Multi-Scale Cross-Dimensional Attention Network for Gland Segmentation
- 19 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 3365-3369
Abstract
Gland lesions affect a large global population. Accurately segmenting surface structures is crucial for assisting in the diagnosis of these diseases. In this direction, we investigate two key issues: 1) How to accurately segment gland morphology and irregular boundaries and 2) How to distinguish gland internal heterogeneity and its similarity to the background. The main results are that 1) parallel multi-scale attention (PMA) smooths the segmentation of blurred boundaries of varying sizes and improves detail accuracy. 2) Cross-dimensional attention (CDA) models the dependencies between gland channels and spatial dimensions to enhance the understanding of spatial information both inside and outside the gland, thereby more accurately distinguishing the gland from the background. Per the main results, we propose a multi-scale cross-dimensional attention network (MCANet) for gland segmentation. Extensive experiments on six real-world datasets demonstrate the superior performance of our method in gland segmentation. The source code is available at https://github.com/yuchaozhi/MCANet.Keywords
Funding Information
- National Natural Science Foundation of China (62462021)
- Philosophy and Social Sciences Planning Project of Zhejiang Province (25JCXK006YB)
- Hainan Provincial Natural Science Foundation of China (625RC716)
- Basic and Applied Basic Research Foundation of Guangdong Province (2025A1515010197)
- Hainan Province Higher Education Teaching Reform Project (HNJG2024ZD-16)
- Hainan Provincial Innovation Research Projects (Qhys2024-258)
This publication has 40 references indexed in Scilit:
- Lightweight transformer-driven multi-scale trapezoidal attention network for saliency detectionEngineering Applications of Artificial Intelligence, 2025
- Segmentation of IC Images in Integrated Circuit Reverse Engineering Using EfficientNet Encoder Based on U‐Net++ ArchitectureInternational Journal of Circuit Theory and Applications, 2025
- Multi-scale morphology-aided deep medical image segmentationEngineering Applications of Artificial Intelligence, 2024
- A comprehensive assessment of artificial intelligence applications for cancer diagnosisArtificial Intelligence Review, 2024
- Diffusion model-based text-guided enhancement network for medical image segmentationExpert Systems with Applications, 2024
- MMUNet: Morphological feature enhancement network for colon cancer segmentation in pathological imagesBiomedical Signal Processing and Control, 2024
- Deep semi-supervised learning for medical image segmentation: A reviewExpert Systems with Applications, 2024
- Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentationExpert Systems with Applications, 2023
- Nuclei and glands instance segmentation in histology images: a narrative reviewArtificial Intelligence Review, 2022
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015