The effective segmentation of esophagus and esophageal cancer from Computed Tomography (CT) images can meaningfully assist doctors in the diagnosis and treatment of esophageal cancer patients. However, problems such as the small proportion of the esophageal region in CT images and the irregular shape of the esophagus will make the diagnosis difficult. In practical applications, not all esophagus and esophageal cancer morphology can be included in the training set, so the generalization ability of the model is very important. These are the difficulties in segmenting the esophagus and esophageal cancer. Since some adjacent tissues and organs of the esophagus are visually close to the esophagus and esophageal cancer, how to ensure that the network can extract effective distinguishing features has become the focus of research. In this paper, a novel U-Net structure — Channel-attention U-Net is proposed to segment esophagus and esophageal cancer from CT slices. This novel network combines a Channel Attention Module (CAM) that can distinguish the esophagus and surrounding tissues by emphasizing and inhibiting channel feature and Cross-level Feature Fusion Module (CFFM) which is utilized to strengthen the generalization ability of the network by using high-level features to weight low-level features. Because the high-level features represent specific organizational information, and the low-level features represent the characteristics of detailed information such as edges and contours, the network can learn specific detailed features of a definite organization. In addition, to locate the esophageal region better, a 3D semi-automatic method for segmenting esophagus and esophageal cancer is proposed. The proposed network is trained using 46,400 CT pictures as the training set and divides 11,600 CT images from the dataset at a ratio of 0.2 as the validation set. Finally, 7,250 CT images were used as the test set to test the performance of the network. The experimental results show that the IoU value of our network can reach 0.625, the dice value is 0.732 and the Hausdorff distance is 3.193.

Electroencephalogram (EEG) technology, particularly high-density EEG (HD EEG) devices, are widely used in fields such as neuroscience. HD EEG devices improve the spatial resolution of EEG by placing more electrodes on the scalp, which meet the requirements of clinical diagnostic applications such as epilepsy focus localization. However, this technique faces challenges, such as high acquisition costs and limited usage scenarios. In this paper, spatio-temporal adaptive diffusion models (STAD) are proposed to pioneer the use of diffusion models for achieving spatial SR reconstruction from low-resolution (LR, 64 channels or fewer) EEG to high-resolution (HR, 256 channels) EEG. Specifically, a spatio-temporal condition module is designed to extract the spatio-temporal features of LR EEG, which then used as conditional inputs to direct the reverse denoising process. Additionally, a multi-scale Transformer denoising module is constructed to leverage multi-scale convolution blocks and cross-attention-based diffusion Transformer blocks for conditional guidance to generate subject-adaptive SR EEG. Experimental results demonstrate that the STAD significantly enhances the spatial resolution of LR EEG and quantitatively outperforms existing methods. Furthermore, STAD demonstrate their value by applying synthetic SR EEG to classification and source localization tasks, indicating their potential to Substantially boost the spatial resolution of EEG.

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to represent novel classes. The correlation-based methods lack the ability to consider interaction of the two subspace matching scores due to the inherent nature of the real-valued 2D convolutions. In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra. Specifically, our QCLNet is formulated as a hyper-complex valued network and represents correlation tensors in the quaternion domain, which uses quaternion-valued convolution to explore the external relations of query subspace when considering the hidden relationship of the support sub-dimension in the quaternion space. Extensive experiments on the PASCAL-5 ⁱ and COCO-20 ⁱ datasets demonstrate that our method outperforms the existing state-of-the-art methods effectively.