Digital Pathology
Digital pathology uses digitized microscopy images to analyze tissue samples, aiming to improve diagnostic accuracy and efficiency in healthcare. Current research focuses on developing and refining deep learning models, including transformers and convolutional neural networks, to address challenges like stain variation, limited annotated data, and the need for improved model interpretability and uncertainty quantification. These advancements are leading to more robust and efficient algorithms for tasks such as image segmentation, classification, and the integration of spatial transcriptomics data, ultimately impacting clinical workflows and potentially accelerating biomarker discovery.
Papers
End-to-end Learning for Image-based Detection of Molecular Alterations in Digital Pathology
Marvin Teichmann, Andre Aichert, Hanibal Bohnenberger, Philipp Ströbel, Tobias Heimann
InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation
Yi Lin, Zeyu Wang, Kwang-Ting Cheng, Hao Chen
Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology
Yunlong Zhang, Yuxuan Sun, Honglin Li, Sunyi Zheng, Chenglu Zhu, Lin Yang