Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis

TL;DR

This paper introduces eWSI, a method combining parameter-efficient fine-tuning with multiple instance learning, enabling end-to-end training of whole slide images efficiently and effectively without extensive domain-specific pre-training.

Contribution

eWSI is a novel integration of PEFT and MIL that reduces computational costs and enhances task-specific learning in WSI analysis, outperforming traditional pre-training approaches.

Findings

eWSI achieves comparable or better performance with ImageNet features.

eWSI improves classification when using in-domain feature extractors.

eWSI reduces the need for extensive domain-specific pre-training.

Abstract

Computational methods on analyzing Whole Slide Images (WSIs) enable early diagnosis and treatments by supporting pathologists in detection and classification of tumors. However, the extremely high resolution of WSIs makes end-to-end training impractical compared to typical image analysis tasks. To address this, most approaches use pre-trained feature extractors to obtain fixed representations of whole slides, which are then combined with Multiple Instance Learning (MIL) for downstream tasks. These feature extractors are typically pre-trained on natural image datasets such as ImageNet, which fail to capture domain-specific characteristics. Although domain-specific pre-training on histopathology data yields more relevant feature representations, it remains computationally expensive and fail to capture task-specific characteristics within the domain. To address the computational cost and lack of task-specificity in domain-specific pre-training, we propose EfficientWSI (eWSI), a careful integration of Parameter-Efficient-Fine-Tuning (PEFT) and Multiple Instance Learning (MIL) that enables end-to-end training on WSI tasks. We evaluate eWSI on seven WSI-level tasks over Camelyon16, TCGA and BRACS datasets. Our results show that eWSI when applied with ImageNet feature extractors yields strong classification performance, matching or outperforming MILs with in-domain feature extractors, alleviating the need for extensive in-domain pre-training. Furthermore, when eWSI is applied with in-domain feature extractors, it further improves classification performance in most cases, demonstrating its ability to capture task-specific information where beneficial. Our findings suggest that eWSI provides a task-targeted, computationally efficient path for WSI tasks, offering a promising direction for task-specific learning in computational pathology.