Boundary aware microscopic hyperspectral pathology image segmentation network guided by information entropy weight.

Introduction: Accurate segmentation of lesion tissues in medical microscopic hyperspectral pathological images is crucial for enhancing early tumor diagnosis and improving patient prognosis. However, the complex structure and indistinct boundaries of lesion tissues present significant challenges in achieving precise segmentation. Methods: To address these challenges, we propose a novel method named BE-Net. It employs multi-scale strategy and edge operators to capture fine edge details, while incorporating information entropy to construct attention mechanisms that further strengthen the representation of relevant features. Specifically, we first propose a Laplacian of Gaussian operator convolution boundary feature extraction block, which encodes feature gradient information through the improved edge detection operators and emphasizes relevant boundary channel weights based on channel information entropy weighting. We further designed a grouped multi-scale edge feature extraction module to optimize the fusion process between the encoder and decoder, with the goal of optimize boundary details and emphasizing relevant channel representations. Finally, we propose a multi-scale spatial boundary feature extraction block to guide the model in emphasizing the most important spatial locations and boundary regions. Result: We evaluate BE-Net on medical microscopic hyperspectral pathological image datasets of gastric intraepithelial neoplasia and gastric mucosal intestinal metaplasia. Experimental results demonstrate that BE-Net outperforms other state-of-the-art segmentation methods in terms of accuracy and boundary preservation. Discussion: This advance has significant implications for the field of MHSIs segmentation. Our code is freely available at https://github.com/sharycao/BE-NET.