Prompt-Guided Adaptive Model Transformation for Whole Slide Image Classification

arXiv:2403.12537v1 Announce Type: new
Abstract: Multiple instance learning (MIL) has emerged as a popular method for classifying histopathology whole slide images (WSIs). Existing approaches typically rely on frozen pre-trained models to extract instance features, neglecting the substantial domain shift between pre-training natural and histopathological images. To address this issue, we propose PAMT, a novel Prompt-guided Adaptive Model Transformation framework that enhances MIL classification performance by seamlessly adapting pre-trained models to the specific characteristics of histopathology data. To capture the intricate …

abstract arxiv classification cs.cv domain extract features image images instance issue mil multiple natural popular pre-trained models pre-training prompt shift training transformation type