WSSS-CRAM: precise segmentation of histopathological images via class region activation mapping

• Published in: Frontiers in microbiology Vol. 15; p. 1483052
• Main Authors: Pan, Ningning, Mi, Xiangyue, Li, Hongzhuang, Ge, Xinting, Sui, Xiaodan, Jiang, Yanyun
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 03.10.2024
• Subjects: category-specific image activation maps; deep learning; histopathological image; Microbiology; precise semantic segmentation; weakly-supervised method; deep learning; category-specific image activation maps; precise semantic segmentation; weakly-supervised method; histopathological image
• ISSN: 1664-302X; 1664-302X
• DOI: 10.3389/fmicb.2024.1483052

Fast, accurate, and automatic analysis of histopathological images using digital image processing and deep learning technology is a necessary task. Conventional histopathological image analysis algorithms require the manual design of features, while deep learning methods can achieve fast prediction and accurate analysis, but rely on the drive of a large amount of labeled data. In this work, we introduce WSSS-CRAM a weakly-supervised semantic segmentation that can obtain detailed pixel-level labels from image-level annotated data. Specifically, we use a discriminative activation strategy to generate category-specific image activation maps via class labels. The category-specific activation maps are then post-processed using conditional random fields to obtain reliable regions that are directly used as ground-truth labels for the segmentation branch. Critically, the two steps of the pseudo-label acquisition and training segmentation model are integrated into an end-to-end model for joint training in this method. Through quantitative evaluation and visualization results, we demonstrate that the framework can predict pixel-level labels from image-level labels, and also perform well when testing images without image-level annotations. Future, we consider extending the algorithm to different pathological datasets and types of tissue images to validate its generalization capability.