Pancreatic cancer pathology image segmentation with channel and spatial long-range dependencies

• Published in: Computers in biology and medicine Vol. 169; p. 107844
• Main Authors: Chen, Zhao-Min, Liao, Yifan, Zhou, Xingjian, Yu, Wenyao, Zhang, Guodao, Ge, Yisu, Ke, Tan, Shi, Keqing
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.02.2024; Elsevier Limited
• Subjects: Cancer; Channel and spatial self-attention; Datasets; Deep learning; Entropy; Humans; Image processing; Image Processing, Computer-Assisted; Image segmentation; Internal Medicine; Long-range dependencies; Long-tailed distribution; Medical imaging; Modules; Other; Pancreatic cancer; Pancreatic cancer pathology image segmentation; Pancreatic Neoplasms; Pathology; Receptive field; Window shift; Channel and spatial self-attention; Long-tailed distribution; Window shift; Pancreatic cancer pathology image segmentation; Long-range dependencies
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107844

Based on deep learning, pancreatic cancer pathology image segmentation technology effectively assists pathologists in achieving improved treatment outcomes. However, compared to traditional image segmentation tasks, the large size of tissues in pathology images requires a larger receptive field. While methods based on dilated convolutions or attention mechanisms can enhance the receptive field, they cannot capture long-range feature dependencies. Directly applying self-attention mechanisms to capture long-range dependencies results in intolerable computational complexity. To address these challenges, we introduce a channel and spatial self-attention (CS) Module designed for efficiently capturing both channel and spatial long-range feature dependencies in pancreatic cancer pathological images. Specifically, the channel and spatial self-attention module consists of an adaptive channel self-attention module and a window-shift spatial self-attention module. The adaptive channel self-attention module adaptively pools features to a fixed size to capture long-range feature dependencies. While the window-shift spatial self-attention module captures spatial long-range dependencies in a window-based manner. Additionally, we propose a re-weighted cross-entropy loss to mitigate the impact of long-tail distribution on performance. Our proposed method surpasses state-of-the-art on both our Pancreatic Cancer Pathology Image (PCPI) dataset and the GlaS challenge dataset. The mDice and mIoU have achieved 73.93% and 59.42% in our PCPI dataset. •Presenting introduce a channel and spatial self-attention module to efficiently captures long-range dependencies.•Presenting a re-weighted cross-entropy loss function that balances the learning of various tissue categories.•Collecting and annotating a dataset of pancreatic cancer pathology images. On this dataset, our method achieves state-of-the-art performance.