Multi-layer pseudo-supervision for histopathology tissue semantic segmentation using patch-level classification labels

•We present a tissue semantic segmentation model for histopathology images using only patch-level classification labels, which greatly saves the annotation time for pathologists.•Multi-layer pseudo-supervision with progressive dropout attention is proposed to reduce the information gap between patch-level and pixel-level labels. And a classification gate mechanism is introduced to reduce the false-positive rate.•Our proposed model achieves state-of-the-art performance comparing with weakly-supervised semantic segmentation models on two datasets, as well as a comparable performance with fully-supervised baseline.•The first LUAD dataset is released for weakly-supervised tissue semantic segmentation. [Display omitted] Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the giga-pixel whole slide images is extremely expensive and time-consuming. In this paper, we use only patch-level classification labels to achieve tissue semantic segmentation on histopathology images, finally reducing the annotation efforts. We propose a two-step model including a classification and a segmentation phases. In the classification phase, we propose a CAM-based model to generate pseudo masks by patch-level labels. In the segmentation phase, we achieve tissue semantic segmentation by our propose Multi-Layer Pseudo-Supervision. Several technical novelties have been proposed to reduce the information gap between pixel-level and patch-level annotations. As a part of this paper, we introduce a new weakly-supervised semantic segmentation (WSSS) dataset for lung adenocarcinoma (LUAD-HistoSeg). We conduct several experiments to evaluate our proposed model on two datasets. Our proposed model outperforms five state-of-the-art WSSS approaches. Note that we can achieve comparable quantitative and qualitative results with the fully-supervised model, with only around a 2% gap for MIoU and FwIoU. By comparing with manual labeling on a randomly sampled 100 patches dataset, patch-level labeling can greatly reduce the annotation time from hours to minutes. The source code and the released datasets are available at: https://github.com/ChuHan89/WSSS-Tissue.