Osteoporosis is a significant global health concern that can be difficult to detect early due to a lack of symptoms. At present, the examination of osteoporosis depends mainly on methods containing dual‐energy X‐ray, quantitative CT, etc., which are high costs in terms of equipment and human time. Therefore, a more efficient and economical method is urgently needed for diagnosing osteoporosis. With the development of deep learning, automatic diagnosis models for various diseases have been proposed. However, the establishment of these models generally requires images with only lesion areas, and annotating the lesion areas is time‐consuming. To address this challenge, we propose a joint learning framework for osteoporosis diagnosis that combines localization, segmentation, and classification to enhance diagnostic accuracy. Our method includes a boundary heat map regression branch for thinning segmentation and a gated convolution module for adjusting context features in the classification module. We also integrate segmentation and classification features and propose a feature fusion module to adjust the weight of different levels of vertebrae. We trained our model on a self‐built dataset and achieved an overall accuracy rate of 93.3% for the three label categories (normal, osteopenia, and osteoporosis) in the testing datasets. The area under the curve for the normal category is 0.973; for the osteopenia category, it is 0.965; and for the osteoporosis category, it is 0.985. Our method provides a promising alternative for the diagnosis of osteoporosis at present.

Objective: To develop and evaluate a deep learning model based on chest CT that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images, and explore the feasibility and effectiveness of the model based on the lumbar 1 vertebral body alone. Materials and methods: The chest CT images of 1048 health check subjects from January 2021 to June were retrospectively collected as the internal dataset (the segmentation model: 548 for training, 100 for tuning and 400 for test. The classification model: 530 for training, 100 for validation and 418 for test set). The subjects were divided into three categories according to the quantitative CT measurements, namely, normal, osteopenia and osteoporosis. First, a deep learning-based segmentation model was constructed, and the dice similarity coefficient(DSC) was used to compare the consistency between the model and manual labelling. Then, two classification models were established, namely, (i) model 1 (fusion feature construction of lumbar vertebral bodies 1 and 2) and (ii) model 2 (feature construction of lumbar 1 alone). Receiver operating characteristic curves were used to evaluate the diagnostic efficacy of the models, and the Delong test was used to compare the areas under the curve. Results: When the number of images in the training set was 300, the DSC value was 0.951 ± 0.030 in the test set. The results showed that the model 1 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.990, 0.952 and 0.980; the model 2 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.983, 0.940 and 0.978. The Delong test showed that there was no significant difference in area under the curve (AUC) values between the osteopenia group and osteoporosis group (P = 0.210, 0.546), while the AUC value of normal model 2 was higher than that of model 1 (0.990 vs. 0.983, P = 0.033). Conclusion: This study proposed a chest CT deep learning model that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images. We further constructed the comparable model based on the lumbar 1 vertebra alone which can shorten the scan length, reduce the radiation dose received by patients, and reduce the training cost of technologists.

Zebrafish embryo fluorescent vessel analysis, which aims to automatically investigate the pathogenesis of diseases, has attracted much attention in medical imaging. Zebrafish vessel segmentation is a fairly challenging task, which requires distinguishing foreground and background vessels from the 3D projection images. Recently, there has been a trend to introduce domain knowledge to deep learning algorithms for handling complex environment segmentation problems with accurate achievements. In this paper, a novel dual deep learning framework called Dual ResUNet is developed to conduct zebrafish embryo fluorescent vessel segmentation. To avoid the loss of spatial and identity information, the U-Net model is extended to a dual model with a new residual unit. To achieve stable and robust segmentation performance, our proposed approach merges domain knowledge with a novel contour term and shape constraint. We compare our method qualitatively and quantitatively with several standard segmentation models. Our experimental results show that the proposed method achieves better results than the state-of-art segmentation methods. By investigating the quality of the vessel segmentation, we come to the conclusion that our Dual ResUNet model can learn the characteristic features in those cases where fluorescent protein is deficient or blood vessels are overlapped and achieves robust performance in complicated environments.

Summary: A multi-feature fusion DCNN model for automated evaluation of lumbar vertebrae L1 on chest combined with clinical information and radiomics permits estimation of volumetric bone mineral density for evaluation of osteoporosis. Purpose: To develop a multi-feature deep learning model based on chest CT, combined with clinical information and radiomics to explore the feasibility in screening for osteoporosis based on estimation of volumetric bone mineral density. Methods: The chest CT images of 1048 health check subjects were retrospectively collected as the master dataset, and the images of 637 subjects obtained from a different CT scanner were used for the external validation cohort. The subjects were divided into three categories according to the quantitative CT (QCT) examination, namely, normal group, osteopenia group, and osteoporosis group. Firstly, a deep learning–based segmentation model was constructed. Then, classification models were established and selected, and then, an optimal model to build bone density value prediction regression model was chosen. Results: The DSC value was 0.951 ± 0.030 in the testing dataset and 0.947 ± 0.060 in the external validation cohort. The multi-feature fusion model based on the lumbar 1 vertebra had the best performance in the diagnosis. The area under the curve (AUC) of diagnosing normal, osteopenia, and osteoporosis was 0.992, 0.973, and 0.989. The mean absolute errors (MAEs) of the bone density prediction regression model in the test set and external testing dataset are 8.20 mg/cm³ and 9.23 mg/cm³, respectively, and the root mean square errors (RMSEs) are 10.25 mg/cm³ and 11.91 mg/cm³, respectively. The R-squared values are 0.942 and 0.923, respectively. The Pearson correlation coefficients are 0.972 and 0.965. Conclusion: The multi-feature fusion DCNN model based on only the lumbar 1 vertebrae and clinical variables can perform bone density three-classification diagnosis and estimate volumetric bone mineral density. If confirmed in independent populations, this automated opportunistic chest CT evaluation can help clinical screening of large-sample populations to identify subjects at high risk of osteoporotic fracture.

Background: This study was aimed to explore the clinical application of dual-energy computed tomography (DECT) monoenergetic plus (mono+) imaging to evaluate anatomical variations in the inferior mesenteric artery (IMA). Methods: The clinical and imaging data of 212 patients who had undergone total abdominal DECT were retrospectively analyzed. The post-processing mono+ technique was used to obtain 40-keV single-level images in the arterial phase. Three-dimensional reconstruction was performed to evaluate the relationship between the IMA root position and the spinal level, IMA length, and IMA branch type, as well as the position of the left colic artery (LCA) and inferior mesenteric vein (IMV) at the IMA root level. Results: The IMA root was located at the L3 level in 78.3% of cases and at the L2/L3 level in 3.3%. The highest vertebral level of IMA origin was L2 (4.2%), and the lowest was L4 (7.1%). The distance from the IMA root to the level of the sacral promontory was 99.58 ± 13.07 mm, which increased with the elevation of the IMA root at the spinal level. Of the patients, 53.8% demonstrated Type I IMA, 23.1% Type II, 20.7% Type III, and 2.4% Type IV. The length of the IMA varied from 13.6 to 66.0 mm. 77.3% of the IMAs belonged to Type A, the adjacent type, and 22.7% to Type B, the distant type. Conclusion: DECT mono+ can preoperatively evaluate the anatomical characteristics of the IMA and the positional relationship between the LCA and IMV at the IMA root level, which would help clinicians plan individualized surgery for patients.

Rehabilitation movement assessment often requires patients to wear expensive and inconvenient sensors or optical markers. To address this issue, we propose a non-contact and real-time approach using a lightweight pose detection algorithm–Sports Rehabilitation-Pose(SR-Pose), and a depth camera for accurate assessment of rehabilitation movement. Our approach utilizes an E-Shufflenet network to extract underlying features of the target, a RLE-Decoder module to directly regress the coordinate values of 16 key points, and a Weight Fusion Unit (WFU) module to output optimal human posture detection results. By combining the detected human pose information with depth information, we accurately calculate the angle between each joint in three-dimensional space. Furthermore, we apply the DTW algorithm to solve the distance measurement and matching problem of video sequences with different lengths in rehabilitation evaluation tasks. Experimental results show that our method can detect human joint nodes with an average detection speed of 14.32ms and an average detection accuracy for pose of 91.2%, demonstrating its computational efficiency and effectiveness for practical application. Our proposed approach provides a low-cost and user-friendly alternative to traditional sensor-based methods, making it a promising solution for rehabilitation movement assessment.