Dual-branch Transformer for semi-supervised medical image segmentation.

PURPOSE: In recent years, the use of deep learning for medical image segmentation has become a popular trend, but its development also faces some challenges. Firstly, due to the specialized nature of medical data, precise annotation is time-consuming and labor-intensive. Training neural networks effectively with limited labeled data is a significant challenge in medical image analysis. Secondly, convolutional neural networks commonly used for medical image segmentation research often focus on local features in images. However, the recognition of complex anatomical structures or irregular lesions often requires the assistance of both local and global information, which has led to a bottleneck in its development. Addressing these two issues, in this paper, we propose a novel network architecture. METHODS: We integrate a shift window mechanism to learn more comprehensive semantic information and employ a semi-supervised learning strategy by incorporating a flexible amount of unlabeled data. Specifically, a typical U-shaped encoder-decoder structure is applied to obtain rich feature maps. Each encoder is designed as a dual-branch structure, containing Swin modules equipped with windows of different size to capture features of multiple scales. To effectively utilize unlabeled data, a level set function is introduced to establish consistency between the function regression and pixel classification. RESULTS: We conducted experiments on the COVID-19 CT dataset and DRIVE dataset and compared our approach with various semi-supervised and fully supervised learning models. On the COVID-19 CT dataset, we achieved a segmentation accuracy of up to 74.56%. Our segmentation accuracy on the DRIVE dataset was 79.79%. CONCLUSIONS: The results demonstrate the outstanding performance of our method on several commonly used evaluation metrics. The high segmentation accuracy of our model demonstrates that utilizing Swin modules with different window sizes can enhance the feature extraction capability of the model, and the level set function can enable semi-supervised models to more effectively utilize unlabeled data. This provides meaningful insights for the application of deep learning in medical image segmentation. Our code will be released once the manuscript is accepted for publication.

Multi-Sequence MRI Registration of Atherosclerotic Carotid Arteries Based on Cross-Scale Siamese Network.

Cardiovascular disease (CVD) is a common disease with high mortality rate, and carotid atherosclerosis (CAS) is one of the leading causes of cardiovascular disease. Multisequence carotid MRI can not only identify carotid atherosclerotic plaque constituents with high sensitivity and specificity, but also obtain different morphological features, which can effectively help doctors improve the accuracy of diagnosis. However, it is difficult to evaluate the accurate evolution of local changes in carotid atherosclerosis in multi-sequence MRI due to the inconsistent parameters of different sequence images and the geometric space mismatch caused by the motion deviation of tissues and organs. To solve these problems, we propose a cross-scale multi-modal image registration method based on the Siamese U-Net. The network uses sub-networks with image inputs of different sizes to extract various features, and a special padding module is designed to make the network available for training on cross-scale features. In addition, to improve the registration performance, a multi-scale loss function under Gaussian smoothing is applied for optimization. For the experiments, we have collected a multi-sequence MRI image dataset from 11 patients with carotid atherosclerosis for a retrospective study. We evaluate our overall architectures by cross-validation on our carotid dataset. The experimental results show that our method can generate precise and reliable results with cross-scale multi-sequence inputs and the registration accuracy can be greatly improved by using the Gaussian smoothing loss function. The DSC of our Siamese structure can reach 84.1% on the carotid data set with cross-size input. With the use of GDSC loss, the average DSC can be improved by 5.23%, while the average distance between fixed landmarks and moving landmarks can be decreased by 6.46%.Our code is made publicly available at: https://github.com/MingHan98/Cross-scale-Siamese-Unet.