Background Accurately diagnosing supraspinatus tears based on magnetic resonance imaging (MRI) is challenging and time-combusting due to the experience level variability of the musculoskeletal radiologists and orthopedic surgeons. We developed a deep learning-based model for automatically diagnosing supraspinatus tears (STs) using shoulder MRI and validated its feasibility in clinical practice. Materials and methods A total of 701 shoulder MRI data (2804 images) were retrospectively collected for model training and internal test. An additional 69 shoulder MRIs (276 images) were collected from patients who underwent shoulder arthroplasty and constituted the surgery test set for clinical validation. Two advanced convolutional neural networks (CNN) based on Xception were trained and optimized to detect STs. The diagnostic performance of the CNN was evaluated according to its sensitivity, specificity, precision, accuracy, and F1 score. Subgroup analyses were performed to verify its robustness, and we also compared the CNN’s performance with that of 4 radiologists and 4 orthopedic surgeons on the surgery and internal test sets. Results Optimal diagnostic performance was achieved on the 2D model, from which F1-scores of 0.824 and 0.75, and areas under the ROC curves of 0.921 (95% confidence interval, 0.841–1.000) and 0.882 (0.817–0.947) were observed on the surgery and internal test sets. For the subgroup analysis, the 2D CNN model demonstrated a sensitivity of 0.33–1.000 and 0.625–1.000 for different degrees of tears on the surgery and internal test sets, and there was no significant performance difference between 1.5 and 3.0 T data. Compared with eight clinicians, the 2D CNN model exhibited better diagnostic performance than the junior clinicians and was equivalent to senior clinicians. Conclusions The proposed 2D CNN model realized the adequate and efficient automatic diagnoses of STs, which achieved a comparable performance of junior musculoskeletal radiologists and orthopedic surgeons. It might be conducive to assisting poor-experienced radiologists, especially in community scenarios lacking consulting experts.

Background: The diagnosis of osteoporosis is still one of the most critical topics for orthopedic surgeons worldwide. One research direction is to use existing clinical imaging data for accurate measurements of bone mineral density (BMD) without additional radiation.Methods: A novel phantom-less quantitative computed tomography (PL-QCT) system was developed to measure BMD and diagnose osteoporosis, as our previous study reported. Compared with traditional phantom-less QCT, this tool can conduct an automatic selection of body tissues and complete the BMD calibration with high efficacy and precision. The function has great advantages in big data screening and thus expands the scope of use of this novel PL-QCT. In this study, we utilized lung cancer or COVID-19 screening low-dose computed tomography (LDCT) of 649 patients for BMD calibration by the novel PL-QCT, and we made the BMD changes with age based on this PL-QCT.Results: The results show that the novel PL-QCT can predict osteoporosis with relatively high accuracy and precision using LDCT, and the AUC values range from 0.68 to 0.88 with DXA results as diagnosis reference. The relationship between PL-QCT BMD with age is close to the real trend population (from ∼160 mg/cc in less than 30 years old to ∼70 mg/cc in greater than 80 years old for both female and male groups). Additionally, the calculation results of Pearson’s r-values for correlation between CT values with BMD in different CT devices were 0.85–0.99.Conclusion: To our knowledge, it is the first time for automatic PL-QCT to evaluate the performance against dual-energy X-ray absorptiometry (DXA) in LDCT images. The results indicate that it may be a promising tool for individuals screened for low-dose chest computed tomography.

BackgroundCystic lesions are frequently observed in knee joint diseases and are usually associated with joint pain, degenerative disorders, or acute injury. Magnetic resonance imaging-based, artificial intelligence-assisted cyst detection is an effective method to improve the whole knee joint analysis. However, few studies have investigated this method. This study is the first attempt at auto-detection of knee cysts based on deep learning methods.MethodsThis retrospective study collected data from 282 subjects with knee cysts confirmed at our institution from January to October 2021. A Squeeze-and-Excitation (SE) inception attention-based You only look once version 5 (SE-YOLOv5) model was developed based on a self-attention mechanism for knee cyst-like lesion detection and differentiation from knee effusions, both characterized by high T2-weighted signals in magnetic resonance imaging (MRI) scans. Model performance was evaluated via metrics including accuracy, precision, recall, mean average precision (mAP), F1 score, and frames per second (fps).ResultsThe deep learning model could accurately identify knee MRI scans and auto-detect both obvious cyst lesions and small ones with inconspicuous contrasts. The SE-YOLO V5 model constructed in this study yielded superior performance (F1 = 0.879, precision = 0.887, recall = 0.872, all class mAP0.5 = 0.944, effusion mAP = 0.945, cyst mAP = 0.942) and improved detection speed compared to a traditional YOLO model.ConclusionThis proof-of-concept study examined whether deep learning models could detect knee cysts and distinguish them from knee effusions. The results demonstrated that the classical Yolo V5 and proposed SE-Yolo V5 models could accurately identify cysts.

No abstract