in the anterior or posterior horn-with exceptional accuracy, as demonstrated by AUC values ranging from 0.83 to 0.94.

CONCLUSIONS

Based on these findings, deep learning models have showcased significant potential in analyzing knee MR images by learning intricate details within images. They offer precise outcomes across diverse tasks, including segmenting specific anatomical structures and identifying pathological regions. Contributions: This study focused exclusively on DL models for identifying and localizing meniscus tears. It presents a meta-analysis that includes eight studies for detecting the presence of a torn meniscus and a meta-analysis of three studies with low heterogeneity that localize and classify the menisci. Another novelty is the analysis of arthroscopic surgery as ground truth. The quality of the studies was assessed against the CLAIM checklist, and the risk of bias was determined using the QUADAS-2 tool.

Recommended Requirements and Essential Elements for Proper Reporting of the Use of Artificial Intelligence Machine Learning Tools in Biomedical Research and Scientific Publications

Essential elements required for proper use of artificial intelligence machine learning tools in biomedical research and scientific publications include (1) explanation justifying why a machine learning approach contributes to the purpose of the study; (2) description of the adequacy of the data (input) to produce the desired results (output); (3) details of the algorithmic (i.e., computational) approach including methods for organizing the data (preprocessing); the machine learning computational algorithm(s) assessed; on what data the models were trained; the presence of bias and efforts to mitigate these effects; and the methods for quantifying the variables (features) most influential in determining the results (e.g., Shapley values); (4) description of methods, and reporting of results, quantitating performance in terms of both model accuracy and model calibration (level of confidence in the model's predictions); (5) availability of the programming code (including a link to the code when available-ideally, the code should be available); (6) discussion of model internal validation (results applicable and sensitive to the population investigated and data on which the model was trained) and external validation (were the results investigated as to whether they are generalizable to different populations? If not, consideration of this limitation and discussion of plans for external validation, i.e., next steps). As biomedical research submissions using artificial intelligence technology increase, these requirements could facilitate purposeful use and comprehensive methodological reporting.

Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears

OBJECTIVE

The purpose of this systematic review was to summarize the results of original research studies evaluating the characteristics and performance of deep learning models for detection of knee ligament and meniscus tears on MRI.

MATERIALS AND METHODS

We searched PubMed for studies published as of February 2, 2022 for original studies evaluating development and evaluation of deep learning models for MRI diagnosis of knee ligament or meniscus tears. We summarized study details according to multiple criteria including baseline article details, model creation, deep learning details, and model evaluation.

RESULTS

19 studies were included with radiology departments leading the publications in deep learning development and implementation for detecting knee injuries via MRI. Among the studies, there was a lack of standard reporting and inconsistently described development details. However, all included studies reported consistently high model performance that significantly supplemented human reader performance.

CONCLUSION

From our review, we found radiology departments have been leading deep learning development for injury detection on knee MRIs. Although studies inconsistently described DL model development details, all reported high model performance, indicating great promise for DL in knee MRI analysis.

A Comprehensive Review on MRI-based Knee Joint Segmentation and Analysis Techniques

Using magnetic resonance imaging (MRI) in osteoarthritis pathogenesis research has proven extremely beneficial. However, it is always challenging for both clinicians and researchers to detect morphological changes in knee joints from magnetic resonance (MR) imaging since the surrounding tissues produce identical signals in MR studies, making it difficult to distinguish between them. Segmenting the knee bone, articular cartilage and menisci from the MR images allows one to examine the complete volume of the bone, articular cartilage, and menisci. It can also be used to assess certain characteristics quantitatively. However, segmentation is a laborious and time-consuming operation that requires sufficient training to complete correctly. With the advancement of MRI technology and computational methods, researchers have developed several algorithms to automate the task of individual knee bone, articular cartilage and meniscus segmentation during the last two decades. This systematic review aims to present available fully and semi-automatic segmentation methods for knee bone, cartilage, and meniscus published in different scientific articles. This review provides a vivid description of the scientific advancements to clinicians and researchers in this field of image analysis and segmentation, which helps the development of novel automated methods for clinical applications. The review also contains the recently developed fully automated deep learning-based methods for segmentation, which not only provides better results compared to the conventional techniques but also open a new field of research in Medical Imaging.

The Use of Artificial Intelligence for the Prediction of Periprosthetic Joint Infection Following Aseptic Revision Total Knee Arthroplasty

Periprosthetic joint infection (PJI) following revision total knee arthroplasty (TKA) for aseptic failure is associated with poor outcomes, patient morbidity, and high health care expenditures. The aim of this study was to develop novel machine learning algorithms for the prediction of PJI following revision TKA for patients with aseptic indications for revision surgery. A single-institution database consisting of 1,432 consecutive revision TKA patients with aseptic etiologies was retrospectively identified. The patient cohort included 208 patients (14.5%) who underwent re-revision surgery for PJI. Three machine learning algorithms (artificial neural networks, support vector machines, k-nearest neighbors) were developed to predict this outcome and these models were assessed by discrimination, calibration, and decision curve analysis. This is a retrospective study. Among the three machine learning models, the neural network model achieved the best performance across discrimination (area under the receiver operating characteristic curve = 0.78), calibration, and decision curve analysis. The strongest predictors for PJI following revision TKA for aseptic reasons were prior open procedure prior to revision surgery, drug abuse, obesity, and diabetes. This study utilized machine learning as a tool for the prediction of PJI following revision TKA for aseptic failure with excellent performance. The validated machine learning models can aid surgeons in patient-specific risk stratifying to assist in preoperative counseling and clinical decision making for patients undergoing aseptic revision TKA.

How AI May Transform Musculoskeletal Imaging

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Feasibility of the fat-suppression image-subtraction method using deep learning for abnormality detection on knee MRI

Purpose

To evaluate the feasibility of using a deep learning (DL) model to generate fat-suppression images and detect abnormalities on knee magnetic resonance imaging (MRI) through the fat-suppression image-subtraction method.

Material and methods

A total of 45 knee MRI studies in patients with knee disorders and 12 knee MRI studies in healthy volunteers were enrolled. The DL model was developed using 2-dimensional convolutional neural networks for generating fat-suppression images and subtracting generated fat-suppression images without any abnormal findings from those with normal/abnormal findings and detecting/classifying abnormalities on knee MRI. The image qualities of the generated fat-suppression images and subtraction-images were assessed. The accuracy, average precision, average recall, F-measure, sensitivity, and area under the receiver operator characteristic curve (AUROC) of DL for each abnormality were calculated.

Results

A total of 2472 image datasets, each consisting of one slice of original T1WI, original intermediate-weighted images, generated fat-suppression (FS)-intermediate-weighted images without any abnormal findings, generated FS-intermediate-weighted images with normal/abnormal findings, and subtraction images between the generated FS-intermediate-weighted images at the same cross-section, were created. The generated fat-suppression images were of adequate image quality. Of the 2472 subtraction-images, 2203 (89.1%) were judged to be of adequate image quality. The accuracies for overall abnormalities, anterior cruciate ligament, bone marrow, cartilage, meniscus, and others were 89.5-95.1%. The average precision, average recall, and F-measure were 73.4-90.6%, 77.5-89.4%, and 78.4-89.4%, respectively. The sensitivity was 57.4-90.5%. The AUROCs were 0.910-0.979.

Conclusions

The DL model was able to generate fat-suppression images of sufficient quality to detect abnormalities on knee MRI through the fat-suppression image-subtraction method.

A practical guide to the implementation of AI in orthopaedic research - part 1: opportunities in clinical application and overcoming existing challenges

Artificial intelligence (AI) has the potential to transform medical research by improving disease diagnosis, clinical decision-making, and outcome prediction. Despite the rapid adoption of AI and machine learning (ML) in other domains and industry, deployment in medical research and clinical practice poses several challenges due to the inherent characteristics and barriers of the healthcare sector. Therefore, researchers aiming to perform AI-intensive studies require a fundamental understanding of the key concepts, biases, and clinical safety concerns associated with the use of AI. Through the analysis of large, multimodal datasets, AI has the potential to revolutionize orthopaedic research, with new insights regarding the optimal diagnosis and management of patients affected musculoskeletal injury and disease. The article is the first in a series introducing fundamental concepts and best practices to guide healthcare professionals and researcher interested in performing AI-intensive orthopaedic research studies. The vast potential of AI in orthopaedics is illustrated through examples involving disease- or injury-specific outcome prediction, medical image analysis, clinical decision support systems and digital twin technology. Furthermore, it is essential to address the role of human involvement in training unbiased, generalizable AI models, their explainability in high-risk clinical settings and the implementation of expert oversight and clinical safety measures for failure. In conclusion, the opportunities and challenges of AI in medicine are presented to ensure the safe and ethical deployment of AI models for orthopaedic research and clinical application. Level of evidence IV.

A Comprehensive Review on the Diagnosis of Knee Injury by Deep Learning-Based Magnetic Resonance Imaging

The continual improvement in the field of medical diagnosis has led to the monopoly of using deep learning (DL)-based magnetic resonance imaging (MRI) for the diagnosis of knee injury related to meniscal injury, ligament injury including the cruciate ligaments, collateral ligaments and medial patella-femoral ligament, and cartilage injury. The present systematic review was done by PubMed and Directory of Open Access Journals (DOAJ), wherein we finalised 24 studies conducted on the accuracy of DL MRI studies for knee injury identification. The studies showed an accuracy of 72.5% to 100% indicating that DL MRI holds an equivalent performance as humans in decision-making and management of knee injuries. This further opens up future exploration for improving MRI-based diagnosis keeping in mind the limitations of verification bias and data imbalance in ground truth subjectivity.

Visual Cascaded-Progressive Convolutional Neural Network (C-PCNN) for Diagnosis of Meniscus Injury

OBJECTIVE

The objective of this study is to develop a novel automatic convolutional neural network (CNN) that aids in the diagnosis of meniscus injury, while enabling the visualization of lesion characteristics. This will improve the accuracy and reduce diagnosis times.

METHODS

We presented a cascaded-progressive convolutional neural network (C-PCNN) method for diagnosing meniscus injuries using magnetic resonance imaging (MRI). A total of 1396 images collected in the hospital were used for training and testing. The method used for training and testing was 5-fold cross validation. Using intraoperative arthroscopic diagnosis and MRI diagnosis as criteria, the C-PCNN was evaluated based on accuracy, sensitivity, specificity, receiver operating characteristic (ROC), and evaluation performance. At the same time, the diagnostic accuracy of doctors with the assistance of cascade- progressive convolutional neural networks was evaluated. The diagnostic accuracy of a C-PCNN assistant with an attending doctor and chief doctor was compared to evaluate the clinical significance.

RESULTS

C-PCNN showed 85.6% accuracy in diagnosing and identifying anterior horn injury, and 92% accuracy in diagnosing and identifying posterior horn injury. The average accuracy of C-PCNN was 89.8%, AUC = 0.86. The diagnosis accuracy of the attending physician with the aid of the C-PCNN was comparable to that of the chief physician.

CONCLUSION

The C-PCNN-based MRI technique for diagnosing knee meniscus injuries has significant practical value in clinical practice. With a high rate of accuracy, clinical auxiliary physicians can increase the speed and accuracy of diagnosis and decrease the number of incorrect diagnoses.

Utilizing a Digital Swarm Intelligence Platform to Improve Consensus Among Radiologists and Exploring Its Applications

Radiologists today play a central role in making diagnostic decisions and labeling images for training and benchmarking artificial intelligence (AI) algorithms. A key concern is low inter-reader reliability (IRR) seen between experts when interpreting challenging cases. While team-based decisions are known to outperform individual decisions, inter-personal biases often creep up in group interactions which limit nondominant participants from expressing true opinions. To overcome the dual problems of low consensus and interpersonal bias, we explored a solution modeled on bee swarms. Two separate cohorts, three board-certified radiologists, (cohort 1), and five radiology residents (cohort 2) collaborated on a digital swarm platform in real time and in a blinded fashion, grading meniscal lesions on knee MR exams. These consensus votes were benchmarked against clinical (arthroscopy) and radiological (senior-most radiologist) standards of reference using Cohen's kappa. The IRR of the consensus votes was then compared to the IRR of the majority and most confident votes of the two cohorts. IRR was also calculated for predictions from a meniscal lesion detecting AI algorithm. The attending cohort saw an improvement of 23% in IRR of swarm votes (k = 0.34) over majority vote (k = 0.11). Similar improvement of 23% in IRR (k = 0.25) in 3-resident swarm votes over majority vote (k = 0.02) was observed. The 5-resident swarm had an even higher improvement of 30% in IRR (k = 0.37) over majority vote (k = 0.07). The swarm consensus votes outperformed individual and majority vote decision in both the radiologists and resident cohorts. The attending and resident swarms also outperformed predictions from a state-of-the-art AI algorithm.

Deep learning-assisted diagnosis of femoral trochlear dysplasia based on magnetic resonance imaging measurements

BACKGROUND

Femoral trochlear dysplasia (FTD) is an important risk factor for patellar instability. Dejour classification is widely used at present and relies on standard lateral X-rays, which are not common in clinical work. Therefore, magnetic resonance imaging (MRI) has become the first choice for the diagnosis of FTD. However, manually measuring is tedious, time-consuming, and easily produces great variability.

AIM

To use artificial intelligence (AI) to assist diagnosing FTD on MRI images and to evaluate its reliability.

METHODS

We searched 464 knee MRI cases between January 2019 and December 2020, including FTD (n = 202) and normal trochlea (n = 252). This paper adopts the heatmap regression method to detect the key points network. For the final evaluation, several metrics (accuracy, sensitivity, specificity, etc.) were calculated.

RESULTS

The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of the AI model ranged from 0.74-0.96. All values were superior to junior doctors and intermediate doctors, similar to senior doctors. However, diagnostic time was much lower than that of junior doctors and intermediate doctors.

CONCLUSION

The diagnosis of FTD on knee MRI can be aided by AI and can be achieved with a high level of accuracy.

Automatic Detection of Meniscus Tears Using Backbone Convolutional Neural Networks on Knee MRI

BACKGROUND

Timely diagnosis of meniscus injuries is key for preventing knee joint dysfunction and improving patient outcomes because it decreases morbidity and facilitates treatment planning.

PURPOSE

To train and evaluate a deep learning model for automated detection of meniscus tears on knee magnetic resonance imaging (MRI).

STUDY TYPE

Bicentric retrospective study.

SUBJECTS

In total, 584 knee MRI studies, divided among training (n = 234), testing (n = 200), and external validation (n = 150) data sets, were used in this study. The public data set MRNet was used as a second external validation data set to evaluate the performance of the model.

SEQUENCE

A 3 T, coronal, and sagittal images from T1-weighted proton density (PD) fast spin-echo (FSE) with fat saturation and T2-weighted FSE with fat saturation sequences.

ASSESSMENT

The detection system for meniscus tear was based on the improved YOLOv4 model with Darknet-53 as the backbone. The performance of the model was also compared with that of three radiologists of varying levels of experience. The determination of the presence of a meniscus tear from surgery reports was used as the ground truth for the images.

STATISTICAL TESTS

Sensitivity, specificity, prevalence, positive predictive value, negative predictive value, accuracy, and receiver operating characteristic curve were used to evaluate the performance of the detection model. Two-way analysis of variance, Wilcoxon signed-rank test, and Tukey's multiple tests were used to evaluate differences in performance between the model and radiologists.

RESULTS

The overall accuracies for detecting meniscus tears using our model on the internal testing, internal validation, and external validation data sets were 95.4%, 95.8%, and 78.8%, respectively. One radiologist had significantly lower performance than our model in detecting meniscal tears (accuracy: 0.9025 ± 0.093 vs. 0.9580 ± 0.025).

DATA CONCLUSION

The proposed model had high sensitivity, specificity, and accuracy for detecting meniscus tears on knee MRIs.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Application of artificial intelligence to imaging interpretations in the musculoskeletal area: Where are we? Where are we going?

The interest of researchers, clinicians and radiologists, in artificial intelligence (AI) continues to grow. Deep learning is a subset of machine learning, in which the computer algorithm itself can determine the optimal imaging features to answer a clinical question. Convolutional neural networks are the most common architecture for performing deep learning on medical images. The various musculoskeletal applications of deep learning are the detection of abnormalities on X-rays or cross-sectional images (CT, MRI), for example the detection of fractures, meniscal tears, anterior cruciate ligament tears, degenerative lesions of the spine, bone metastases, classification of e.g., dural sac stenosis, degeneration of intervertebral discs, assessment of skeletal age, and segmentation, for example of cartilage. Software developments are already impacting the daily practice of orthopedic imaging by automatically detecting fractures on radiographs. Improving image acquisition protocols, improving the quality of low-dose CT images, reducing acquisition times in MRI, or improving MR image resolution is possible through deep learning. Deep learning offers an automated way to offload time-consuming manual processes and improve practitioner performance. This article reviews the current state of AI in musculoskeletal imaging.

Radiomics and Deep Learning for Disease Detection in Musculoskeletal Radiology: An Overview of Novel MRI- and CT-Based Approaches

ABSTRACT

Radiomics and machine learning-based methods offer exciting opportunities for improving diagnostic performance and efficiency in musculoskeletal radiology for various tasks, including acute injuries, chronic conditions, spinal abnormalities, and neoplasms. While early radiomics-based methods were often limited to a smaller number of higher-order image feature extractions, applying machine learning-based analytic models, multifactorial correlations, and classifiers now permits big data processing and testing thousands of features to identify relevant markers. A growing number of novel deep learning-based methods describe magnetic resonance imaging- and computed tomography-based algorithms for diagnosing anterior cruciate ligament tears, meniscus tears, articular cartilage defects, rotator cuff tears, fractures, metastatic skeletal disease, and soft tissue tumors. Initial radiomics and deep learning techniques have focused on binary detection tasks, such as determining the presence or absence of a single abnormality and differentiation of benign versus malignant. Newer-generation algorithms aim to include practically relevant multiclass characterization of detected abnormalities, such as typing and malignancy grading of neoplasms. So-called delta-radiomics assess tumor features before and after treatment, with temporal changes of radiomics features serving as surrogate markers for tumor responses to treatment. New approaches also predict treatment success rates, surgical resection completeness, and recurrence risk. Practice-relevant goals for the next generation of algorithms include diagnostic whole-organ and advanced classification capabilities. Important research objectives to fill current knowledge gaps include well-designed research studies to understand how diagnostic performances and suggested efficiency gains of isolated research settings translate into routine daily clinical practice. This article summarizes current radiomics- and machine learning-based magnetic resonance imaging and computed tomography approaches for musculoskeletal disease detection and offers a perspective on future goals and objectives.

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

OBJECTIVES

The aim is to validate the performance of a deep convolutional neural network (DCNN) for vertebral body measurements and insufficiency fracture detection on lumbar spine MRI.

METHODS

This retrospective analysis included 1000 vertebral bodies in 200 patients (age 75.2 ± 9.8 years) who underwent lumbar spine MRI at multiple institutions. 160/200 patients had ≥ one vertebral body insufficiency fracture, 40/200 had no fracture. The performance of the DCNN and that of two fellowship-trained musculoskeletal radiologists in vertebral body measurements (anterior/posterior height, extent of endplate concavity, vertebral angle) and evaluation for insufficiency fractures were compared. Statistics included (a) interobserver reliability metrics using intraclass correlation coefficient (ICC), kappa statistics, and Bland-Altman analysis, and (b) diagnostic performance metrics (sensitivity, specificity, accuracy). A statistically significant difference was accepted if the 95% confidence intervals did not overlap.

RESULTS

The inter-reader agreement between radiologists and the DCNN was excellent for vertebral body measurements, with ICC values of > 0.94 for anterior and posterior vertebral height and vertebral angle, and good to excellent for superior and inferior endplate concavity with ICC values of 0.79-0.85. The performance of the DCNN in fracture detection yielded a sensitivity of 0.941 (0.903-0.968), specificity of 0.969 (0.954-0.980), and accuracy of 0.962 (0.948-0.973). The diagnostic performance of the DCNN was independent of the radiological institution (accuracy 0.964 vs. 0.960), type of MRI scanner (accuracy 0.957 vs. 0.964), and magnetic field strength (accuracy 0.966 vs. 0.957).

CONCLUSIONS

A DCNN can achieve high diagnostic performance in vertebral body measurements and insufficiency fracture detection on heterogeneous lumbar spine MRI.

KEY POINTS

• A DCNN has the potential for high diagnostic performance in measuring vertebral bodies and detecting insufficiency fractures of the lumbar spine.

Deep convolutional feature details for better knee disorder diagnoses in magnetic resonance images

Convolutional neural networks (CNNs) applied to magnetic resonance imaging (MRI) have demonstrated their ability in the automatic diagnosis of knee injuries. Despite the promising results, the currently available solutions do not take into account the particular anatomy of knee disorders. Existing works have shown that injuries are localized in small-sized knee regions near the center of MRI scans. Based on such insights, we propose MRPyrNet, a CNN architecture capable of extracting more relevant features from these regions. Our solution is composed of a Feature Pyramid Network with Pyramidal Detail Pooling, and can be plugged into any existing CNN-based diagnostic pipeline. The first module aims to enhance the CNN intermediate features to better detect the small-sized appearance of disorders, while the second one captures such kind of evidence by maintaining its detailed information. An extensive evaluation campaign is conducted to understand in-depth the potential of the proposed solution. The experimental results achieved demonstrate that the application of MRPyrNet to baseline methodologies improves their diagnostic capability, especially in the case of anterior cruciate ligament tear and meniscal tear because of MRPyrNet's ability in exploiting the relevant appearance features of such disorders. Code is available at https://github.com/matteo-dunnhofer/MRPyrNet.

[Automatic identification algorithm of meniscus tear based on radiomics of knee MRI]

OBJECTIVE

To establish a classification model based on knee MRI radiomics, realize automatic identification of meniscus tear, and provide reference for accurate diagnosis of meniscus injury.

METHODS

A total of 228 patients (246 knees) with meniscus injury who were admitted between July 2018 and March 2021 were selected as the research objects. There were 146 males and 82 females; the age ranged from 9 to 76 years, with a median age of 53 years. There were 210 cases of meniscus injury in one knee and 18 cases in both knees. All the patients were confirmed by arthroscopy, among which 117 knees with meniscus tear and 129 knees with meniscus non-tear injury. The proton density weighted-spectral attenuated inversion recovery (PDW-SPAIR) sequence images of sagittal MRI were collected, and two doctors performed radiomics studies. The 246 knees were randomly divided into training group and testing group according to the ratio of 7∶3. First, ITK-SNAP3.6.0 software was used to extract the region of interest (ROI) of the meniscus and radiomic features. After retaining the radiomic features with intraclass correlation coefficient (ICC)>0.8, the max-relevance and min-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were used for filtering the features to establish an automatic identification model of meniscus tear. The receiver operator characteristic curve (ROC) and the corresponding area under the ROC curve (AUC) was obtained; the model performance was comprehensively evaluated by calculating the accuracy, sensitivity, and specificity.

RESULTS

A total of 1 316-dimensional radiomic features were extracted from the meniscus ROI, and the ICC within the group and ICC between the groups of the 981-dimensional radiomic features were both greater than 0.80. The redundant information in the 981-dimensional radiomic features was eliminated by mRMR, and the 20-dimensional radiomic features were retained. The optimal feature subset was further selected by LASSO, and 8-dimensional radiomic features were selected. The average ICC within the group and the average ICC between the groups were 0.942 and 0.920, respectively. The AUC of the training group was 0.889±0.036 [95% CI (0.845, 0.942), P<0.001], and the accuracy, sensitivity, and specificity were 0.873, 0.869, and 0.842, respectively; the AUC of the testing group was 0.876±0.036 [95% CI (0.875, 0.984), P<0.001], and the accuracy, sensitivity, and specificity were 0.862, 0.851, and 0.845, respectively.

CONCLUSION

The model established by the radiomics method has good automatic identification performance of meniscus tear.

Meaningless Applications and Misguided Methodologies in Artificial Intelligence-Related Orthopaedic Research Propagates Hype Over Hope

There exists great hope and hype in the literature surrounding applications of artificial intelligence (AI) to orthopaedic surgery. Between 2018 and 2021, a total of 178 AI-related articles were published in orthopaedics. However, for every 2 original research papers that apply AI to orthopaedics, a commentary or review is published (30.3%). AI-related research in orthopaedics frequently fails to provide use cases that offer the uninitiated an opportunity to appraise the importance of AI by studying meaningful questions, evaluating unknown hypotheses, or analyzing quality data. The hype perpetuates a feed-forward cycle that relegates AI to a meaningless buzzword by rewarding those with nascent understanding and rudimentary technical knowhow into committing several basic errors: (1) inappropriately conflating vernacular ("AI/machine learning"), (2) repackaging registry data, (3) prematurely releasing internally validated algorithms, (4) overstating the "black box phenomenon" by failing to provide weighted analysis, (5) claiming to evaluate AI rather than the data itself, and (6) withholding full model architecture code. Relevant AI-specific guidelines are forthcoming, but forced application of the original Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines designed for regression analyses is irrelevant and misleading. To safeguard meaningful use, AI-related research efforts in orthopaedics should be (1) directed toward administrative support over clinical evaluation and management, (2) require the use of the advanced model, and (3) answer a question that was previously unknown, unanswered, or unquantifiable.

MRI evaluation of meniscal anatomy: which parameters reach the best inter-observer concordance?

Purpose

The aim of the study is to evaluate which MRI parameters achieve the best degree of inter-individual concordance in the description of meniscal fibrocartilage, regarding its morphology, signal and position.

Materials and methods

Eighty-nine knee MRIs were included in the study, retrospectively re-evaluated by three radiologists who completed a binary report (normal/abnormal) describing the meniscus signal, position relative to the tibial plateau margin and morphology. The inter-individual concordance value was calculated using Cohen's test.

Results

We obtained different inter-individual concordance values according to the parameters considered. The concordance was poor in the description of the meniscal position relative to the tibial plateau margin (average k = 0.6); the result was comparable in the description of the meniscal morphology (average k = 0.56). The best results were obtained with the meniscal signal analysis (average k = 0.8).

Conclusion

To the best of our knowledge, there are no studies in the literature assessing the concordance between multiple readers in the description of the parameters we studied. The results we obtained suggest that the most reliable parameter for describing meniscal fibrocartilage is its signal intensity, whereas morphology and position may lead to different interpretations that are not always unequivocal.

Development of convolutional neural network model for diagnosing meniscus tear using magnetic resonance image

BACKGROUND

Deep learning (DL) is an advanced machine learning approach used in diverse areas, such as image analysis, bioinformatics, and natural language processing. A convolutional neural network (CNN) is a representative DL model that is advantageous for image recognition and classification. In this study, we aimed to develop a CNN to detect meniscal tears and classify tear types using coronal and sagittal magnetic resonance (MR) images of each patient.

METHODS

We retrospectively collected 599 cases (medial meniscus tear = 384, lateral meniscus tear = 167, and medial and lateral meniscus tear = 48) of knee MR images from patients with meniscal tears and 449 cases of knee MR images from patients without meniscal tears. To develop the DL model for evaluating the presence of meniscal tears, all the collected knee MR images of 1048 cases were used. To develop the DL model for evaluating the type of meniscal tear, 538 cases with meniscal tears (horizontal tear = 268, complex tear = 147, radial tear = 48, and longitudinal tear = 75) and 449 cases without meniscal tears were used. Additionally, a CNN algorithm was used. To measure the model's performance, 70% of the included data were randomly assigned to the training set, and the remaining 30% were assigned to the test set.

RESULTS

The area under the curves (AUCs) of our model were 0.889, 0.817, and 0.924 for medial meniscal tears, lateral meniscal tears, and medial and lateral meniscal tears, respectively. The AUCs of the horizontal, complex, radial, and longitudinal tears were 0.761, 0.850, 0.601, and 0.858, respectively.

CONCLUSION

Our study showed that the CNN model has the potential to be used in diagnosing the presence of meniscal tears and differentiating the types of meniscal tears.

Identification and diagnosis of meniscus tear by magnetic resonance imaging using a deep learning model

Objective

Meniscus tear is a common problem in sports trauma, and its imaging diagnosis mainly relies on MRI. To improve the diagnostic accuracy and efficiency, a deep learning model was employed in this study and the identification efficiency was evaluated.

Methods

Standard knee MRI images from 924 individual patients were used to complete the training, validation and testing processes. Mask regional convolutional neural network (R–CNN) was used to build the deep learning network structure, and ResNet50 was adopted to develop the backbone network. The deep learning model was trained and validated with a dataset containing 504 and 220 patients, respectively. Internal testing was performed based on a dataset of 200 patients, and 180 patients from 8 hospitals were regarded as an external dataset for model validation. Additionally, 40 patients who were diagnosed by the arthroscopic surgery were enrolled as the final test dataset.

Results

After training and validation, the deep learning model effectively recognized healthy and injured menisci. Average precision for the three types of menisci (healthy, torn and degenerated menisci) ranged from 68% to 80%. Diagnostic accuracy for healthy, torn and degenerated menisci was 87.50%, 86.96%, and 84.78%, respectively. Validation results from external dataset demonstrated that the accuracy of diagnosing torn and intact meniscus tear through 3.0T MRI images was higher than 80%, while the accuracy verified by arthroscopic surgery was 87.50%.

Conclusion

Mask R–CNN effectively identified and diagnosed meniscal injuries, especially for tears that occurred in different parts of the meniscus. The recognition ability was admirable, and the diagnostic accuracy could be further improved with increased training sample size. Therefore, this deep learning model showed great potential in diagnosing meniscus injuries.

Translational potential of this article

Deep learning model exerted unique effect in terms of reducing doctors’ workload and improving diagnostic accuracy. Injured and healthy menisci could be more accurately identified and classified based on training and learning datasets. This model could also distinguish torn from degenerated menisci, making it an effective tool for MRI-assisted diagnosis of meniscus injuries in clinical practice.

Automatic MRI segmentation of pectoralis major muscle using deep learning

To develop and validate a deep convolutional neural network (CNN) method capable of selecting the greatest Pectoralis Major Cross-Sectional Area (PMM-CSA) and automatically segmenting PMM on an axial Magnetic Resonance Imaging (MRI). We hypothesized a CNN technique can accurately perform both tasks compared with manual reference standards. Our method is based on two steps: (A) segmentation model, (B) PMM-CSA selection. In step A, we manually segmented the PMM on 134 axial T1-weighted PM MRIs. The segmentation model was trained from scratch (MONAI/Pytorch SegResNet, 4 mini-batch, 1000 epochs, dropout 0.20, Adam, learning rate 0.0005, cosine annealing, softmax). Mean-dice score determined the segmentation score on 8 internal axial T1-weighted PM MRIs. In step B, we used the OpenCV2 (version 4.5.1, https://opencv.org) framework to calculate the PMM-CSA of the model predictions and ground truth. Then, we selected the top-3 slices with the largest cross-sectional area and compared them with the ground truth. If one of the selected was in the top-3 from the ground truth, then we considered it to be a success. A top-3 accuracy evaluated this method on 8 axial T1-weighted PM MRIs internal test cases. The segmentation model (Step A) produced an accurate pectoralis muscle segmentation with a Mean Dice score of 0.94 ± 0.01. The results of Step B showed top-3 accuracy > 98% to select an appropriate axial image with the greatest PMM-CSA. Our results show an overall accurate selection of PMM-CSA and automated PM muscle segmentation using a combination of deep CNN algorithms.

Feasibility of Constructing an Automatic Meniscus Injury Detection Model Based on Dual-Mode Magnetic Resonance Imaging (MRI) Radiomics of the Knee Joint

Objective

To explore the feasibility of automatically detecting the degree of meniscus injury by radiomics fusion of dual-mode magnetic resonance imaging (MRI) features of sagittal and coronal planes of the knee joint.

Methods

This retrospective study included 164 arthroscopically confirmed meniscus injuries in 152 patients admitted to the Department of Orthopaedics of our hospital from July 2018 to March 2021. A total of 1316-dimensional radiomics signatures were extracted from single-mode sagittal and coronal plane images of menisci, respectively. Then, the sagittal and coronal plane features were fused to form a dual-mode joint feature group with a total of 2632-dimensional radiomics signatures. The minimum redundancy maximum relevance (mRMR) algorithm and the least absolute shrinkage and selection operator (LASSO) regression were used to select features and generate optimal radiomics signatures. The single-mode sagittal plane feature model (Model 1), single-mode coronal plane feature model (Model 2), and the combined sagittal and coronal plane feature model (Model 3) performance were tested by receiver operating characteristic (ROC) curves and Delong test. The calibration curve test was used to verify the reliability of radiomics signatures of the three models.

Results

The average intra- and interobserver intraclass correlation coefficients (ICCs) of the most significant 8-dimensional radiomics signatures of Model 1 and Model 2 were 0.935 (range 0.832-0.998) and 0.928 (range 0.845-0.998), respectively. All the three models had good detection performance; Model 3 had the most significant performance (the areas under the curve (AUCs) of training, and validation sets were 0.947 and 0.923, respectively), which was superior to Model 1 (AUCs of training set and validation set were 0.889 and 0.876, respectively) and Model 2 (AUCs of training set and validation set were 0.831 and 0.851, respectively). The detection probability of training and validation sets in the three models was highly consistent with the actual clinical probability.

Conclusions

It is feasible to establish a model for automatic detection of meniscus damage by means of radiomics. The detection performance of the dual-mode knee MRI model is better than that of any single-mode model, showing potent feature analysis ability and outstanding detection performance.

Knee Injury Detection Using Deep Learning on MRI Studies: A Systematic Review

The improved treatment of knee injuries critically relies on having an accurate and cost-effective detection. In recent years, deep-learning-based approaches have monopolized knee injury detection in MRI studies. The aim of this paper is to present the findings of a systematic literature review of knee (anterior cruciate ligament, meniscus, and cartilage) injury detection papers using deep learning. The systematic review was carried out following the PRISMA guidelines on several databases, including PubMed, Cochrane Library, EMBASE, and Google Scholar. Appropriate metrics were chosen to interpret the results. The prediction accuracy of the deep-learning models for the identification of knee injuries ranged from 72.5-100%. Deep learning has the potential to act at par with human-level performance in decision-making tasks related to the MRI-based diagnosis of knee injuries. The limitations of the present deep-learning approaches include data imbalance, model generalizability across different centers, verification bias, lack of related classification studies with more than two classes, and ground-truth subjectivity. There are several possible avenues of further exploration of deep learning for improving MRI-based knee injury diagnosis. Explainability and lightweightness of the deployed deep-learning systems are expected to become crucial enablers for their widespread use in clinical practice.

Artificial intelligence in musculoskeletal imaging: a perspective on value propositions, clinical use, and obstacles

Artificial intelligence and deep learning (DL) offer musculoskeletal radiology exciting possibilities in multiple areas, including image reconstruction and transformation, tissue segmentation, workflow support, and disease detection. Novel DL-based image reconstruction algorithms correcting aliasing artifacts, signal loss, and noise amplification with previously unobtainable effectiveness are prime examples of how DL algorithms deliver promised value propositions in musculoskeletal radiology. The speed of DL-based tissue segmentation promises great efficiency gains that may permit the inclusion of tissue compositional-based information routinely into radiology reports. Similarly, DL algorithms give rise to a myriad of opportunities for workflow improvements, including intelligent and adaptive hanging protocols, speech recognition, report generation, scheduling, precertification, and billing. The value propositions of disease-detecting DL algorithms include reduced error rates and increased productivity. However, more studies using authentic clinical workflow settings are necessary to fully understand the value of DL algorithms for disease detection in clinical practice. Successful workflow integration and management of multiple algorithms are critical for translating the value propositions of DL algorithms into clinical practice but represent a major roadblock for which solutions are critically needed. While there is no consensus about the most sustainable business model, radiology departments will need to carefully weigh the benefits and disadvantages of each commercially available DL algorithm. Although more studies are needed to understand the value and impact of DL algorithms on clinical practice, DL technology will likely play an important role in the future of musculoskeletal imaging.

Studying osteoarthritis with artificial intelligence applied to magnetic resonance imaging

The 3D nature and soft-tissue contrast of MRI makes it an invaluable tool for osteoarthritis research, by facilitating the elucidation of disease pathogenesis and progression. The recent increasing employment of MRI has certainly been stimulated by major advances that are due to considerable investment in research, particularly related to artificial intelligence (AI). These AI-related advances are revolutionizing the use of MRI in clinical research by augmenting activities ranging from image acquisition to post-processing. Automation is key to reducing the long acquisition times of MRI, conducting large-scale longitudinal studies and quantitatively defining morphometric and other important clinical features of both soft and hard tissues in various anatomical joints. Deep learning methods have been used recently for multiple applications in the musculoskeletal field to improve understanding of osteoarthritis. Compared with labour-intensive human efforts, AI-based methods have advantages and potential in all stages of imaging, as well as post-processing steps, including aiding diagnosis and prognosis. However, AI-based methods also have limitations, including the arguably limited interpretability of AI models. Given that the AI community is highly invested in uncovering uncertainties associated with model predictions and improving their interpretability, we envision future clinical translation and progressive increase in the use of AI algorithms to support clinicians in optimizing patient care.

Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches

Deep learning-based MRI diagnosis of internal joint derangement is an emerging field of artificial intelligence, which offers many exciting possibilities for musculoskeletal radiology. A variety of investigational deep learning algorithms have been developed to detect anterior cruciate ligament tears, meniscus tears, and rotator cuff disorders. Additional deep learning-based MRI algorithms have been investigated to detect Achilles tendon tears, recurrence prediction of musculoskeletal neoplasms, and complex segmentation of nerves, bones, and muscles. Proof-of-concept studies suggest that deep learning algorithms may achieve similar diagnostic performances when compared to human readers in meta-analyses; however, musculoskeletal radiologists outperformed most deep learning algorithms in studies including a direct comparison. Earlier investigations and developments of deep learning algorithms focused on the binary classification of the presence or absence of an abnormality, whereas more advanced deep learning algorithms start to include features for characterization and severity grading. While many studies have focused on comparing deep learning algorithms against human readers, there is a paucity of data on the performance differences of radiologists interpreting musculoskeletal MRI studies without and with artificial intelligence support. Similarly, studies demonstrating the generalizability and clinical applicability of deep learning algorithms using realistic clinical settings with workflow-integrated deep learning algorithms are sparse. Contingent upon future studies showing the clinical utility of deep learning algorithms, artificial intelligence may eventually translate into clinical practice to assist detection and characterization of various conditions on musculoskeletal MRI exams.

A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database

We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data and how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.

Towards novel osteoarthritis biomarkers: Multi-criteria evaluation of 46,996 segmented knee MRI data from the Osteoarthritis Initiative

Convolutional neural networks (CNNs) are the state-of-the-art for automated assessment of knee osteoarthritis (KOA) from medical image data. However, these methods lack interpretability, mainly focus on image texture, and cannot completely grasp the analyzed anatomies' shapes. In this study we assess the informative value of quantitative features derived from segmentations in order to assess their potential as an alternative or extension to CNN-based approaches regarding multiple aspects of KOA. Six anatomical structures around the knee (femoral and tibial bones, femoral and tibial cartilages, and both menisci) are segmented in 46,996 MRI scans. Based on these segmentations, quantitative features are computed, i.e., measurements such as cartilage volume, meniscal extrusion and tibial coverage, as well as geometric features based on a statistical shape encoding of the anatomies. The feature quality is assessed by investigating their association to the Kellgren-Lawrence grade (KLG), joint space narrowing (JSN), incident KOA, and total knee replacement (TKR). Using gold standard labels from the Osteoarthritis Initiative database the balanced accuracy (BA), the area under the Receiver Operating Characteristic curve (AUC), and weighted kappa statistics are evaluated. Features based on shape encodings of femur, tibia, and menisci plus the performed measurements showed most potential as KOA biomarkers. Differentiation between non-arthritic and severely arthritic knees yielded BAs of up to 99%, 84% were achieved for diagnosis of early KOA. Weighted kappa values of 0.73, 0.72, and 0.78 were achieved for classification of the grade of medial JSN, lateral JSN, and KLG, respectively. The AUC was 0.61 and 0.76 for prediction of incident KOA and TKR within one year, respectively. Quantitative features from automated segmentations provide novel biomarkers for KLG and JSN classification and show potential for incident KOA and TKR prediction. The validity of these features should be further evaluated, especially as extensions of CNN-based approaches. To foster such developments we make all segmentations publicly available together with this publication.

Research on sports aided teaching and training decision system oriented to deep convolutional neural network

Aiming at the construction of the decision-making system for sports-assisted teaching and training, this article first gives a deep convolutional neural network model for sports-assisted teaching and training decision-making. Subsequently, In order to meet the needs of athletes to assist in physical exercise, a squat training robot is built using a self-developed modular flexible cable drive unit, and its control system is designed to assist athletes in squatting training in sports. First, the human squat training mechanism is analyzed, and the overall structure of the robot is determined; second, the robot force servo control strategy is designed, including the flexible cable traction force planning link, the lateral force compensation link and the establishment of a single flexible cable passive force controller; In order to verify the effect of robot training, a single flexible cable force control experiment and a man-machine squat training experiment were carried out. In the single flexible cable force control experiment, the suppression effect of excess force reached more than 50%. In the squat experiment under 200 N, the standard deviation of the system loading force is 7.52 N, and the dynamic accuracy is above 90.2%. Experimental results show that the robot has a reasonable configuration, small footprint, stable control system, high loading accuracy, and can assist in squat training in physical education.

A Deep Learning System for Synthetic Knee Magnetic Resonance Imaging: Is Artificial Intelligence-Based Fat-Suppressed Imaging Feasible?

MATERIALS AND METHODS

This single-center study was approved by the institutional review board. Artificial intelligence-based FS MRI scans were created from non-FS images using a deep learning system with a modified convolutional neural network-based U-Net that used a training set of 25,920 images and validation set of 16,416 images. Three musculoskeletal radiologists reviewed 88 knee MR studies in 2 sessions, the original (proton density [PD] + FSPD) and the synthetic (PD + AFSMRI). Readers recorded AFSMRI quality (diagnostic/nondiagnostic) and the presence or absence of meniscal, ligament, and tendon tears; cartilage defects; and bone marrow abnormalities. Contrast-to-noise rate measurements were made among subcutaneous fat, fluid, bone marrow, cartilage, and muscle. The original MRI sequences were used as the reference standard to determine the diagnostic performance of AFSMRI (combined with the original PD sequence). This is a fully balanced study design, where all readers read all images the same number of times, which allowed the determination of the interchangeability of the original and synthetic protocols. Descriptive statistics, intermethod agreement, interobserver concordance, and interchangeability tests were applied. A P value less than 0.01 was considered statistically significant for the likelihood ratio testing, and P value less than 0.05 for all other statistical analyses.

RESULTS

Artificial intelligence-based FS MRI quality was rated as diagnostic (98.9% [87/88] to 100% [88/88], all readers). Diagnostic performance (sensitivity/specificity) of the synthetic protocol was high, for tears of the menisci (91% [71/78], 86% [84/98]), cruciate ligaments (92% [12/13], 98% [160/163]), collateral ligaments (80% [16/20], 100% [156/156]), and tendons (90% [9/10], 100% [166/166]). For cartilage defects and bone marrow abnormalities, the synthetic protocol offered an overall sensitivity/specificity of 77% (170/221)/93% (287/307) and 76% (95/125)/90% (443/491), respectively. Intermethod agreement ranged from moderate to substantial for almost all evaluated structures (menisci, cruciate ligaments, collateral ligaments, and bone marrow abnormalities). No significant difference was observed between methods for all structural abnormalities by all readers (P > 0.05), except for cartilage assessment. Interobserver agreement ranged from moderate to substantial for almost all evaluated structures. Original and synthetic protocols were interchangeable for the diagnosis of all evaluated structures. There was no significant difference for the common exact match proportions for all combinations (P > 0.01). The conspicuity of all tissues assessed through contrast-to-noise rate was higher on AFSMRI than on original FSPD images (P < 0.05).

CONCLUSIONS

Artificial intelligence-based FS MRI (3D AFSMRI) is feasible and offers a method for fast imaging, with similar detection rates for structural abnormalities of the knee, compared with original 3D MR sequences.

Clinical and Research Medical Applications of Artificial Intelligence

Artificial intelligence (AI), including machine learning (ML), has transformed numerous industries through newfound efficiencies and supportive decision-making. With the exponential growth of computing power and large datasets, AI has transitioned from theory to reality in teaching machines to automate tasks without human supervision. AI-based computational algorithms analyze "training sets" using pattern recognition and learning from inputted data to classify and predict outputs that otherwise could not be effectively analyzed with human processing or standard statistical methods. Though widespread understanding of the fundamental principles and adoption of applications have yet to be achieved, recent applications and research efforts implementing AI have demonstrated great promise in predicting future injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting telehealth. With appreciation, caution, and experience applying AI, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. The purpose of this review is to discuss the pearls, pitfalls, and applications associated with AI.

Musculoskeletal trauma imaging in the era of novel molecular methods and artificial intelligence

Over the past decade rapid advancements in molecular imaging (MI) and artificial intelligence (AI) have revolutionized traditional musculoskeletal radiology. Molecular imaging refers to the ability of various methods to in vivo characterize and quantify biological processes, at a molecular level. The extracted information provides the tools to understand the pathophysiology of diseases and thus to early detect, to accurately evaluate the extend and to apply and evaluate targeted treatments. At present, molecular imaging mainly involves CT, MRI, radionuclide, US, and optical imaging and has been reported in many clinical and preclinical studies. Although originally MI techniques targeted at central nervous system disorders, later on their value on musculoskeletal disorders was also studied in depth. Meaningful exploitation of the large volume of imaging data generated by molecular and conventional imaging techniques, requires state-of-the-art computational methods that enable rapid handling of large volumes of information. AI allows end-to-end training of computer algorithms to perform tasks encountered in everyday clinical practice including diagnosis, disease severity classification and image optimization. Notably, the development of deep learning algorithms has offered novel methods that enable intelligent processing of large imaging datasets in an attempt to automate decision-making in a wide variety of settings related to musculoskeletal trauma. Current applications of AI include the diagnosis of bone and soft tissue injuries, monitoring of the healing process and prediction of injuries in the professional sports setting. This review presents the current applications of novel MI techniques and methods and the emerging role of AI regarding the diagnosis and evaluation of musculoskeletal trauma.

Applications of Artificial Intelligence in Musculoskeletal Imaging: From the Request to the Report

Artificial intelligence (AI) will transform every step in the imaging value chain, including interpretive and noninterpretive components. Radiologists should familiarize themselves with AI developments to become leaders in their clinical implementation. This article explores the impact of AI through the entire imaging cycle of musculoskeletal radiology, from the placement of the requisition to the generation of the report, with an added Canadian perspective. Noninterpretive tasks which may be assisted by AI include the ordering of appropriate imaging tests, automatic exam protocoling, optimized scheduling, shorter magnetic resonance imaging acquisition time, computed tomography imaging with reduced artifact and radiation dose, and new methods of generation and utilization of radiology reports. Applications of AI for image interpretation consist of the determination of bone age, body composition measurements, screening for osteoporosis, identification of fractures, evaluation of segmental spine pathology, detection and temporal monitoring of osseous metastases, diagnosis of primary bone and soft tissue tumors, and grading of osteoarthritis.