Histopathology Whole Slide Image
Histopathology whole slide image (WSI) analysis involves classifying and analyzing gigapixel images of tissue samples for medical diagnosis, a task complicated by image size and annotation scarcity. Current research focuses on developing advanced deep learning models, including transformers and graph neural networks, often incorporating multiple instance learning (MIL) to handle the inherent heterogeneity of WSIs and improve classification accuracy and interpretability. These advancements aim to improve diagnostic accuracy and efficiency for pathologists, potentially leading to better patient care and facilitating telepathology in resource-limited settings.
Papers
Kernel Attention Transformer (KAT) for Histopathology Whole Slide Image Classification
Yushan Zheng, Jun Li, Jun Shi, Fengying Xie, Zhiguo Jiang
Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images Analysis
Jun Li, Yushan Zheng, Kun Wu, Jun Shi, Fengying Xie, Zhiguo Jiang