SSCA-Net: Simultaneous Self- and Channel-Attention Neural Network for Multiscale Structure-Preserving Vessel Segmentation

Abstract

Vessel segmentation is a fundamental, yet not well-solved problem in medical image analysis, due to the complicated geometrical and topological structures of human vessels. Unlike existing rule- and conventional learning-based techniques, which hardly capture the location of tiny vessel structures and perceive their global spatial structures, we propose Simultaneous Self- and Channel-attention Neural Network (termed SSCA-Net) to solve the multiscale structure-preserving vessel segmentation (MSVS) problem. SSCA-Net differs from the conventional neural networks in modeling image global contexts, showing more power to understand the global semantic information by both self- and channel-attention (SCA) mechanism and offering high performance on segmenting vessels with multiscale structures (e.g., DSC: 96.21% and MIoU: 92.70% on the intracranial vessel dataset). Specifically, the SCA module is designed and embedded in the feature decoding stage to learn SCA features at different layers, in which the self-attention is used to obtain the position information of the feature itself, and the channel attention is designed to guide the shallow features to obtain global feature information. To evaluate the effectiveness of our SSCA-Net, we compare it with several state-of-the-art methods on three well-known vessel segmentation benchmark datasets. Qualitative and quantitative results demonstrate clear improvements of our method over the state-of-the-art in terms of preserving vessel details and global spatial structures.

PDC-Net: parallel dilated convolutional network with channel attention mechanism for pituitary adenoma segmentation

“…In the traditional convolutional neural network, continuous convolution and pooling operations will lead to a decrease in image resolution and the loss of spatial structure information, which has a great impact on the task of medical image segmentation, and directly lead to the blurred boundary and pixel classification errors after segmentation. With the appearance of atrous spatial pyramid pooling (ASSP) structure (Chen et al, 2018b), the above problems can be solved well, and many optimized models are proposed continuously (Ni et al, 2021;Xie et al, 2021;Lan et al, 2022;Liang et al, 2022). By connecting convolution layers with different expansion rates in parallel, ASSP can alleviate the problem of spatial information loss caused by Frontiers in Physiology frontiersin.org downsampling, and enlarge the receptive field without increasing the amount of computation, to obtain more regional information.…”

Spatial and Spectral-Channel Attention Network for Denoising on Hyperspectral Remote Sensing Image

“…Just like the mentioned points in Section 2.2, to take both traditional NSS and GCS priors into account in the network, we introduce two attention mechanisms, i.e., spatial attention and spectral attention [55][56][57][58] which could approximate the NSS and GCS characteristics in a sense, respectively. Specifically, NSS across space is to investigate the spatial similarity between image patches (even pixels).…”