Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet

Machine learning-based automated scan prescription of lumbar spine MRI acquisitions

PURPOSE

High quality scan prescription that optimally covers the area of interest with scan planes aligned to relevant anatomical structures is crucial for error-free radiologic interpretation. The goal of this project was to develop a machine learning pipeline for oblique scan prescription that could be trained on localizer images and metadata from previously acquired MR exams.

METHODS

A novel Multislice Rotational Region-based Convolutional Neural Network (MS-R2CNN) architecture was developed. Based on this architecture, models for automated prescription sagittal lumbar spine acquisitions from axial, sagittal, and coronal localizer slices were trained. The automated prescription pipeline was integrated with the scanner console software and evaluated in experiments with healthy volunteers (N = 3) and patients with lower-back pain (N = 20).

RESULTS

Experiments in healthy volunteers demonstrated high accuracy of automated prescription in all subjects. There was good agreement between alignment and coverage of manual and automated prescriptions, as well as consistent views of the lumbar spine at different positions of the subjects within the scanner bore. In patients with lower-back pain, the generated prescription was applied in 18 cases (90% of the total number). None of the cases required major adjustment, while in 11 cases (55%) there were minor manual adjustments to the generated prescription.

CONCLUSIONS

This study demonstrates the ability of oriented object detection-based models to be trained to prescribe oblique lumbar spine MRI acquisitions without the need of manual annotation or feature engineering and the feasibility of using machine learning-based pipelines on the scanner for automated prescription of MRI acquisitions.

DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction

Magnetic resonance imaging (MRI) is non-invasive and crucial for clinical diagnosis, but it has long acquisition time and aliasing artifacts. Accelerated imaging techniques can effectively reduce the scanning time of MRI, thereby decreasing the anxiety and discomfort of patients. Vision Transformer (ViT) based methods have greatly improved MRI image reconstruction, but their computational complexity and memory requirements for the self-attention mechanism grow quadratically with image resolution, which limits their use for high resolution images. In addition, the current generative adversarial networks in MRI reconstruction are difficult to train stably. To address these problems, we propose a Local Vision Transformer (LVT) based adversarial Diffusion model (Diff-GAN) for accelerating MRI reconstruction. We employ a generative adversarial network (GAN) as the reverse diffusion model to enable large diffusion steps. In the forward diffusion module, we use a diffusion process to generate Gaussian mixture distribution noise, which mitigates the gradient vanishing issue in GAN training. This network leverages the LVT module with the local self-attention, which can capture high-quality local features and detailed information. We evaluate our method on four datasets: IXI, MICCAI 2013, MRNet and FastMRI, and demonstrate that Diff-GAN can outperform several state-of-the-art GAN-based methods for MRI reconstruction.

Gradient-Based Saliency Maps Are Not Trustworthy Visual Explanations of Automated AI Musculoskeletal Diagnoses

Saliency maps are popularly used to "explain" decisions made by modern machine learning models, including deep convolutional neural networks (DCNNs). While the resulting heatmaps purportedly indicate important image features, their "trustworthiness," i.e., utility and robustness, has not been evaluated for musculoskeletal imaging. The purpose of this study was to systematically evaluate the trustworthiness of saliency maps used in disease diagnosis on upper extremity X-ray images. The underlying DCNNs were trained using the Stanford MURA dataset. We studied four trustworthiness criteria-(1) localization accuracy of abnormalities, (2) repeatability, (3) reproducibility, and (4) sensitivity to underlying DCNN weights-across six different gradient-based saliency methods (Grad-CAM (GCAM), gradient explanation (GRAD), integrated gradients (IG), Smoothgrad (SG), smooth IG (SIG), and XRAI). Ground-truth was defined by the consensus of three fellowship-trained musculoskeletal radiologists who each placed bounding boxes around abnormalities on a holdout saliency test set. Compared to radiologists, all saliency methods showed inferior localization (AUPRCs: 0.438 (SG)-0.590 (XRAI); average radiologist AUPRC: 0.816), repeatability (IoUs: 0.427 (SG)-0.551 (IG); average radiologist IOU: 0.613), and reproducibility (IoUs: 0.250 (SG)-0.502 (XRAI); average radiologist IOU: 0.613) on abnormalities such as fractures, orthopedic hardware insertions, and arthritis. Five methods (GCAM, GRAD, IG, SG, XRAI) passed the sensitivity test. Ultimately, no saliency method met all four trustworthiness criteria; therefore, we recommend caution and rigorous evaluation of saliency maps prior to their clinical use.

One-stop detection of anterior cruciate ligament injuries on magnetic resonance imaging using deep learning with multicenter validation

Background

Anterior cruciate ligament (ACL) injuries are closely associated with knee osteoarthritis (OA). However, diagnosing ACL injuries based on knee magnetic resonance imaging (MRI) has been subjective and time-consuming for clinical doctors. Therefore, we aimed to devise a deep learning (DL) model leveraging MRI to enable a comprehensive and automated approach for the detection of ACL injuries.

Methods

A retrospective study was performed extracting data from the Osteoarthritis Initiative (OAI). A total of 1,589 knees (comprising 1,443 intact, 90 with partial tears, and 56 with full tears) were enrolled to construct the classification model. This one-stop detection pipeline was developed using a tailored YOLOv5m architecture and a ResNet-18 convolutional neural network (CNN) to facilitate tasks based on sagittal 2-dimensional (2D) intermediate-weighted fast spin-echo sequence at 3.0T. To ensure the reliability and robustness of the classification system, it was subjected to external validation across 3 distinct datasets. The accuracy, sensitivity, specificity, and the mean average precision (mAP) were utilized as the evaluation metric for the model performance by employing a 5-fold cross-validation approach. The radiologist's interpretations were employed as the reference for conducting the evaluation.

Results

The localization model demonstrated an accuracy of 0.89 and a sensitivity of 0.93, achieving a mAP score of 0.96. The classification model demonstrated strong performance in detecting intact, partial tears, and full tears at the optimal threshold on the internal dataset, with sensitivities of 0.941, 0.833, and 0.929, specificities of 0.925, 0.947, and 0.991, and accuracies of 0.940, 0.941, and 0.989, respectively. In comparison, on a subset consisting of 171 randomly selected knees from the OAI, the radiologists demonstrated a sensitivity ranging between 0.660 and 1.000, specificity ranging between 0.691 and 1.000, and accuracy ranging between 0.689 and 1.000. On a subset consisting of 170 randomly selected knees from the Chinese dataset, the radiologists exhibited a sensitivity ranging between 0.711 and 0.948, specificity ranging between 0.768 and 0.977, and accuracy ranging between 0.683 and 0.917. After retraining, the model achieved sensitivities ranging between 0.630 and 0.961, specificities ranging between 0.860 and 0.961, and accuracies ranging between 0.832 and 0.951, respectively, on the external validation dataset.

Conclusions

The proposed model utilizing knee MRI showcases robust performance in the domains of ACL localization and classification.

Self-supervised learning for medical image data with anatomy-oriented imaging planes

Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is crucial to the success of transfer learning. Various pretext tasks have been proposed to utilize properties of medical image data (e.g., three dimensionality), which are more relevant to medical image analysis than generic ones for natural images. However, previous work rarely paid attention to data with anatomy-oriented imaging planes, e.g., standard cardiac magnetic resonance imaging views. As these imaging planes are defined according to the anatomy of the imaged organ, pretext tasks effectively exploiting this information can pretrain the networks to gain knowledge on the organ of interest. In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes. The first is to learn the relative orientation between the imaging planes and implemented as regressing their intersecting lines. The second exploits parallel imaging planes to regress their relative slice locations within a stack. Both pretext tasks are conceptually straightforward and easy to implement, and can be combined in multitask learning for better representation learning. Thorough experiments on two anatomical structures (heart and knee) and representative target tasks (semantic segmentation and classification) demonstrate that the proposed pretext tasks are effective in pretraining deep networks for remarkably boosted performance on the target tasks, and superior to other recent approaches.

Semi-supervised medical image classification via distance correlation minimization and graph attention regularization

We propose a novel semi-supervised learning method to leverage unlabeled data alongside minimal annotated data and improve medical imaging classification performance in realistic scenarios with limited labeling budgets to afford data annotations. Our method introduces distance correlation to minimize correlations between feature representations from different views of the same image encoded with non-coupled deep neural networks architectures. In addition, it incorporates a data-driven graph-attention based regularization strategy to model affinities among images within the unlabeled data by exploiting their inherent relational information in the feature space. We conduct extensive experiments on four medical imaging benchmark data sets involving X-ray, dermoscopic, magnetic resonance, and computer tomography imaging on single and multi-label medical imaging classification scenarios. Our experiments demonstrate the effectiveness of our method in achieving very competitive performance and outperforming several state-of-the-art semi-supervised learning methods. Furthermore, they confirm the suitability of distance correlation as a versatile dependence measure and the benefits of the proposed graph-attention based regularization for semi-supervised learning in medical imaging analysis.

Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics

Bone age assessment (BAA) is a crucial task in clinical, forensic, and athletic fields. Since traditional age estimation methods are suffered from potential radiation damage, this study aimed to develop and evaluate a deep learning radiomics method based on multiparametric knee MRI for noninvasive and automatic BAA. This retrospective study enrolled 598 patients (age range,10.00-29.99 years) who underwent MR examinations of the knee joint (T1/T2*/PD-weighted imaging). Three-dimensional convolutional neural networks (3D CNNs) were trained to extract and fuse multimodal and multiscale MRI radiomic features for age estimation and compared to traditional machine learning models based on hand-crafted features. The age estimation error was greater in individuals aged 25-30 years; thus, this method may not be suitable for individuals over 25 years old. In the test set aged 10-25 years (n = 95), the 3D CNN (a fusion of T1WI, T2*WI, and PDWI) demonstrated the lowest mean absolute error of 1.32 ± 1.01 years, which is higher than that of other MRI modalities and the hand-crafted models. In the classification for 12-, 14-, 16-, and 18- year thresholds, accuracies and the areas under the ROC curves were all over 0.91 and 0.96, which is similar to the manual methods. Visualization of important features showed that 3D CNN estimated age by focusing on the epiphyseal plates. The deep learning radiomics method enables non-invasive and automated BAA from multimodal knee MR images. The use of 3D CNN and MRI-based radiomics has the potential to assist radiologists or medicolegists in age estimation.

Improving inceptionV4 model based on fractional-order snow leopard optimization algorithm for diagnosing of ACL tears

In the current research study, a new method is presented to diagnose Anterior Cruciate Ligament (ACL) tears by introducing an optimized version of the InceptionV4 model. Our proposed methodology utilizes a custom-made variant of the Snow Leopard Optimization Algorithm, known as the Fractional-order Snow Leopard Optimization Algorithm (FO-LOA), to extract essential features from knee magnetic resonance imaging (MRI) images. This results in a substantial improvement in the accuracy of ACL tear detection. By effectively extracting critical features from knee MRI images, our proposed methodology significantly enhances diagnostic accuracy, potentially reducing false negatives and false positives. The enhanced model based on FO-LOA underwent thorough testing using the MRNet dataset, demonstrating exceptional performance metrics including an accuracy rate of 98.00%, sensitivity of 98.00%, precision of 97.00%, specificity of 98.00%, F1-score of 98.00%, and Matthews Correlation Coefficient (MCC) of 88.00%. These findings surpass current methodologies like Convolutional Neural Network (CNN), Inception-v3, Deep Belief Networks and Improved Honey Badger Algorithm (DBN/IHBA), integration of the CNN with an Amended Cooking Training-based Optimizer version (CNN/ACTO), Self-Supervised Representation Learning (SSRL), signifying a significant breakthrough in ACL injury diagnosis. Using FO-SLO to optimize the InceptionV4 framework shows promise in improving the accuracy of ACL tear identification, enabling prompt and efficient treatment interventions.

The 100 most cited articles in artificial intelligence related to orthopedics

Background

This bibliometric study aimed to identify and analyze the top 100 articles related to artificial intelligence in the field of orthopedics.

Methods

The articles were assessed based on their number of citations, publication years, countries, journals, authors, affiliations, and funding agencies. Additionally, they were analyzed in terms of their themes and objectives. Keyword co-occurrence, co-citation of authors, and co-citation of references analyses were conducted using VOSviewer (version 1.6.19).

Results

The number of citations of these articles ranged from 32 to 272, with six papers having more than 200 citations The years of 2019 (n: 37) and 2020 (n: 19) together constituted 56% of the list. The USA was the leading contributor country to this field (n: 61). The most frequently used keywords were "machine learning" (n: 26), "classification" (n: 18), "deep learning" (n: 16), "artificial intelligence" (n: 14), respectively. The most common themes were decision support (n: 25), fracture detection (n: 24), and osteoarthrtitis staging (n: 21). The majority of the studies were diagnostic in nature (n: 85), with only two articles focused on treatment.

Conclusions

This study provides valuable insights and presents the historical perspective of scientific development on artificial intelligence in the field of orthopedics. The literature in this field is expanding rapidly. Currently, research is generally done for diagnostic purposes and predominantly focused on decision support systems, fracture detection, and osteoarthritis classification.

Visual interpretable MRI fine grading of meniscus injury for intelligent assisted diagnosis and treatment

Meniscal injury represents a common type of knee injury, accounting for over 50% of all knee injuries. The clinical diagnosis and treatment of meniscal injury heavily rely on magnetic resonance imaging (MRI). However, accurately diagnosing the meniscus from a comprehensive knee MRI is challenging due to its limited and weak signal, significantly impeding the precise grading of meniscal injuries. In this study, a visual interpretable fine grading (VIFG) diagnosis model has been developed to facilitate intelligent and quantified grading of meniscal injuries. Leveraging a multilevel transfer learning framework, it extracts comprehensive features and incorporates an attributional attention module to precisely locate the injured positions. Moreover, the attention-enhancing feedback module effectively concentrates on and distinguishes regions with similar grades of injury. The proposed method underwent validation on FastMRI_Knee and Xijing_Knee dataset, achieving mean grading accuracies of 0.8631 and 0.8502, surpassing the state-of-the-art grading methods notably in error-prone Grade 1 and Grade 2 cases. Additionally, the visually interpretable heatmaps generated by VIFG provide accurate depictions of actual or potential meniscus injury areas beyond human visual capability. Building upon this, a novel fine grading criterion was introduced for subtypes of meniscal injury, further classifying Grade 2 into 2a, 2b, and 2c, aligning with the anatomical knowledge of meniscal blood supply. It can provide enhanced injury-specific details, facilitating the development of more precise surgical strategies. The efficacy of this subtype classification was evidenced in 20 arthroscopic cases, underscoring the potential enhancement brought by intelligent-assisted diagnosis and treatment for meniscal injuries.

Establishment of a prognostic model for gastric cancer patients who underwent radical gastrectomy using machine learning: a two-center study

Objective

Gastric cancer is a prevalent gastrointestinal malignancy worldwide. In this study, a prognostic model was developed for gastric cancer patients who underwent radical gastrectomy using machine learning, employing advanced computational techniques to investigate postoperative mortality risk factors in such patients.

Methods

Data of 295 patients with gastric cancer who underwent radical gastrectomy at the Department of General Surgery of Affiliated Hospital of Xuzhou Medical University (Xuzhou, China) between March 2016 and November 2019 were retrospectively analyzed as the training group. Additionally, 109 patients who underwent radical gastrectomy at the Department of General Surgery Affiliated to Jining First People's Hospital (Jining, China) were included for external validation. Four machine learning models, including logistic regression (LR), decision tree (DT), random forest (RF), and gradient boosting machine (GBM), were utilized. Model performance was assessed by comparing the area under the curve (AUC) for each model. An LR-based nomogram model was constructed to assess patients' clinical prognosis.

Results

Lasso regression identified eight associated factors: age, sex, maximum tumor diameter, nerve or vascular invasion, TNM stage, gastrectomy type, lymphocyte count, and carcinoembryonic antigen (CEA) level. The performance of these models was evaluated using the AUC. In the training group, the AUC values were 0.795, 0.759, 0.873, and 0.853 for LR, DT, RF, and GBM, respectively. In the validation group, the AUC values were 0.734, 0.708, 0.746, and 0.707 for LR, DT, RF, and GBM, respectively. The nomogram model, constructed based on LR, demonstrated excellent clinical prognostic evaluation capabilities.

Conclusion

Machine learning algorithms are robust performance assessment tools for evaluating the prognosis of gastric cancer patients who have undergone radical gastrectomy. The LR-based nomogram model can aid clinicians in making more reliable clinical decisions.

Artificial intelligence for detection of effusion and lipo-hemarthrosis in X-rays and CT of the knee

BACKGROUND

Traumatic knee injuries are challenging to diagnose accurately through radiography and to a lesser extent, through CT, with fractures sometimes overlooked. Ancillary signs like joint effusion or lipo-hemarthrosis are indicative of fractures, suggesting the need for further imaging. Artificial Intelligence (AI) can automate image analysis, improving diagnostic accuracy and help prioritizing clinically important X-ray or CT studies.

OBJECTIVE

To develop and evaluate an AI algorithm for detecting effusion of any kind in knee X-rays and selected CT images and distinguishing between simple effusion and lipo-hemarthrosis indicative of intra-articular fractures.

METHODS

This retrospective study analyzed post traumatic knee imaging from January 2016 to February 2023, categorizing images into lipo-hemarthrosis, simple effusion, or normal. It utilized the FishNet-150 algorithm for image classification, with class activation maps highlighting decision-influential regions. The AI's diagnostic accuracy was validated against a gold standard, based on the evaluations made by a radiologist with at least four years of experience.

RESULTS

Analysis included CT images from 515 patients and X-rays from 637 post traumatic patients, identifying lipo-hemarthrosis, simple effusion, and normal findings. The AI showed an AUC of 0.81 for detecting any effusion, 0.78 for simple effusion, and 0.83 for lipo-hemarthrosis in X-rays; and 0.89, 0.89, and 0.91, respectively, in CTs.

CONCLUSION

The AI algorithm effectively detects knee effusion and differentiates between simple effusion and lipo-hemarthrosis in post-traumatic patients for both X-rays and selected CT images further studies are needed to validate these results.

Refined Detection and Classification of Knee Ligament Injury Based on ResNet Convolutional Neural Networks

Currently, medical imaging has largely supplanted traditional methods in the realm of diagnosis and treatment planning. This shift is primarily attributable to the non-invasive nature, rapidity, and user-friendliness of medical-imaging techniques. The widespread adoption of medical imaging, however, has shifted the bottleneck to healthcare professionals who must analyze each case post-image acquisition. This process is characterized by its sluggishness and subjectivity, making it susceptible to errors. The anterior cruciate ligament (ACL), a frequently injured knee ligament, predominantly affects a youthful and sports-active demographic. ACL injuries often leave patients with substantial disabilities and alter knee mechanics. Since some of these cases necessitate surgery, it is crucial to accurately classify and detect ACL injury. This paper investigates the utilization of pre-trained convolutional neural networks featuring residual connections (ResNet) along with image-processing methods to identify ACL injury and differentiate between various tear levels. The ResNet employed in this study is not the standard ResNet but rather an adapted version capable of processing 3D volumes constructed from 2D image slices. Achieving a peak accuracy of 97.15% with a custom split, 96.32% through Monte-Carlo cross-validation, and 93.22% via five-fold cross-validation, our approach enhances the performance of three-class classifiers by over 7% in terms of raw accuracy. Moreover, we achieved an improvement of more than 1% across all types of evaluation. It is quite clear that the model's output can effectively serve as an initial diagnostic baseline for radiologists with minimal effort and nearly instantaneous results. This advancement underscores the paper's focus on harnessing deep learning for the nuanced detection and classification of ACL tears, demonstrating a significant leap toward automating and refining diagnostic accuracy in sports medicine and orthopedics.

A Deep Learning Model Enhances Clinicians' Diagnostic Accuracy to More Than 96% for Anterior Cruciate Ligament Ruptures on Magnetic Resonance Imaging

PURPOSE

To develop a deep learning model to accurately detect anterior cruciate ligament (ACL) ruptures on magnetic resonance imaging (MRI) and to evaluate its effect on the diagnostic accuracy and efficiency of clinicians.

METHODS

A training dataset was built from MRIs acquired from January 2017 to June 2021, including patients with knee symptoms, irrespective of ACL ruptures. An external validation dataset was built from MRIs acquired from January 2021 to June 2022, including patients who underwent knee arthroscopy or arthroplasty. Patients with fractures or prior knee surgeries were excluded in both datasets. Subsequently, a deep learning model was developed and validated using these datasets. Clinicians of varying expertise levels in sports medicine and radiology were recruited, and their capacities in diagnosing ACL injuries in terms of accuracy and diagnosing time were evaluated both with and without artificial intelligence (AI) assistance.

RESULTS

A deep learning model was developed based on the training dataset of 22,767 MRIs from 5 centers and verified with external validation dataset of 4,086 MRIs from 6 centers. The model achieved an area under the receiver operating characteristic curve of 0.987 and a sensitivity and specificity of 95.1%. Thirty-eight clinicians from 25 centers were recruited to diagnose 3,800 MRIs. The AI assistance significantly improved the accuracy of all clinicians, exceeding 96%. Additionally, a notable reduction in diagnostic time was observed. The most significant improvements in accuracy and time efficiency were observed in the trainee groups, suggesting that AI support is particularly beneficial for clinicians with moderately limited diagnostic expertise.

CONCLUSIONS

This deep learning model demonstrated expert-level diagnostic performance for ACL ruptures, serving as a valuable tool to assist clinicians of various specialties and experience levels in making accurate and efficient diagnoses.

LEVEL OF EVIDENCE

Level III, retrospective comparative case series.

The Role of Artificial Intelligence in the Identification and Evaluation of Bone Fractures

Artificial intelligence (AI), particularly deep learning, has made enormous strides in medical imaging analysis. In the field of musculoskeletal radiology, deep-learning models are actively being developed for the identification and evaluation of bone fractures. These methods provide numerous benefits to radiologists such as increased diagnostic accuracy and efficiency while also achieving standalone performances comparable or superior to clinician readers. Various algorithms are already commercially available for integration into clinical workflows, with the potential to improve healthcare delivery and shape the future practice of radiology. In this systematic review, we explore the performance of current AI methods in the identification and evaluation of fractures, particularly those in the ankle, wrist, hip, and ribs. We also discuss current commercially available products for fracture detection and provide an overview of the current limitations of this technology and future directions of the field.

Enabling Personalized Medicine in Orthopaedic Surgery Through Artificial Intelligence: A Critical Analysis Review

» The application of artificial intelligence (AI) in the field of orthopaedic surgery holds potential for revolutionizing health care delivery across 3 crucial domains: (I) personalized prediction of clinical outcomes and adverse events, which may optimize patient selection, surgical planning, and enhance patient safety and outcomes; (II) diagnostic automated and semiautomated imaging analyses, which may reduce time burden and facilitate precise and timely diagnoses; and (III) forecasting of resource utilization, which may reduce health care costs and increase value for patients and institutions.» Computer vision is one of the most highly studied areas of AI within orthopaedics, with applications pertaining to fracture classification, identification of the manufacturer and model of prosthetic implants, and surveillance of prosthesis loosening and failure.» Prognostic applications of AI within orthopaedics include identifying patients who will likely benefit from a specified treatment, predicting prosthetic implant size, postoperative length of stay, discharge disposition, and surgical complications. Not only may these applications be beneficial to patients but also to institutions and payors because they may inform potential cost expenditure, improve overall hospital efficiency, and help anticipate resource utilization.» AI infrastructure development requires institutional financial commitment and a team of clinicians and data scientists with expertise in AI that can complement skill sets and knowledge. Once a team is established and a goal is determined, teams (1) obtain, curate, and label data; (2) establish a reference standard; (3) develop an AI model; (4) evaluate the performance of the AI model; (5) externally validate the model, and (6) reinforce, improve, and evaluate the model's performance until clinical implementation is possible.» Understanding the implications of AI in orthopaedics may eventually lead to wide-ranging improvements in patient care. However, AI, while holding tremendous promise, is not without methodological and ethical limitations that are essential to address. First, it is important to ensure external validity of programs before their use in a clinical setting. Investigators should maintain high quality data records and registry surveillance, exercise caution when evaluating others' reported AI applications, and increase transparency of the methodological conduct of current models to improve external validity and avoid propagating bias. By addressing these challenges and responsibly embracing the potential of AI, the medical field may eventually be able to harness its power to improve patient care and outcomes.

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.

Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: AJR Expert Panel Narrative Review

Artificial intelligence (AI) is increasingly used in clinical practice for musculoskeletal imaging tasks, such as disease diagnosis and image reconstruction. AI applications in musculoskeletal imaging have focused primarily on radiography, CT, and MRI. Although musculoskeletal ultrasound stands to benefit from AI in similar ways, such applications have been relatively underdeveloped. In comparison with other modalities, ultrasound has unique advantages and disadvantages that must be considered in AI algorithm development and clinical translation. Challenges in developing AI for musculoskeletal ultrasound involve both clinical aspects of image acquisition and practical limitations in image processing and annotation. Solutions from other radiology subspecialties (e.g., crowdsourced annotations coordinated by professional societies), along with use cases (most commonly rotator cuff tendon tears and palpable soft-tissue masses), can be applied to musculoskeletal ultrasound to help develop AI. To facilitate creation of high-quality imaging datasets for AI model development, technologists and radiologists should focus on increasing uniformity in musculoskeletal ultrasound performance and increasing annotations of images for specific anatomic regions. This Expert Panel Narrative Review summarizes available evidence regarding AI's potential utility in musculoskeletal ultrasound and challenges facing its development. Recommendations for future AI advancement and clinical translation in musculoskeletal ultrasound are discussed.

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 applications in musculoskeletal imaging: a narrative review

This narrative review focuses on clinical applications of artificial intelligence (AI) in musculoskeletal imaging. A range of musculoskeletal disorders are discussed using a clinical-based approach, including trauma, bone age estimation, osteoarthritis, bone and soft-tissue tumors, and orthopedic implant-related pathology. Several AI algorithms have been applied to fracture detection and classification, which are potentially helpful tools for radiologists and clinicians. In bone age assessment, AI methods have been applied to assist radiologists by automatizing workflow, thus reducing workload and inter-observer variability. AI may potentially aid radiologists in identifying and grading abnormal findings of osteoarthritis as well as predicting the onset or progression of this disease. Either alone or combined with radiomics, AI algorithms may potentially improve diagnosis and outcome prediction of bone and soft-tissue tumors. Finally, information regarding appropriate positioning of orthopedic implants and related complications may be obtained using AI algorithms. In conclusion, rather than replacing radiologists, the use of AI should instead help them to optimize workflow, augment diagnostic performance, and keep up with ever-increasing workload.Relevance statement This narrative review provides an overview of AI applications in musculoskeletal imaging. As the number of AI technologies continues to increase, it will be crucial for radiologists to play a role in their selection and application as well as to fully understand their potential value in clinical practice. Key points • AI may potentially assist musculoskeletal radiologists in several interpretative tasks.• AI applications to trauma, age estimation, osteoarthritis, tumors, and orthopedic implants are discussed.• AI should help radiologists to optimize workflow and augment diagnostic performance.

Value Creation Through Artificial Intelligence and Cardiovascular Imaging: A Scientific Statement From the American Heart Association

Multiple applications for machine learning and artificial intelligence (AI) in cardiovascular imaging are being proposed and developed. However, the processes involved in implementing AI in cardiovascular imaging are highly diverse, varying by imaging modality, patient subtype, features to be extracted and analyzed, and clinical application. This article establishes a framework that defines value from an organizational perspective, followed by value chain analysis to identify the activities in which AI might produce the greatest incremental value creation. The various perspectives that should be considered are highlighted, including clinicians, imagers, hospitals, patients, and payers. Integrating the perspectives of all health care stakeholders is critical for creating value and ensuring the successful deployment of AI tools in a real-world setting. Different AI tools are summarized, along with the unique aspects of AI applications to various cardiac imaging modalities, including cardiac computed tomography, magnetic resonance imaging, and positron emission tomography. AI is applicable and has the potential to add value to cardiovascular imaging at every step along the patient journey, from selecting the more appropriate test to optimizing image acquisition and analysis, interpreting the results for classification and diagnosis, and predicting the risk for major adverse cardiac events.

Deep Learning-Assisted Identification of Femoroacetabular Impingement (FAI) on Routine Pelvic Radiographs

To use a novel deep learning system to localize the hip joints and detect findings of cam-type femoroacetabular impingement (FAI). A retrospective search of hip/pelvis radiographs obtained in patients to evaluate for FAI yielded 3050 total studies. Each hip was classified separately by the original interpreting radiologist in the following manner: 724 hips had severe cam-type FAI morphology, 962 moderate cam-type FAI morphology, 846 mild cam-type FAI morphology, and 518 hips were normal. The anteroposterior (AP) view from each study was anonymized and extracted. After localization of the hip joints by a novel convolutional neural network (CNN) based on the focal loss principle, a second CNN classified the images of the hip as cam positive, or no FAI. Accuracy was 74% for diagnosing normal vs. abnormal cam-type FAI morphology, with aggregate sensitivity and specificity of 0.821 and 0.669, respectively, at the chosen operating point. The aggregate AUC was 0.736. A deep learning system can be applied to detect FAI-related changes on single view pelvic radiographs. Deep learning is useful for quickly identifying and categorizing pathology on imaging, which may aid the interpreting radiologist.

Evaluating the clinical utility of artificial intelligence assistance and its explanation on the glioma grading task

Clinical evaluation evidence and model explainability are key gatekeepers to ensure the safe, accountable, and effective use of artificial intelligence (AI) in clinical settings. We conducted a clinical user-centered evaluation with 35 neurosurgeons to assess the utility of AI assistance and its explanation on the glioma grading task. Each participant read 25 brain MRI scans of patients with gliomas, and gave their judgment on the glioma grading without and with the assistance of AI prediction and explanation. The AI model was trained on the BraTS dataset with 88.0% accuracy. The AI explanation was generated using the explainable AI algorithm of SmoothGrad, which was selected from 16 algorithms based on the criterion of being truthful to the AI decision process. Results showed that compared to the average accuracy of 82.5±8.7% when physicians performed the task alone, physicians' task performance increased to 87.7±7.3% with statistical significance (p-value = 0.002) when assisted by AI prediction, and remained at almost the same level of 88.5±7.0% (p-value = 0.35) with the additional assistance of AI explanation. Based on quantitative and qualitative results, the observed improvement in physicians' task performance assisted by AI prediction was mainly because physicians' decision patterns converged to be similar to AI, as physicians only switched their decisions when disagreeing with AI. The insignificant change in physicians' performance with the additional assistance of AI explanation was because the AI explanations did not provide explicit reasons, contexts, or descriptions of clinical features to help doctors discern potentially incorrect AI predictions. The evaluation showed the clinical utility of AI to assist physicians on the glioma grading task, and identified the limitations and clinical usage gaps of existing explainable AI techniques for future improvement.

New clinical opportunities of low-field MRI: heart, lung, body, and musculoskeletal

Contemporary whole-body low-field MRI scanners (< 1 T) present new and exciting opportunities for improved body imaging. The fundamental reason is that the reduced off-resonance and reduced SAR provide substantially increased flexibility in the design of MRI pulse sequences. Promising body applications include lung parenchyma imaging, imaging adjacent to metallic implants, cardiac imaging, and dynamic imaging in general. The lower cost of such systems may make MRI favorable for screening high-risk populations and population health research, and the more open configurations allowed may prove favorable for obese subjects and for pregnant women. This article summarizes promising body applications for contemporary whole-body low-field MRI systems, with a focus on new platforms developed within the past 5 years. This is an active area of research, and one can expect many improvements as MRI physicists fully explore the landscape of pulse sequences that are feasible, and as clinicians apply these to patient populations.

Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI

BACKGROUND

Differentiation of high-flow from low-flow vascular malformations (VMs) is crucial for therapeutic management of this orphan disease.

OBJECTIVE

A convolutional neural network (CNN) was evaluated for differentiation of peripheral vascular malformations (VMs) on T2-weighted short tau inversion recovery (STIR) MRI.

METHODS

527 MRIs (386 low-flow and 141 high-flow VMs) were randomly divided into training, validation and test set for this single-center study. 1) Results of the CNN's diagnostic performance were compared with that of two expert and four junior radiologists. 2) The influence of CNN's prediction on the radiologists' performance and diagnostic certainty was evaluated. 3) Junior radiologists' performance after self-training was compared with that of the CNN.

RESULTS

Compared with the expert radiologists the CNN achieved similar accuracy (92% vs. 97%, p = 0.11), sensitivity (80% vs. 93%, p = 0.16) and specificity (97% vs. 100%, p = 0.50). In comparison to the junior radiologists, the CNN had a higher specificity and accuracy (97% vs. 80%, p <  0.001; 92% vs. 77%, p <  0.001). CNN assistance had no significant influence on their diagnostic performance and certainty. After self-training, the junior radiologists' specificity and accuracy improved and were comparable to that of the CNN.

CONCLUSIONS

Diagnostic performance of the CNN for differentiating high-flow from low-flow VM was comparable to that of expert radiologists. CNN did not significantly improve the simulated daily practice of junior radiologists, self-training was more effective.

Application of machine learning-based multi-sequence MRI radiomics in diagnosing anterior cruciate ligament tears

OBJECTIVE

To compare the diagnostic power among various machine learning algorithms utilizing multi-sequence magnetic resonance imaging (MRI) radiomics in detecting anterior cruciate ligament (ACL) tears. Additionally, this research aimed to create and validate the optimal diagnostic model.

METHODS

In this retrospective analysis, 526 patients were included, comprising 178 individuals with ACL tears and 348 with a normal ACL. Radiomics features were derived from multi-sequence MRI scans, encompassing T1-weighted imaging and proton density (PD)-weighted imaging. The process of selecting the most reliable radiomics features involved using interclass correlation coefficient (ICC) testing, t tests, and the least absolute shrinkage and selection operator (LASSO) technique. After the feature selection process, five machine learning classifiers were created. These classifiers comprised logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP). A thorough performance evaluation was carried out, utilizing diverse metrics like the area under the receiver operating characteristic curve (ROC), specificity, accuracy, sensitivity positive predictive value, and negative predictive value. The classifier exhibiting the best performance was chosen. Subsequently, three models were developed: the PD model, the T1 model, and the combined model, all based on the optimal classifier. The diagnostic performance of these models was assessed by employing AUC values, calibration curves, and decision curve analysis.

RESULTS

Out of 2032 features, 48 features were selected. The SVM-based multi-sequence radiomics outperformed all others, achieving AUC values of 0.973 and 0.927, sensitivities of 0.933 and 0.857, and specificities of 0.930 and 0.829, in the training and validation cohorts, respectively.

CONCLUSION

The multi-sequence MRI radiomics model, which is based on machine learning, exhibits exceptional performance in diagnosing ACL tears. It provides valuable insights crucial for the diagnosis and treatment of knee joint injuries, serving as an accurate and objective supplementary diagnostic tool for clinical practitioners.

Predictive value of machine learning models for lymph node metastasis in gastric cancer: A two-center study

BACKGROUND

Gastric cancer is one of the most common malignant tumors in the digestive system, ranking sixth in incidence and fourth in mortality worldwide. Since 42.5% of metastatic lymph nodes in gastric cancer belong to nodule type and peripheral type, the application of imaging diagnosis is restricted.

AIM

To establish models for predicting the risk of lymph node metastasis in gastric cancer patients using machine learning (ML) algorithms and to evaluate their predictive performance in clinical practice.

METHODS

Data of a total of 369 patients who underwent radical gastrectomy at the Department of General Surgery of Affiliated Hospital of Xuzhou Medical University (Xuzhou, China) from March 2016 to November 2019 were collected and retrospectively analyzed as the training group. In addition, data of 123 patients who underwent radical gastrectomy at the Department of General Surgery of Jining First People's Hospital (Jining, China) were collected and analyzed as the verification group. Seven ML models, including decision tree, random forest, support vector machine (SVM), gradient boosting machine, naive Bayes, neural network, and logistic regression, were developed to evaluate the occurrence of lymph node metastasis in patients with gastric cancer. The ML models were established following ten cross-validation iterations using the training dataset, and subsequently, each model was assessed using the test dataset. The models' performance was evaluated by comparing the area under the receiver operating characteristic curve of each model.

RESULTS

Among the seven ML models, except for SVM, the other ones exhibited higher accuracy and reliability, and the influences of various risk factors on the models are intuitive.

CONCLUSION

The ML models developed exhibit strong predictive capabilities for lymph node metastasis in gastric cancer, which can aid in personalized clinical diagnosis and treatment.

The Role of Artificial Intelligence in Anterior Cruciate Ligament Injuries: Current Concepts and Future Perspectives

The remarkable progress in data aggregation and deep learning algorithms has positioned artificial intelligence (AI) and machine learning (ML) to revolutionize the field of medicine. AI is becoming more and more prevalent in the healthcare sector, and its impact on orthopedic surgery is already evident in several fields. This review aims to examine the literature that explores the comprehensive clinical relevance of AI-based tools utilized before, during, and after anterior cruciate ligament (ACL) reconstruction. The review focuses on current clinical applications and future prospects in preoperative management, encompassing risk prediction and diagnostics; intraoperative tools, specifically navigation, identifying complex anatomic landmarks during surgery; and postoperative applications in terms of postoperative care and rehabilitation. Additionally, AI tools in educational and training settings are presented. Orthopedic surgeons are showing a growing interest in AI, as evidenced by the applications discussed in this review, particularly those related to ACL injury. The exponential increase in studies on AI tools applicable to the management of ACL tears promises a significant future impact in its clinical application, with growing attention from orthopedic surgeons.

A deep learning knowledge distillation framework using knee MRI and arthroscopy data for meniscus tear detection

Purpose: To construct a deep learning knowledge distillation framework exploring the utilization of MRI alone or combing with distilled Arthroscopy information for meniscus tear detection. Methods: A database of 199 paired knee Arthroscopy-MRI exams was used to develop a multimodal teacher network and an MRI-based student network, which used residual neural networks architectures. A knowledge distillation framework comprising the multimodal teacher network T and the monomodal student network S was proposed. We optimized the loss functions of mean squared error (MSE) and cross-entropy (CE) to enable the student network S to learn arthroscopic information from the teacher network T through our deep learning knowledge distillation framework, ultimately resulting in a distilled student network S T. A coronal proton density (PD)-weighted fat-suppressed MRI sequence was used in this study. Fivefold cross-validation was employed, and the accuracy, sensitivity, specificity, F1-score, receiver operating characteristic (ROC) curves and area under the receiver operating characteristic curve (AUC) were used to evaluate the medial and lateral meniscal tears detection performance of the models, including the undistilled student model S, the distilled student model S T and the teacher model T. Results: The AUCs of the undistilled student model S, the distilled student model S T, the teacher model T for medial meniscus (MM) tear detection and lateral meniscus (LM) tear detection are 0.773/0.672, 0.792/0.751 and 0.834/0.746, respectively. The distilled student model S T had higher AUCs than the undistilled model S. After undergoing knowledge distillation processing, the distilled student model demonstrated promising results, with accuracy (0.764/0.734), sensitivity (0.838/0.661), and F1-score (0.680/0.754) for both medial and lateral tear detection better than the undistilled one with accuracy (0.734/0.648), sensitivity (0.733/0.607), and F1-score (0.620/0.673). Conclusion: Through the knowledge distillation framework, the student model S based on MRI benefited from the multimodal teacher model T and achieved an improved meniscus tear detection performance.

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.

Approaching expert-level accuracy for differentiating ACL tear types on MRI with deep learning

Treatment for anterior cruciate ligament (ACL) tears depends on the condition of the ligament. We aimed to identify different tear statuses from preoperative MRI using deep learning-based radiomics with sex and age. We reviewed 862 patients with preoperative MRI scans reflecting ACL status from Hunan Provincial People's Hospital. Based on sagittal proton density-weighted images, a fully automated approach was developed that consisted of a deep learning model for segmenting ACL tissue (ACL-DNet) and a deep learning-based recognizer for ligament status classification (ACL-SNet). The efficacy of the proposed approach was evaluated by using the sensitivity, specificity and area under the receiver operating characteristic curve (AUC) and compared with that of a group of three orthopedists in the holdout test set. The ACL-DNet model yielded a Dice coefficient of 98% ± 6% on the MRI datasets. Our proposed classification model yielded a sensitivity of 97% and a specificity of 97%. In comparison, the sensitivity of alternative models ranged from 84 to 90%, while the specificity was between 86 and 92%. The AUC of the ACL-SNet model was 99%, demonstrating high overall diagnostic accuracy. The diagnostic performance of the clinical experts as reflected in the AUC was 96%, 92% and 88%, respectively. The fully automated model shows potential as a highly reliable and reproducible tool that allows orthopedists to noninvasively identify the ACL status and may aid in optimizing different techniques, such as ACL remnant preservation, for ACL reconstruction.

Artificial intelligence generated content (AIGC) in medicine: A narrative review

Recently, artificial intelligence generated content (AIGC) has been receiving increased attention and is growing exponentially. AIGC is generated based on the intentional information extracted from human-provided instructions by generative artificial intelligence (AI) models. AIGC quickly and automatically generates large amounts of high-quality content. Currently, there is a shortage of medical resources and complex medical procedures in medicine. Due to its characteristics, AIGC can help alleviate these problems. As a result, the application of AIGC in medicine has gained increased attention in recent years. Therefore, this paper provides a comprehensive review on the recent state of studies involving AIGC in medicine. First, we present an overview of AIGC. Furthermore, based on recent studies, the application of AIGC in medicine is reviewed from two aspects: medical image processing and medical text generation. The basic generative AI models, tasks, target organs, datasets and contribution of studies are considered and summarized. Finally, we also discuss the limitations and challenges faced by AIGC and propose possible solutions with relevant studies. We hope this review can help readers understand the potential of AIGC in medicine and obtain some innovative ideas in this field.

Future of Artificial Intelligence in Surgery: A Narrative Review

Artificial intelligence (AI) is the capability of a machine to execute cognitive processes that are typically considered to be functions of the human brain. It is the study of algorithms that enable machines to reason and perform mental tasks, including problem-solving, object and word recognition, and decision-making. Once considered science fiction, AI today is a fact and an increasingly prevalent subject in both academic and popular literature. It is expected to reshape medicine, benefiting both healthcare professionals and patients. Machine learning (ML) is a subset of AI that allows machines to learn and make predictions by recognizing patterns, thus empowering the medical team to deliver better care to patients through accurate diagnosis and treatment. ML is expanding its footprint in a variety of surgical specialties, including general surgery, ophthalmology, cardiothoracic surgery, and vascular surgery, to name a few. In recent years, we have seen AI make its way into the operating theatres. Though it has not yet been able to replace the surgeon, it has the potential to become a highly valuable surgical tool. Rest assured that the day is not far off when AI shall play a significant intraoperative role, a projection that is currently marred by safety concerns. This review aims to explore the present application of AI in various surgical disciplines and how it benefits both patients and physicians, as well as the current obstacles and limitations facing its seemingly unstoppable rise.

Comparison of Machine Learning and Logic Regression Algorithms for Predicting Lymph Node Metastasis in Patients with Gastric Cancer: A two-Center Study

OBJECTIVES

This two-center study aimed to establish a model for predicting the risk of lymph node metastasis in gastric cancer patients using machine learning (ML) and logistic regression (LR) algorithms, and to evaluate its predictive performance in clinical practice.

METHODS

Data of a total of 369 patients who underwent radical gastrectomy in the Department of General Surgery of Affiliated Hospital of Xuzhou Medical University (Xuzhou, China) from March 2016 to November 2019 were collected and retrospectively analyzed as the training group. In addition, data of 123 patients who underwent radical gastrectomy in the Department of General Surgery of Jining First People's Hospital (Jining, China) were collected and analyzed as the verification group. Besides, 7 ML and logistic models were developed, including decision tree, random forest, support vector machine (SVM), gradient boosting machine (GBM), naive Bayes, neural network, and LR, in order to evaluate the occurrence of lymph node metastasis in patients with gastric cancer. The ML model was established following 10 cross-validation iterations within the training dataset, and subsequently, each model was assessed using the test dataset. The model's performance was evaluated by comparing the area under the receiver operating characteristic curve of each model.

RESULTS

Compared with the traditional logistic model, among the 7 ML algorithms, except for SVM, the other models exhibited higher accuracy and reliability, and the influences of various risk factors on the model were more intuitive.

CONCLUSION

For the prediction of lymph node metastasis in gastric cancer patients, the ML algorithm outperformed traditional LR, and the GBM algorithm exhibited the most robust predictive capability.

Advances in medical image analysis with vision Transformers: A comprehensive review

The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range dependencies and spatial correlations, which is a clear advantage over convolutional neural networks (CNNs), which have been the de facto standard in Computer Vision problems so far. Thus, Transformers have become an integral part of modern medical image analysis. In this review, we provide an encyclopedic review of the applications of Transformers in medical imaging. Specifically, we present a systematic and thorough review of relevant recent Transformer literature for different medical image analysis tasks, including classification, segmentation, detection, registration, synthesis, and clinical report generation. For each of these applications, we investigate the novelty, strengths and weaknesses of the different proposed strategies and develop taxonomies highlighting key properties and contributions. Further, if applicable, we outline current benchmarks on different datasets. Finally, we summarize key challenges and discuss different future research directions. In addition, we have provided cited papers with their corresponding implementations in https://github.com/mindflow-institue/Awesome-Transformer.

Performance of machine learning-based coronary computed tomography angiography for selecting revascularization candidates

BACKGROUND

Limited studies have investigated the accuracy of therapeutic decision-making using machine learning-based coronary computed tomography angiography (ML-CCTA) compared with CCTA.

PURPOSE

To investigate the performance of ML-CCTA for therapeutic decision compared with CCTA.

MATERIAL AND METHODS

The study population consisted of 322 consecutive patients with stable coronary artery disease. The SYNTAX score was calculated with an online calculator based on ML-CCTA results. Therapeutic decision-making was determined by ML-CCTA results and the ML-CCTA-based SYNTAX score. The therapeutic strategy and the appropriate revascularization procedure were selected using ML-CCTA, CCTA, and invasive coronary angiography (ICA) independently.

RESULTS

The sensitivity, specificity, positive predictive value, negative predictive value, accuracy of ML-CCTA and CCTA for selecting revascularization candidates were 87.01%, 96.43%, 95.71%, 89.01%, 91.93%, and 85.71%, 87.50%, 86.27%, 86.98%, 86.65%, respectively, using ICA as the standard reference. The area under the receiver operating characteristic curve (AUC) of ML-CCTA for selecting revascularization candidates was significantly higher than CCTA (0.917 vs. 0.866, P = 0.016). Subgroup analysis showed the AUC of ML-CCTA for selecting percutaneous coronary intervention (PCI) or coronary artery bypass graft (CABG) candidates was significantly higher than CCTA (0.883 vs. 0.777, P < 0.001, 0.912 vs. 0.826, P = 0.003, respectively).

CONCLUSION

ML-CCTA could distinguish between patients who need revascularization and those who do not. In addition, ML-CCTA showed a slightly superior to CCTA in making an appropriate decision for patients and selecting a suitable revascularization strategy.

Joint learning framework of cross-modal synthesis and diagnosis for Alzheimer's disease by mining underlying shared modality information

Alzheimer's disease (AD) is one of the most common neurodegenerative disorders presenting irreversible progression of cognitive impairment. How to identify AD as early as possible is critical for intervention with potential preventive measures. Among various neuroimaging modalities used to diagnose AD, functional positron emission tomography (PET) has higher sensitivity than structural magnetic resonance imaging (MRI), but it is also costlier and often not available in many hospitals. How to leverage massive unpaired unlabeled PET to improve the diagnosis performance of AD from MRI becomes rather important. To address this challenge, this paper proposes a novel joint learning framework of unsupervised cross-modal synthesis and AD diagnosis by mining underlying shared modality information, improving the AD diagnosis from MRI while synthesizing more discriminative PET images. We mine underlying shared modality information in two aspects: diversifying modality information through the cross-modal synthesis network and locating critical diagnosis-related patterns through the AD diagnosis network. First, to diversify the modality information, we propose a novel unsupervised cross-modal synthesis network, which implements the inter-conversion between 3D PET and MRI in a single model modulated by the AdaIN module. Second, to locate shared critical diagnosis-related patterns, we propose an interpretable diagnosis network based on fully 2D convolutions, which takes either 3D synthesized PET or original MRI as input. Extensive experimental results on the ADNI dataset show that our framework can synthesize more realistic images, outperform the state-of-the-art AD diagnosis methods, and have better generalization on external AIBL and NACC datasets.

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.

Improving Image Classification of Knee Radiographs: An Automated Image Labeling Approach

Large numbers of radiographic images are available in musculoskeletal radiology practices which could be used for training of deep learning models for diagnosis of knee abnormalities. However, those images do not typically contain readily available labels due to limitations of human annotations. The purpose of our study was to develop an automated labeling approach that improves the image classification model to distinguish normal knee images from those with abnormalities or prior arthroplasty. The automated labeler was trained on a small set of labeled data to automatically label a much larger set of unlabeled data, further improving the image classification performance for knee radiographic diagnosis. We used BioBERT and EfficientNet as the feature extraction backbone of the labeler and imaging model, respectively. We developed our approach using 7382 patients and validated it on a separate set of 637 patients. The final image classification model, trained using both manually labeled and pseudo-labeled data, had the higher weighted average AUC (WA-AUC 0.903) value and higher AUC values among all classes (normal AUC 0.894; abnormal AUC 0.896, arthroplasty AUC 0.990) compared to the baseline model (WA-AUC = 0.857; normal AUC 0.842; abnormal AUC 0.848, arthroplasty AUC 0.987), trained using only manually labeled data. Statistical tests show that the improvement is significant on normal (p value < 0.002), abnormal (p value < 0.001), and WA-AUC (p value = 0.001). Our findings demonstrated that the proposed automated labeling approach significantly improves the performance of image classification for radiographic knee diagnosis, allowing for facilitating patient care and curation of large knee datasets.

An integrated model combined intra- and peritumoral regions for predicting chemoradiation response of non small cell lung cancers based on radiomics and deep learning

PURPOSE

The purpose of this study was to develop a model for predicting chemoradiation response in non-small cell lung cancer (NSCLC) patients by integrating radiomics and deep-learning features and combined intra- and peritumoral regions with pre-treated CT images.

MATERIALS AND METHODS

This study enrolled 462 patients with NSCLC who received chemoradiation. On the basis of pretreated CT images, we developed three models to compare the prediction of chemoradiation: intratumoral, peritumoral and combined regions. To further illustrate each model, we established different feature integration methods: a) radiomics model with 1500 features; b) deep learning model with a multiple instance learning algorithm; c) integrated model by integrating radiomic and deep learning features. For radiomics and integrated models, support vector machine and the least absolute shrinkage and selection operator were used to extract and select features. Transfer learning and max pooling algorithms were used to identify high informative features in deep learning models. We applied ten-fold cross validation in model training and testing.

RESULTS

The best area under the curve (AUC) of intratumoral, peritumoral and combined models were 0.89 (95% CI, 0.74-0.93), 0.86 (95% CI, 0.75-0.92) and 0.92 (95% CI, 0.81-0.95), respectively. It indicated the importance of the peritumoral region for treatment response prediction and should be used in combination with the intratumoral region. Integrated models gave better results than models with radiomics and deep learning features alone in all regions of interest and radiomics models outperformed deep learning models in any comparative models.

CONCLUSIONS

The model that integrate radiomic and deep learning features and combined intra- and peritumoral regions provide valuable information in predicting treatment response of chemoradiation. It can help oncologists customize personalized clinical treatment plans for NSCLC patients.

Self-supervised pre-training with contrastive and masked autoencoder methods for dealing with small datasets in deep learning for medical imaging

Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations for all training samples. However, in the medical imaging domain, annotated datasets for specific tasks are often small due to the high complexity of annotations, limited access, or the rarity of diseases. To address this challenge, deep learning models can be pre-trained on large image datasets without annotations using methods from the field of self-supervised learning. After pre-training, small annotated datasets are sufficient to fine-tune the models for a specific task. The most popular self-supervised pre-training approaches in medical imaging are based on contrastive learning. However, recent studies in natural image processing indicate a strong potential for masked autoencoder approaches. Our work compares state-of-the-art contrastive learning methods with the recently introduced masked autoencoder approach "SparK" for convolutional neural networks (CNNs) on medical images. Therefore, we pre-train on a large unannotated CT image dataset and fine-tune on several CT classification tasks. Due to the challenge of obtaining sufficient annotated training data in medical imaging, it is of particular interest to evaluate how the self-supervised pre-training methods perform when fine-tuning on small datasets. By experimenting with gradually reducing the training dataset size for fine-tuning, we find that the reduction has different effects depending on the type of pre-training chosen. The SparK pre-training method is more robust to the training dataset size than the contrastive methods. Based on our results, we propose the SparK pre-training for medical imaging tasks with only small annotated datasets.

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.

Artificial intelligence for the detection of sacroiliitis on magnetic resonance imaging in patients with axial spondyloarthritis

Background

Magnetic resonance imaging (MRI) is important for the early detection of axial spondyloarthritis (axSpA). We developed an artificial intelligence (AI) model for detecting sacroiliitis in patients with axSpA using MRI.

Methods

This study included MRI examinations of patients who underwent semi-coronal MRI scans of the sacroiliac joints owing to chronic back pain with short tau inversion recovery (STIR) sequences between January 2010 and December 2021. Sacroiliitis was defined as a positive MRI finding according to the ASAS classification criteria for axSpA. We developed a two-stage framework. First, the Faster R-CNN network extracted regions of interest (ROIs) to localize the sacroiliac joints. Maximum intensity projection (MIP) of three consecutive slices was used to mimic the reading of two adjacent slices. Second, the VGG-19 network determined the presence of sacroiliitis in localized ROIs. We augmented the positive dataset six-fold. The sacroiliitis classification performance was measured using the sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). The prediction models were evaluated using three-round three-fold cross-validation.

Results

A total of 296 participants with 4,746 MRI slices were included in the study. Sacroiliitis was identified in 864 MRI slices of 119 participants. The mean sensitivity, specificity, and AUROC for the detection of sacroiliitis were 0.725 (95% CI, 0.705-0.745), 0.936 (95% CI, 0.924-0.947), and 0.830 (95%CI, 0.792-0.868), respectively, at the image level and 0.947 (95% CI, 0.912-0.982), 0.691 (95% CI, 0.603-0.779), and 0.816 (95% CI, 0.776-0.856), respectively, at the patient level. In the original model, without using MIP and dataset augmentation, the mean sensitivity, specificity, and AUROC were 0.517 (95% CI, 0.493-0.780), 0.944 (95% CI, 0.933-0.955), and 0.731 (95% CI, 0.681-0.780), respectively, at the image level and 0.806 (95% CI, 0.729-0.883), 0.617 (95% CI, 0.523-0.711), and 0.711 (95% CI, 0.660-0.763), respectively, at the patient level. The performance was improved by MIP techniques and data augmentation.

Conclusion

An AI model was developed for the detection of sacroiliitis using MRI, compatible with the ASAS criteria for axSpA, with the potential to aid MRI application in a wider clinical setting.

Learning entity-oriented representation for biomedical relation extraction

Biomedical Relation Extraction (BioRE) aims to automatically extract semantic relations for given entity pairs and is of great significance in biomedical research. Current popular methods often utilize pretrained language models to extract semantic features from individual input instances, which frequently suffer from overlapping semantics. Overlapping semantics refers to the situation in which a sentence contains multiple entity pairs that share the same context, leading to highly similar information between these entity pairs. In this study, we propose a model for learning Entity-oriented Representation (EoR) that aims to improve the performance of the model by enhancing the discriminability between entity pairs. It contains three modules: sentence representation, entity-oriented representation, and output. The first module learns the global semantic information of the input instance; the second module focuses on extracting the semantic information of the sentence from the target entities; and the third module enhances distinguishability among entity pairs and classifies the relation type. We evaluated our approach on four BioRE tasks with eight datasets, and the experiments showed that our EoR achieved state-of-the-art performance for PPI, DDI, CPI, and DPI tasks. Further analysis demonstrated the benefits of entity-oriented semantic information in handling multiple entity pairs in the BioRE task.

Automated diagnosis of anterior cruciate ligament via a weighted multi-view network

Objective: To build a three-dimensional (3D) deep learning-based computer-aided diagnosis (CAD) system and investigate its applicability for automatic detection of anterior cruciate ligament (ACL) of the knee joint in magnetic resonance imaging (MRI). Methods: In this study, we develop a 3D weighted multi-view convolutional neural network by fusing different views of MRI to detect ACL. The network is evaluated on two MRI datasets, the in-house MRI-ACL dataset and the publicly available MRNet-v1.0 dataset. In the MRI-ACL dataset, the retrospective study collects 100 cases, and four views per patient are included. There are 50 ACL patients and 50 normal patients, respectively. The MRNet-v1.0 dataset contains 1,250 cases with three views, of which 208 are ACL patients, and the rest are normal or other abnormal patients. Results: The area under the receiver operating characteristic curve (AUC) of the ACL diagnosis system is 97.00% and 92.86% at the optimal threshold for the MRI-ACL dataset and the MRNet-v1.0 dataset, respectively, indicating a high overall diagnostic accuracy. In comparison, the best AUC of the single-view diagnosis methods are 96.00% (MRI-ACL dataset) and 91.78% (MRNet-v1.0 dataset), and our method improves by about 1.00% and 1.08%. Furthermore, our method also improves by about 1.00% (MRI-ACL dataset) and 0.28% (MRNet-v1.0 dataset) compared with the multi-view network (i.e., MRNet). Conclusion: The presented 3D weighted multi-view network achieves superior AUC in diagnosing ACL, not only in the in-house MRI-ACL dataset but also in the publicly available MRNet-v1.0 dataset, which demonstrates its clinical applicability for the automatic detection of ACL.

Risk stratification by nomogram of deep learning radiomics based on multiparametric magnetic resonance imaging in knee meniscus injury

PURPOSE

To construct and validate a nomogram model that integrated deep learning radiomic features based on multiparametric MRI and clinical features for risk stratification of meniscus injury.

METHODS

A total of 167 knee MR images were collected from two institutions. All patients were classified into two groups based on the MR diagnostic criteria proposed by Stoller et al. The automatic meniscus segmentation model was constructed through V-net. LASSO regression was performed to extract the optimal features correlated to risk stratification. A nomogram model was constructed by combining the Radscore and clinical features. The performance of the models was evaluated by ROC analysis and calibration curve. Subsequently, the model was simulated by junior doctors in order to test its practical application effect.

RESULTS

The Dice similarity coefficients of automatic meniscus segmentation models were all over 0.8. Eight optimal features, identified by LASSO regression, were employed to calculate the Radscore. The combined model showed a better performance in both the training cohort (AUC = 0.90, 95%CI: 0.84-0.95) and the validation cohort (AUC = 0.84, 95%CI: 0.72-0.93). The calibration curve indicated a better accuracy of the combined model than either the Radscore or clinical model alone. The simulation results showed that the diagnostic accuracy of junior doctors increased from 74.9 to 86.2% after using the model.

CONCLUSION

Deep learning V-net demonstrated great performance in automatic meniscus segmentation of the knee joint. It was reliable for stratifying the risk of meniscus injury of the knee by nomogram which integrated the Radscores and clinical features.

Human-machine cooperation meta-model for clinical diagnosis by adaptation to human expert's diagnostic characteristics

Artificial intelligence (AI) using deep learning approaches the capabilities of human experts in medical image diagnosis. However, due to liability issues in medical decisions, AI is often relegated to an assistant role. Based on this responsibility constraint, the effective use of AI to assist human intelligence in real-world clinics remains a challenge. Given the significant inter-individual variations in clinical decisions among physicians based on their expertise, AI needs to adapt to individual experts, complementing weaknesses and enhancing strengths. For this adaptation, AI should not only acquire domain knowledge but also understand the specific human experts it assists. This study introduces a meta-model for human-machine cooperation that first evaluates each expert's class-specific diagnostic tendencies using conditional probability, based on which the meta-model adjusts the AI's predictions. This meta-model was applied to ear disease diagnosis using otoendoscopy, highlighting improved performance when incorporating individual diagnostic characteristics, even with limited evaluation data. The highest accuracy was achieved by combining each expert's conditional probabilities with machine classification probability, using optimal weights specific to each individual's overall classification accuracy. This tailored model aims to mitigate potential misjudgments due to psychological effects caused by machine suggestions and to capitalize on the unique expertise of individual clinicians.

Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules

BACKGROUND

To develop a fully automated CNN detection system based on magnetic resonance imaging (MRI) for ACL injury, and to explore the feasibility of CNN for ACL injury detection on MRI images.

METHODS

Including 313 patients aged 16 - 65 years old, the raw data are 368 pieces with injured ACL and 100 pieces with intact ACL. By adding flipping, rotation, scaling and other methods to expand the data, the final data set is 630 pieces including 355 pieces of injured ACL and 275 pieces of intact ACL. Using the proposed CNN model with two attention mechanism modules, data sets are trained and tested with fivefold cross-validation.

RESULTS

The performance is evaluated using accuracy, precision, sensitivity, specificity and F1 score of our proposed CNN model, with results of 0.8063, 0.7741, 0.9268, 0.6509 and 0.8436. The average accuracy in the fivefold cross-validation is 0.8064. For our model, the average area under curves (AUC) for detecting injured ACL has results of 0.8886.

CONCLUSION

We propose an effective and automatic CNN model to detect ACL injury from MRI of human knees. This model can effectively help clinicians diagnose ACL injury, improving diagnostic efficiency and reducing misdiagnosis and missed diagnosis.

Toward New Assessment of Knee Cartilage Degeneration

OBJECTIVE

Assessment of human joint cartilage is a crucial tool to detect and diagnose pathological conditions. This exploratory study developed a workflow for 3D modeling of cartilage and bone based on multimodal imaging. New evaluation metrics were created and, a unique set of data was gathered from healthy controls and patients with clinically evaluated degeneration or trauma.

DESIGN

We present a novel methodology to evaluate knee bone and cartilage based on features extracted from magnetic resonance imaging (MRI) and computed tomography (CT) data. We developed patient specific 3D models of the tibial, femoral, and patellar bones and cartilages. Forty-seven subjects with a history of degenerative disease, traumatic events, or no symptoms or trauma (control group) were recruited in this study. Ninety-six different measurements were extracted from each knee, 78 2D and 18 3D measurements. We compare the sensitivity of different metrics to classify the cartilage condition and evaluate degeneration.

RESULTS

Selected features extracted show significant difference between the 3 groups. We created a cumulative index of bone properties that demonstrated the importance of bone condition to assess cartilage quality, obtaining the greatest sensitivity on femur within medial and femoropatellar compartments. We were able to classify degeneration with a maximum recall value of 95.9 where feature importance analysis showed a significant contribution of the 3D parameters.

CONCLUSION

The present work demonstrates the potential for improving sensitivity in cartilage assessment. Indeed, current trends in cartilage research point toward improving treatments and therefore our contribution is a first step toward sensitive and personalized evaluation of cartilage condition.

Comparison of evaluation metrics of deep learning for imbalanced imaging data in osteoarthritis studies

PURPOSE

To compare the evaluation metrics for deep learning methods that were developed using imbalanced imaging data in osteoarthritis studies.

MATERIALS AND METHODS

This retrospective study utilized 2996 sagittal intermediate-weighted fat-suppressed knee MRIs with MRI Osteoarthritis Knee Score readings from 2467 participants in the Osteoarthritis Initiative study. We obtained probabilities of the presence of bone marrow lesions (BMLs) from MRIs in the testing dataset at the sub-region (15 sub-regions), compartment, and whole-knee levels based on the trained deep learning models. We compared different evaluation metrics (e.g., receiver operating characteristic (ROC) and precision-recall (PR) curves) in the testing dataset with various class ratios (presence of BMLs vs. absence of BMLs) at these three data levels to assess the model's performance.

RESULTS

In a subregion with an extremely high imbalance ratio, the model achieved a ROC-AUC of 0.84, a PR-AUC of 0.10, a sensitivity of 0, and a specificity of 1.

CONCLUSION

The commonly used ROC curve is not sufficiently informative, especially in the case of imbalanced data. We provide the following practical suggestions based on our data analysis: 1) ROC-AUC is recommended for balanced data, 2) PR-AUC should be used for moderately imbalanced data (i.e., when the proportion of the minor class is above 5% and less than 50%), and 3) for severely imbalanced data (i.e., when the proportion of the minor class is below 5%), it is not practical to apply a deep learning model, even with the application of techniques addressing imbalanced data issues.