生物医学工程学杂志最新文献

Medical images of coronary artery plaque are always accompanied by the situation of extreme class imbalance. The traditional two-step methods locate the region of interest (ROI) in the sample firstly, and then segment the sample within the ROI. On the other hand, the traditional resampling methods use resampling strategies to increase the number of minority class samples to mitigate the effects of class imbalance. These two types of methods either make the network structure more complex or decrease training efficiency and performance of the model due to the increase of samples. This paper proposes a method including a novel focal weighted accuracy loss function and improved metrics evaluation algorithms to address the issues in the segmentation of coronary artery calcification plaque mentioned above. Experimental results on the selected dataset show the proposed method increased the training speed and improved the segmentation performance of the model without performing resampling on the dataset. Specifically, the F1-score was 0.873 5, the precision was 0.929 6, and the recall was 0.823 8. The F1-score was largely improved compared with the method using focal loss function. Furthermore, compared with methods with multiple models and methods via resampling the minority class samples, research results demonstrate that the proposed method improved the accuracy and efficiency in coronary artery plaque segmentation while has a shorter training time, which lays the foundation for improving the efficiency and scientific nature of diagnosing related diseases in the future.

Three-dimensional (3D) deformable image registration plays a critical role in 3D medical image processing. This technique aligns images from different time points, modalities, or individuals in 3D space, enabling the comparison and fusion of anatomical or functional information. To simultaneously capture the local details of anatomical structures and the long-range dependencies in 3D medical images, while reducing the high costs of manual annotations, this paper proposes an unsupervised 3D medical image registration method based on shifted window Transformer and convolutional neural network (CNN), termed Swin Transformer-CNN-hybrid network (STCHnet). In the encoder part, STCHnet uses Swin Transformer and CNN to extract global and local features from 3D images, respectively, and optimizes feature representation through feature fusion. In the decoder part, STCHnet utilizes Swin Transformer to integrate information globally, and CNN to refine local details, reducing the complexity of the deformation field while maintaining registration accuracy. Experiments on the information extraction from images (IXI) and open access series of imaging studies (OASIS) datasets, along with qualitative and quantitative comparisons with existing registration methods, demonstrate that the proposed STCHnet outperforms baseline methods in terms of Dice similarity coefficient (DSC) and standard deviation of the log-Jacobian determinant (SDlogJ), achieving improved 3D medical image registration performance under unsupervised conditions.

For patients with MRI-negative drug-resistant epilepsy, noninvasive localization of targets for transcranial electrical stimulation (tES) remains a clinical challenge. This study proposes a novel target localization approach that integrates electroencephalogram source imaging, brain network analysis, and a neural computational model. We analyzed electrocorticography (ECoG) data from 12 patients, quantified the epileptogenicity of epileptic network nodes, and noninvasively located optimal stimulation targets. Three source imaging methods and two brain network reconstruction measures were compared for localization performance. Among four patients with good outcomes, the method accurately localized epileptogenic tissues in three. Results of tES simulation demonstrated that cathodal direct current stimulation of the target region significantly reduced the brain network's epileptogenicity. This study provides a noninvasive, quantifiable targeting strategy for tES therapy in epilepsy patients.

This study aims to investigate the diagnostic value of ¹⁸F-NaF micro PET/CT imaging in mouse models of acute gouty arthritis (AGA). Three male Balb/c mice were designated as the normal control group (Group A), and 18 male Balb/c mice were used to establish the AGA model (Group B). Group A and model groups B (B _1h, B _3h, B _6h, B _8h, B _12h, B _24h) underwent micro PET/CT imaging 40 minutes after injection of the radiotracer. All groups of mice underwent complete blood count, blood uric acid testing, and pathological biopsy of the ankle joint. The results showed that the counts of inflammatory cells in the blood routine of Group B were higher than those of Group A, and there were statistically significant differences between Group B _6h and B _8h compared to Group A ( P < 0.05). ¹⁸F-NaF micro PET/CT imaging revealed abnormal tracer accumulation in the right ankle joints of group B, but no bone destruction were observed on CT at the lesion sites; In group A, there was no obvious abnormal gathering of tracer in the left ankle joint. The ratios of maximum standardized uptake value (SUVmax) of the right and left ankle joints (R/L _SUVmax) in Group B were higher than those in Group A, and the difference between Group B _6h and Group A was statistically significant ( P < 0.05). The R/L _SUVmax ratios were positively correlated with the counts of white blood cells and neutrophils in the blood routine and microscopic inflammatory cells ( R = 0.79, P < 0.01; R = 0.72, P < 0.01; R = 0.79, P < 0.01, respectively). Overall, ¹⁸F-NaF micro PET/CT imaging can detect early bone metabolism changes in AGA and visually monitor its dynamic pathophysiological progression.

Artificial blood vessels are commonly applied in the treatment and reconstruction surgeries of cardiovascular diseases, which have a considerable clinical demand. Using a 6 mm diameter as a threshold, they are categorized into large- and small-diameter types. Calcification is one of the factors affecting whether artificial blood vessels can successfully be transplanted and function. The occurrence of calcification after implantation may lead to graft failure, particularly compromising the long-term patency of small-diameter grafts. Therefore, focusing on the research of calcification mechanisms and anti-calcification strategies for artificial blood vessels is of great importance. In this paper, we summarized the possible calcification mechanisms of artificial vessels and methods to prevent or delay post-implantation calcification, with the aim of providing insights for future research on anti-calcification artificial vessels.

Osteoarthritis is a common degenerative joint disease, which is often analyzed by X-ray images. However, if there is a lack of clinical experience when reading the films, it is easy to cause misdiagnosis. Although deep learning has made significant progress in the field of medical image processing, existing models still have limitations in capturing subtle lesion features such as joint spaces. This paper proposes an automatic diagnosis method for osteoarthritis based on the improved shifted windows Transformer (Swin Transformer) and graph convolutional network. By enhancing the modeling of joint space features and cross-layer feature fusion, it is expected to effectively improve the accuracy of early diagnosis of osteoarthritis. Firstly, this paper designs the shifted windows horizontal attention mechanism (SW-HAM), which can enhance the feature extraction ability in the horizontal direction. Secondly, the central-attention graphSAGE (CAG-SAGE) is introduced to conduct weighted aggregation of the feature information of the lesion area through the dynamic attention mechanism. Finally, cross-layer connection technology is utilized to achieve efficient fusion of multi-layer features. The experimental results show that the SW-HAM and CAG-SAGE modules and cross-layer connections significantly improve the model performance. The classification accuracy, recall rate, precision rate, F1 score, and area under the curve are 94.59%, 95.14%, 94.05%, 94.41%, and 96.30% respectively, all of which are superior to the classical network and existing methods. It provides a new and effective method for the classification and diagnosis of osteoarthritis.

Diabetic retinopathy (DR) and its complication, diabetic macular edema (DME), are major causes of visual impairment and even blindness. The occurrence of DR and DME is pathologically interconnected, and their clinical diagnoses are closely related. Joint learning can help improve the accuracy of diagnosis. This paper proposed a novel adaptive lesion-aware fusion network (ALFNet) to facilitate the joint grading of DR and DME. ALFNet employed DenseNet-121 as the backbone and incorporated an adaptive lesion attention module (ALAM) to capture the distinct lesion characteristics of DR and DME. A deep feature fusion module (DFFM) with a shared-parameter local attention mechanism was designed to learn the correlation between the two diseases. Furthermore, a four-branch composite loss function was introduced to enhance the network's multi-task learning capability. Experimental results demonstrated that ALFNet achieved superior joint grading performance on the Messidor dataset, with joint accuracy rates of 0.868 (DR 2 & DME 3), outperforming state-of-the-art methods. These results highlight the unique advantages of the proposed approach in the joint grading of DR and DME, thereby improving the efficiency and accuracy of clinical decision-making.

Compared with traditional orthopedic metal implants, magnesium alloys demonstrate superior mechanical strength and biocompatibility, while also exhibiting biodegradability, bone-inducing properties, and antibacterial activity. However, currently developed medical magnesium alloys suffer from insufficient corrosion resistance, failing to meet clinical requirements. Rare earth elements, which can effectively enhance critical properties like corrosion resistance in magnesium alloys, have become the core additive elements for developing new medical magnesium alloys. Consequently, the design, preparation, and clinical translation of rare earth magnesium alloys have garnered significant attention in recent years. This study aims to briefly explore the feasibility, challenges, and future prospects of biodegradable rare earth magnesium alloys as orthopedic internal fixation implants.

A certain degree of varus alignment is physiological in the native knee, and alignment strategies such as kinematic and functional alignment permit residual postoperative varus. However, identical total varus angles may result from varying combinations of femoral and tibial varus, whose biomechanical implications for implant loading and ligament stress remain unclear. This study aims to investigate the biomechanical effects of different femoral-tibial varus configurations in total knee arthroplasty (TKA). Using combined geometric modeling and finite element analysis, TKA models with different varus combinations were constructed to evaluate changes in limb moment arms, polyethylene insert stress, and ligament forces during static knee flexion (0°-90°). Results demonstrated that a higher proportion of femoral varus, under equivalent total varus and flexion angles, led to reduced maximum polyethylene stress and decreased tension in the medial collateral ligament (MCL) and anterolateral ligament complex (ALL). Knee flexion angle had a more significant impact on polyethylene stress than varus: stress increased by approximately 2.48 times at 90° flexion compared to 0°, whereas 12° varus increased stress by only approximately 14%. The ALL experienced the greatest tensile load during flexion, indicating a key stabilizing role. In conclusion, optimizing the combination of femoral and tibial varus may help redistribute loads and improve implant longevity. This study reveals, from a biomechanical perspective, how different varus configurations affect stress distribution in the prosthesis and surrounding soft tissues, suggesting that intraoperative osteotomy strategies should comprehensively consider the combined alignment of the femur and tibia.

Colorectal cancer typically originates from the malignant transformation of colonic polyps, making the automatic and accurate segmentation of colonic polyps crucial for clinical diagnosis. Deep learning techniques such as U-Net and Transformer can effectively extract implicit features from medical images, and thus have significant potential in colonic polyp image segmentation. This paper first introduced commonly used evaluation metrics and datasets for colonic polyp segmentation. It then reviewed the application of segmentation models based on U-Net, Transformer, and their hybrid approaches in this domain. Finally, it summarized the improvement methods, advantages, and limitations of polyp segmentation algorithms, discussed the challenges faced by U-Net- and Transformer-based models, and provided an outlook on future research directions in this field.