Effective integration of object boundaries and regions for improving the performance of medical image segmentation by using two cascaded networks

TSCA-Net: Transformer based spatial-channel attention segmentation network for medical images

Deep learning architectures based on convolutional neural network (CNN) and Transformer have achieved great success in medical image segmentation. Models based on the encoder-decoder framework like U-Net have been successfully employed in many realistic scenarios. However, due to the low contrast between object and background, various shapes and scales of objects, and complex background in medical images, it is difficult to locate targets and obtain better segmentation performance by extracting effective information from images. In this paper, an encoder-decoder architecture based on spatial and channel attention modules built by Transformer is proposed for medical image segmentation. Concretely, spatial and channel attention modules based on Transformer are utilized to extract spatial and channel global complementary information at different layers in U-shape network, which is beneficial to learn the detail features in different scales. To fuse better spatial and channel information from Transformer features, a spatial and channel feature fusion block is designed for the decoder. The proposed network inherits the advantages of both CNN and Transformer with the local feature representation and long-range dependency for medical images. Qualitative and quantitative experiments demonstrate that the proposed method outperforms against eight state-of-the-art segmentation methods on five publicly medical image datasets including different modalities, such as 80.23% and 93.56% Dice value, 67.13% and 88.94% Intersection over Union (IoU) value on the Multi-organ Nucleus Segmentation (MoNuSeg) and Combined Healthy Abdominal Organ Segmentation with Computed Tomography scans (CHAOS-CT) datasets.

TdDS-UNet: top-down deeply supervised U-Net for the delineation of 3D colorectal cancer

Automatically delineating colorectal cancers with fuzzy boundaries from 3D images is a challenging task, but the problem of fuzzy boundary delineation in existing deep learning-based methods have not been investigated in depth. Here, an encoder-decoder-based U-shaped network (U-Net) based on top-down deep supervision (TdDS) was designed to accurately and automatically delineate the fuzzy boundaries of colorectal cancer. TdDS refines the semantic targets of the upper and lower stages by mapping ground truths that are more consistent with the stage properties than upsampling deep supervision. This stage-specific approach can guide the model to learn a coarse-to-fine delineation process and improve the delineation accuracy of fuzzy boundaries by gradually shrinking the boundaries. Experimental results showed that TdDS is more customizable and plays a role similar to the attentional mechanism, and it can further improve the capability of the model to delineate colorectal cancer contours. A total of 103, 12, and 29 3D pelvic magnetic resonance imaging volumes were used for training, validation, and testing, respectively. The comparative results indicate that the proposed method exhibits the best comprehensive performance, with a dice similarity coefficient (DSC) of 0.805 ± 0.053 and a hausdorff distance (HD) of 9.28 ± 5.14 voxels. In the delineation performance analysis section also showed that 44.49% of the delineation results are satisfactory and do not require revisions. This study can provide new technical support for the delineation of 3D colorectal cancer. Our method is open source, and the code is available athttps://github.com/odindis/TdDS/tree/main.

CASF-Net: Cross-attention and cross-scale fusion network for medical image segmentation

BACKGROUND

Automatic segmentation of medical images has progressed greatly owing to the development of convolutional neural networks (CNNs). However, there are two uncertainties with current approaches based on convolutional operations: (1) how to eliminate the general limitations that CNNs lack the ability of modeling long-range dependencies and global contextual interactions, and (2) how to efficiently discover and integrate global and local features that are implied in the image. Notably, these two problems are interconnected, yet previous approaches mainly focus on the first problem and ignore the importance of information integration.

METHODS

In this paper, we propose a novel cross-attention and cross-scale fusion network (CASF-Net), which aims to explicitly tap the potential of dual-branch networks and fully integrate the coarse and fine-grained feature representations. Specifically, the well-designed dual-branch encoder hammers at modeling non-local dependencies and multi-scale contexts, significantly improving the quality of semantic segmentation. Moreover, the proposed cross-attention and cross-scale module efficiently perform multi-scale information fusion, being capable of further exploring the long-range contextual information.

RESULTS

Extensive experiments conducted on three different types of medical image segmentation tasks demonstrate the state-of-the-art performance of our proposed method both visually and numerically.

CONCLUSIONS

This paper assembles the feature representation capabilities of CNN and transformer and proposes cross-attention and cross-scale fusion algorithms. The promising results show new possibilities of using cross-fusion mechanisms in more downstream medical image tasks.