Recently, deep learning has made an important contribution to the development of medical image segmentation, such as U-Net and its variants. However, the existing methods based deep learning perform poorly in the small structures, structure continuity and efficiency. In this paper, we present EU-Net, an efficient and more powerful U-Net-like architecture for medical image segmentation, which consists of a lightweight encoder and decoder that are connected through dense skip-connection. To further improve the robustness of the EU-Net, chain EU-Net is proposed. Chain EU-Net is based on a streamlined architecture that uses multiple EU-Net to build light weight deep neural networks by dense skip-connection. We evaluate the EU-Net and chain EU-Net on three typical medical image segmentation tasks: GLAS (Gland segmentation) dataset, RITE (Retinal Images Vessel Tree Extraction) dataset and LiTS (Liver Tumor Segmentation Challenge) dataset. In addition, we used PUFH (Peking University First Hospital) dataset. Experimental results show that the proposed methods achieve state-of-the-art performance with very few parameters.

Point cloud registration is a fundamental problem in computer vision and 3D computing, aiming to align point cloud data from different sensors or viewpoints into a unified coordinate system. In recent years, the rapid development of RGB-D sensor technology has greatly facilitated the acquisition of RGB-D data. In previous unsupervised point cloud registration methods based on RGB-D data, there has often been an overemphasis on matching local features, while the potential value of global information has been overlooked, thus limiting the improvement in registration performance. To address this issue, this paper proposes a self-attention-based global information attention module, which learns the global context of fused RGB-D features and effectively integrates global information into each individual feature. Furthermore, this paper introduces alternating self-attention and cross-attention layers, enabling the final feature fusion to achieve a broader global receptive field, thereby facilitating more precise matching relationships. We conduct extensive experiments on the ScanNet and 3DMatch datasets, and the results show that, compared to the previous state-of-the-art methods, our approach reduces the average rotation error by 26.9% and 32% on the ScanNet and 3DMatch datasets, respectively. Our method also achieves state-of-the-art performance on other key metrics.