Transformers in pathological image analysis: A survey

Abstract

With the advancements of artificial intelligence, deep learning has emerged as the predominant approach in computational pathology. It is dedicated to automatically analyzing the intricate phenotype information embedded in various pathological images, with the goal of delivering more precise diagnoses, prognoses, and treatment recommendations for cancer patients. As the latest breakthrough in deep learning technology, Transformers are gaining traction in the realm of pathological image analysis by harnessing self-attention mechanisms to capture global information. Consequently, this study presents a comprehensive review of state-of-the-art models leveraging Transformers, applied across tasks such as classification, segmentation, and survival analysis in pathological image analysis. Initially, we delineate the concept and key components of Transformers, followed by a survey of their recent applications in pathology. These applications encompass pathological image classification, segmentation, lesion detection and localization, as well as the utilization of specific Transformer architectures for patient survival analysis. Subsequently, we delve into the challenges encountered in employing Transformers for pathological image analysis and speculate on future developmental trajectories. Our aim is to furnish readers with an exhaustive roadmap to deepen their comprehension of Transformer applications in pathology, thereby fostering the advancement of more sophisticated technologies and enabling more precise diagnoses and treatment strategies for cancer patients.