Computer-Aided Diagnosis of Different Rotator Cuff Lesions Using Shoulder Musculoskeletal Ultrasound

Artificial Intelligence Aids Detection of Rotator Cuff Pathology: A Systematic Review

PURPOSE

To determine the model performance of artificial intelligence (AI) in detecting rotator cuff pathology using different imaging modalities and to compare capability with physicians in clinical scenarios.

METHODS

The review followed the PRISMA guidelines and was registered on PROSPERO. The criteria were as follows: 1) studies on the application of AI in detecting rotator cuff pathology using medical images, and 2) studies on smart devices for assisting in diagnosis were excluded. The following data were extracted and recorded: statistical characteristics, input features, AI algorithms used, sample sizes of training and testing sets, and model performance. The data extracted from the included studies were narratively reviewed.

RESULTS

A total of 14 articles, comprising 23,119 patients, met the inclusion and exclusion criteria. The pooled mean age of the patients was 56.7 years, and the female rate was 56.1%. The area under the curve (AUC) of the algorithmic model to detect rotator cuff pathology from ultrasound images, MRI images, and radiographic series ranged from 0.789 to 0.950, 0.844 to 0.943, and 0.820 to 0.830, respectively. Notably, 1 of the studies reported that AI models based on ultrasound images demonstrated a diagnostic performance similar to that of radiologists. Another comparative study demonstrated that AI models using MRI images exhibited greater accuracy and specificity compared to orthopedic surgeons in the diagnosis of rotator cuff pathology, albeit not in sensitivity.

CONCLUSIONS

The detection of rotator cuff pathology has been significantly aided by the exceptional performance of AI models. In particular, these models are equally adept as musculoskeletal radiologists in using ultrasound to diagnose rotator cuff pathology. Furthermore, AI models exhibit statistically superior levels of accuracy and specificity when using MRI to diagnose rotator cuff pathology, albeit with no marked difference in sensitivity, in comparison to orthopaedic surgeons.

LEVEL OF EVIDENCE

Level III, systematic review of Level III studies.

Detection of the rotator cuff tears using a novel convolutional neural network from magnetic resonance image (MRI)

The rotator cuff tear is a common situation for basketballers, handballers, or other athletes that strongly use their shoulders. This injury can be diagnosed precisely from a magnetic resonance (MR) image. In this paper, a novel deep learning-based framework is proposed to diagnose rotator cuff tear from MRI images of patients suspected of the rotator cuff tear. First, we collected 150 shoulders MRI images from two classes of rotator cuff tear patients and healthy ones with the same numbers. These images were observed by an orthopedic specialist and then tagged and used as input in the various configurations of the Convolutional Neural Network (CNN). At this stage, five different configurations of convolutional networks have been examined. Then, in the next step, the selected network with the highest accuracy is used to extract the deep features and classify the two classes of rotator cuff tear and healthy. Also, MRI images are feed to two quick pre-trained CNNs (MobileNetv2 and SqueezeNet) to compare with the proposed CNN. Finally, the evaluation is performed using the 5-fold cross-validation method. Also, a specific Graphical User Interface (GUI) was designed in the MATLAB environment for simplicity, which allows for testing by detecting the image class. The proposed CNN achieved higher accuracy than the two mentioned pre-trained CNNs. The average accuracy, precision, sensitivity, and specificity achieved by the best selected CNN configuration are equal to 92.67%, 91.13%, 91.75%, and 92.22%, respectively. The deep learning algorithm could accurately rule out significant rotator cuff tear based on shoulder MRI.

Ultrasonic Through-Transmission Measurements of Human Musculoskeletal and Fat Properties

The study described here was aimed at investigating the feasibility of using the ultrasonic through-transmission technique to estimate human musculoskeletal and fat properties. Five hundred eighty-two volunteers were assessed by dual-energy X-ray absorptiometry (DXA) and ultrasonic transmission techniques. Bone mineral density (BMD), muscle and fat mass were measured for both legs and the whole body. Hip BMD and spine BMD were also measured. Ultrasonic transmission measurements were performed on the heel, and the measured parameters were broadband ultrasound attenuation (BUA), speed of sound (SOS), ultrasonic stiffness index (SI), T-score and Z-score, which were significantly correlated with all measured BMDs. The optimal correlation was observed between SI and left-leg BMD (p < 0.001) before and after adjustment for age, sex and body mass index (BMI). The linear and partial correlation analyses revealed that BUA and SOS were closely associated with muscle and fat mass, respectively. Multiple regressions revealed that muscle and fat mass significantly contributed to the prediction of transmission parameters, explaining up to 17.83% (p < 0.001) variance independently of BMD. The results suggest that the ultrasonic through-transmission technique could help in the clinical diagnosis of skeletal and muscular system diseases.

Development of a convolutional neural network for the identification and the measurement of the median nerve on ultrasound images acquired at carpal tunnel level

Background

Deep learning applied to ultrasound (US) can provide a feedback to the sonographer about the correct identification of scanned tissues and allows for faster and standardized measurements. The most frequently adopted parameter for US diagnosis of carpal tunnel syndrome is the increasing of the cross-sectional area (CSA) of the median nerve. Our aim was to develop a deep learning algorithm, relying on convolutional neural networks (CNNs), for the localization and segmentation of the median nerve and the automatic measurement of its CSA on US images acquired at the proximal inlet of the carpal tunnel.

Methods

Consecutive patients with rheumatic and musculoskeletal disorders were recruited. Transverse US images were acquired at the carpal tunnel inlet, and the CSA was manually measured. Anatomical variants were registered. The dataset consisted of 246 images (157 for training, 40 for validation, and 49 for testing) from 103 patients each associated with manual annotations of the nerve boundary. A Mask R-CNN, state-of-the-art CNN for image semantic segmentation, was trained on this dataset to accurately localize and segment the median nerve section. To evaluate the performances on the testing set, precision (Prec), recall (Rec), mean average precision (mAP), and Dice similarity coefficient (DSC) were computed. A sub-analysis excluding anatomical variants was performed. The CSA was automatically measured by the algorithm.

Results

The algorithm correctly identified the median nerve in 41/49 images (83.7%) and in 41/43 images (95.3%) excluding anatomical variants. The following metrics were obtained (with and without anatomical variants, respectively): Prec 0.86 ± 0.33 and 0.96 ± 0.18, Rec 0.88 ± 0.33 and 0.98 ± 0.15, mAP 0.88 ± 0.33 and 0.98 ± 0.15, and DSC 0.86 ± 0.19 and 0.88 ± 0.19. The agreement between the algorithm and the sonographer CSA measurements was excellent [ICC 0.97 (0.94–0.98)].

Conclusions

The developed algorithm has shown excellent performances, especially if excluding anatomical variants. Future research should aim at expanding the US image dataset including a wider spectrum of normal anatomy and pathology. This deep learning approach has shown very high potentiality for a fully automatic support for US assessment of carpal tunnel syndrome.

Construction of a Computer-Aided Analysis System for Orthopedic Diseases Based on High-Frequency Ultrasound Images

The area of medical diagnosis has been transformed by computer-aided diagnosis (CAD). With the advancement of technology and the widespread availability of medical data, CAD has gotten a lot of attention, and numerous methods for predicting different pathological diseases have been created. Ultrasound (US) is the safest clinical imaging method; therefore, it is widely utilized in medical and healthcare settings with computer-aided systems. However, owing to patient movement and equipment constraints, certain artefacts make identification of these US pictures challenging. To enhance the quality of pictures for classification and segmentation, certain preprocessing techniques are required. Hence, we proposed a three-stage image segmentation method using U-Net and Iterative Random Forest Classifier (IRFC) to detect orthopedic diseases in ultrasound images efficiently. Initially, the input dataset is preprocessed using Enhanced Wiener Filter for image denoising and image enhancement. Then, the proposed segmentation method is applied. Feature extraction is performed by transform-based analysis. Finally, obtained features are reduced to optimal subset using Principal Component Analysis (PCA). The classification is done using the proposed Iterative Random Forest Classifier. The proposed method is compared with the conventional performance measures like accuracy, specificity, sensitivity, and dice score. The proposed method is proved to be efficient for detecting orthopedic diseases in ultrasound images than the conventional methods.

Investigation of Ultrasound as a Diagnostic Imaging Modality for Little League Shoulder

Objective Ultrasound (US) is an established imaging modality in adult sports medicine but is not commonly used in the diagnosis of pediatric sports conditions, such as Little League shoulder (LLS). This study was conducted to determine the reliability of US measurement of width of the physis at the proximal humerus in diagnosed LLS and to compare US to radiography (RA) in detecting a difference between the affected (dominant) (A) and unaffected (U) shoulders.

Materials and Methods Ten male baseball players diagnosed with LLS were enrolled in the study. US images of the proximal humeral physis at the greater tuberosity of both shoulders were obtained by an US-trained sports medicine physician, and the physeal width was measured. Blinded to prior measurements, a separate physician performed measurements on the stored US images. Measurements were compared with RA on the anteroposterior (AP) view for both A and U at the time of the initial visit and for A at follow-up.

Results The physeal width (mm) at A and U at the initial visit averaged 5.94 ± 1.69 and 4.36 ± 1.20 respectively on RA, and 4.15 ± 1.12 and 3.40 ± 0.85 on US. Median difference of averaged US measurements between A and U at initial evaluation was 0.75 mm (p = 0.00016). A linear model showed US measurements to be predictive of RA on A (R2 = 0.51) and U (R2 = 0.48).

Conclusion US was able to reliably measure the width of the proximal humeral physis and detect a difference between A and U. US correlated well with RA (standard for LLS). US should be considered by the US-trained physician for the diagnosis of LLS.

Imbalanced Loss-Integrated Deep-Learning-Based Ultrasound Image Analysis for Diagnosis of Rotator-Cuff Tear

A rotator cuff tear (RCT) is an injury in adults that causes difficulty in moving, weakness, and pain. Only limited diagnostic tools such as magnetic resonance imaging (MRI) and ultrasound Imaging (UI) systems can be utilized for an RCT diagnosis. Although UI offers comparable performance at a lower cost to other diagnostic instruments such as MRI, speckle noise can occur the degradation of the image resolution. Conventional vision-based algorithms exhibit inferior performance for the segmentation of diseased regions in UI. In order to achieve a better segmentation for diseased regions in UI, deep-learning-based diagnostic algorithms have been developed. However, it has not yet reached an acceptable level of performance for application in orthopedic surgeries. In this study, we developed a novel end-to-end fully convolutional neural network, denoted as Segmentation Model Adopting a pRe-trained Classification Architecture (SMART-CA), with a novel integrated on positive loss function (IPLF) to accurately diagnose the locations of RCT during an orthopedic examination using UI. Using the pre-trained network, SMART-CA can extract remarkably distinct features that cannot be extracted with a normal encoder. Therefore, it can improve the accuracy of segmentation. In addition, unlike other conventional loss functions, which are not suited for the optimization of deep learning models with an imbalanced dataset such as the RCT dataset, IPLF can efficiently optimize the SMART-CA. Experimental results have shown that SMART-CA offers an improved precision, recall, and dice coefficient of 0.604% (+38.4%), 0.942% (+14.0%) and 0.736% (+38.6%) respectively. The RCT segmentation from a normal ultrasound image offers the improved precision, recall, and dice coefficient of 0.337% (+22.5%), 0.860% (+15.8%) and 0.484% (+28.5%), respectively, in the RCT segmentation from an ultrasound image with severe speckle noise. The experimental results demonstrated the IPLF outperforms other conventional loss functions, and the proposed SMART-CA optimized with the IPLF showed better performance than other state-of-the-art networks for the RCT segmentation with high robustness to speckle noise.

Artificial Intelligence for Ultrasound Informative Image Selection of Metacarpal Head Cartilage. A Pilot Study

Objectives: This study aims to develop an automatic deep-learning algorithm, which is based on Convolutional Neural Networks (CNNs), for ultrasound informative-image selection of hyaline cartilage at metacarpal head level. The algorithm performance and that of three beginner sonographers were compared with an expert assessment, which was considered the gold standard.

Methods: The study was divided into two steps. In the first one, an automatic deep-learning algorithm for image selection was developed using 1,600 ultrasound (US) images of the metacarpal head cartilage (MHC) acquired in 40 healthy subjects using a very high-frequency probe (up to 22 MHz). The algorithm task was to identify US images defined informative as they show enough information to fulfill the Outcome Measure in Rheumatology US definition of healthy hyaline cartilage. The algorithm relied on VGG16 CNN, which was fine-tuned to classify US images in informative and non-informative ones. A repeated leave-four-subject out cross-validation was performed using the expert sonographer assessment as gold-standard. In the second step, the expert assessed the algorithm and the beginner sonographers' ability to obtain US informative images of the MHC.

Results: The VGG16 CNN showed excellent performance in the first step, with a mean area (AUC) under the receiver operating characteristic curve, computed among the 10 models obtained from cross-validation, of 0.99 ± 0.01. The model that reached the best AUC on the testing set, which we named “MHC identifier 1,” was then evaluated by the expert sonographer. The agreement between the algorithm, and the expert sonographer was almost perfect [Cohen's kappa: 0.84 (95% confidence interval: 0.71–0.98)], whereas the agreement between the expert and the beginner sonographers using conventional assessment was moderate [Cohen's kappa: 0.63 (95% confidence interval: 0.49–0.76)]. The conventional obtainment of US images by beginner sonographers required 6.0 ± 1.0 min, whereas US videoclip acquisition by a beginner sonographer lasted only 2.0 ± 0.8 min.

Conclusion: This study paves the way for the automatic identification of informative US images for assessing MHC. This may redefine the US reliability in the evaluation of MHC integrity, especially in terms of intrareader reliability and may support beginner sonographers during US training.

Quantitative Evaluation of Rotator Cuff Tears Based on Non-linear Statistical Analysis of Ultrasound Radiofrequency Signals

There is increasing clinical requirement for early and accurate ultrasound diagnosis of rotator cuff tears (RCTs). A method based on non-linear statistical analysis was proposed for the detection of RCTs using ultrasound radiofrequency (RF) signals. One hundred fifty-two patients with shoulder pain were first examined with ultrasound and then diagnosed with magnetic resonance imaging (MRI) as the ground truth. By comparison of the region of interest (ROI) with a part of the supraspinatus with no pathologic change part in the same RF signal frame, the relative P_ks value (viz., rP_ks value) was evaluated to quantify the pathophysiologic changes. The results indicated that the rP_ks values of all RCTs are <0.7, and the accuracy, sensitivity and specificity of the proposed method can reach 97.5%, 100% and 91.4%, respectively. This computer-aided method was found to perform better diagnostic than the results reported by an experienced radiologist (accuracy = 75.7%, sensitivity = 72.6%, and specificity = 85.7%). The high sensitivity advantage of this method indicates that the prospects for its application in the computer-aided diagnosis of RCTs are good.

Computer-aided diagnosis of isocitrate dehydrogenase genotypes in glioblastomas from radiomic patterns

World Health Organization tumor classifications of the central nervous system differentiate glioblastoma multiforme (GBM) into wild-type (WT) and mutant isocitrate dehydrogenase (IDH) genotypes. This study proposes a noninvasive computer-aided diagnosis to interpret the status of IDH in glioblastomas from transformed magnetic resonance imaging patterns. The collected image database was composed of 32 WT and 7 mutant IDH cases. For each image, a ranklet transformation which changed the original pixel values into relative coefficients was 1st applied to reduce the effects of different scanning parameters and machines on the underlying patterns. Extracting various textural features from the transformed ranklet images and combining them in a logistic regression classifier allowed an IDH prediction. We achieved an accuracy of 90%, a sensitivity of 57%, and a specificity of 97%. Four of the selected textural features in the classifier (homogeneity, difference entropy, information measure of correlation, and inverse difference normalized) were significant (P < .05), and the other 2 were close to being significant (P = .06). The proposed computer-aided diagnosis system based on radiomic textural features from ranklet-transformed images using relative rankings of pixel values as intensity-invariant coefficients is a promising noninvasive solution to provide recommendations about the IDH status in GBM across different healthcare institutions.

Detecting Rotator Cuff Tears: A Network Meta-analysis of 144 Diagnostic Studies

BACKGROUND

Many imaging techniques have been developed for the detection of rotator cuff tears (RCTs). Despite numerous quantitative diagnostic studies, their relative accuracy remains inconclusive.

PURPOSE

To determine which of 3 commonly used imaging modalities is optimal for the diagnosis of RCTs.

STUDY DESIGN

Systematic review; Level of evidence, 4.

METHODS

Studies evaluating the performance of magnetic resonance imaging (MRI), magnetic resonance arthrography (MRA), and ultrasound (US) used in the detection of RCTs were retrieved from the PubMed/MEDLINE and Embase databases. Diagnostic data were extracted from articles that met the inclusion/exclusion criteria. A network meta-analysis was performed using an arm-based model to pool the absolute sensitivity and specificity, relative sensitivity and specificity, and diagnostic odds ratio as well as the superiority index for ranking the probability of these techniques.

RESULTS

A total of 144 studies involving 14,059 patients (14,212 shoulders) were included in this network meta-analysis. For the detection of full-thickness (FT) tears, partial-thickness (PT) tears, or any tear, MRA had the highest sensitivity, specificity, and superiority index. For the detection of any tear, MRI had better performance than US (sensitivity: 0.84 vs 0.81, specificity: 0.86 vs 0.82, and superiority index: 0.98 vs 0.22, respectively). With regard to FT tears, MRI had a higher sensitivity and superiority index than US (0.91 vs 0.87 and 0.67 vs 0.28, respectively) and a similar specificity (0.88 vs 0.88, respectively). The results for PT tears were similar to the detection of FT tears. A sensitivity analysis was performed by removing studies involving only 1 arm for FT tears, PT tears, or any tear, and the results remained stable.

CONCLUSION

This network meta-analysis of diagnostic tests revealed that high-field MRA had the highest diagnostic value for detecting any tear, followed by low-field MRA, high-field MRI, high-frequency US, low-field MRI, and low-frequency US. These findings can help guide clinicians in deciding on the appropriate imaging modality.