The quantitative analysis of Programmed death-ligand 1 (PD-L1) via Immunohistochemical (IHC) plays a crucial role in guiding immunotherapy. However, IHC faces challenges, including high costs, time consumption and result variability. Conversely, Hematoxylin-Eosin (H&E) staining offers cost-effectiveness, speed, and stable results. Nonetheless, H&E staining, which solely visualizes cellular morphological features, lacks clinical applicability in detecting biomarker expressions like PD-L1. Substituting H&E staining for IHC in determining PD-L1 status is a clinically significant and challenging task. Motivated by above observations, we propose a Multi-Task supervised learning (MTSL)-based connectivity region attention network (MCRANet) for PD-L1 status segmentation in H&E stained images. To reduce interference from non-tumor areas, the MTSL-based region attention is proposed to enhances the network's capability to distinguish between tumor and non-tumor regions. Consequently, this augmentation further improves the network's segmentation efficacy for PD-L1 positive and negative regions. Furthermore, the PD-L1 expression regions demonstrate interconnection throughout the tissue section. Leveraging this topological prior knowledge, we integrate a connectivity modeling module (CM module) within the MTSL-based region attention module (MRA module) to enhance the precision of MTSL-based region attention localization. This integration further improves the structural similarity between the segmentation results and the ground truth. Extensive visual and quantitative results demonstrate that our supervised-learning-guided MRA module produces more interpretable attention and the introduced CM module provides accurate positional attention to the MRA module. Compared to other state-of-the-art networks, MCRANet exhibits superior segmentation performance with a dice similarity coefficient (DSC) of 79.6 % on the lung squamous cell carcinoma (LUSC) PD-L1 status dataset.
Read full abstract