Diagnostic Performance for Detecting Bone Marrow Edema of the Hip on Dual-Energy CT: Deep Learning Model vs. Musculoskeletal Physicians and Radiologists

Diagnostic performance of dual-energy CT in detecting bone marrow edema in lower limb joint injuries: a meta-analysis

OBJECTIVE

We aimed to evaluate the diagnostic performance of dual-energy computed tomography (DECT) in detecting bone marrow edema (BME) in patients with lower limb joint injuries.

METHODS

A thorough literature search was conducted across the PubMed, Embase, and Web of Science databases to identify relevant studies up to April 2024. Studies examining the diagnostic performance of DECT in detecting BME in lower limb joint injuries patients were included. Sensitivity and specificity were evaluated using the inverse variance method and transformed via the Freeman-Tukey double arcsine transformation. Furthermore, the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was utilized to evaluate the methodological quality of the included studies.

RESULTS

This meta-analysis included 17 articles involving 625 patients. The pooled sensitivity, specificity, and AUC for DECT in detecting BME in lower limb joint injuries patients were 0.82 (95 % CI: 0.76-0.87), 0.95 (95 % CI: 0.92-0.97), and 0.95 (95 % CI: 0.93-0.97), respectively. The pooled sensitivity of DECT for detecting BME in knee, hip, and ankle joint injuries was 0.80, 0.84, and 0.80, with no significant difference among these joints (P = 0.55). The pooled specificity for knee, hip, and ankle injuries was 0.95, 0.97, and 0.89. Specificity differed significantly among the joints (P < 0.01), with the highest specificity in hip injuries.

CONCLUSIONS

Our meta-analysis indicates that DECT demonstrates high diagnostic performance in detecting BME in patients with lower limb joint injuries, with the highest specificity observed in hip joint injuries. To validate these findings, further larger prospective studies are necessary.

W-DRAG: A joint framework of WGAN with data random augmentation optimized for generative networks for bone marrow edema detection in dual energy CT

Dual-energy computed tomography (CT) is an excellent substitute for identifying bone marrow edema in magnetic resonance imaging. However, it is rarely used in practice owing to its low contrast. To overcome this problem, we constructed a framework based on deep learning techniques to screen for diseases using axial bone images and to identify the local positions of bone lesions. To address the limited availability of labeled samples, we developed a new generative adversarial network (GAN) that extends expressions beyond conventional augmentation (CA) methods based on geometric transformations. We theoretically and experimentally determined that combining the concepts of data augmentation optimized for GAN training (DAG) and Wasserstein GAN yields a considerably stable generation of synthetic images and effectively aligns their distribution with that of real images, thereby achieving a high degree of similarity. The classification model was trained using real and synthetic samples. Consequently, the GAN technique used in the diagnostic test had an improved F1 score of approximately 7.8% compared with CA. The final F1 score was 80.24%, and the recall and precision were 84.3% and 88.7%, respectively. The results obtained using the augmented samples outperformed those obtained using pure real samples without augmentation. In addition, we adopted explainable AI techniques that leverage a class activation map (CAM) and principal component analysis to facilitate visual analysis of the network's results. The framework was designed to suggest an attention map and scattering plot to visually explain the disease predictions of the network.

Dual-energy CT applications in musculoskeletal disorders

Dual-energy CT (DECT) is an exciting application in CT technology conferring many advantages over conventional single-energy CT at no additional with comparable radiation dose to the patient. Various emerging and increasingly established clinical DECT applications in musculoskeletal (MSK) imaging such as bone marrow oedema detection, metal artefact reduction, monosodium urate analysis, and collagen analysis for ligamentous, meniscal, and disc injuries are made possible through its advanced DECT post-processing capabilities. These provide superior information on tissue composition, artefact reduction and image optimization. Newer DECT applications to evaluate fat fraction for sarcopenia, Rho/Z application for soft tissue calcification differentiation, 3D rendering, and AI integration are being assessed for future use. In this article, we will discuss the established and developing applications of DECT in the setting of MSK radiology as well as the basic principles of DECT which facilitate them.

Classification of Skin Cancer Lesions Using Explainable Deep Learning

Skin cancer is among the most prevalent and life-threatening forms of cancer that occur worldwide. Traditional methods of skin cancer detection need an in-depth physical examination by a medical professional, which is time-consuming in some cases. Recently, computer-aided medical diagnostic systems have gained popularity due to their effectiveness and efficiency. These systems can assist dermatologists in the early detection of skin cancer, which can be lifesaving. In this paper, the pre-trained MobileNetV2 and DenseNet201 deep learning models are modified by adding additional convolution layers to effectively detect skin cancer. Specifically, for both models, the modification includes stacking three convolutional layers at the end of both the models. A thorough comparison proves that the modified models show their superiority over the original pre-trained MobileNetV2 and DenseNet201 models. The proposed method can detect both benign and malignant classes. The results indicate that the proposed Modified DenseNet201 model achieves 95.50% accuracy and state-of-the-art performance when compared with other techniques present in the literature. In addition, the sensitivity and specificity of the Modified DenseNet201 model are 93.96% and 97.03%, respectively.