Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification

TL;DR

This paper demonstrates that domain-specific pre-training significantly enhances confidence and accuracy in classifying glioma subtypes from Whole Slide Images, outperforming generic pre-trained models.

Contribution

It shows the impact of domain-specific pre-training on WSI classification, achieving state-of-the-art results with models like CLAM and TransMIL.

Findings

Domain-specific pre-training increases model confidence.

Achieved new state-of-the-art in glioma subtype classification.

Models show high potential for clinical application.

Abstract

Whole Slide Images (WSIs) or histopathology images are used in digital pathology. WSIs pose great challenges to deep learning models for clinical diagnosis, owing to their size and lack of pixel-level annotations. With the recent advancements in computational pathology, newer multiple-instance learning-based models have been proposed. Multiple-instance learning for WSIs necessitates creating patches and uses the encoding of these patches for diagnosis. These models use generic pre-trained models (ResNet-50 pre-trained on ImageNet) for patch encoding. The recently proposed KimiaNet, a DenseNet121 model pre-trained on TCGA slides, is a domain-specific pre-trained model. This paper shows the effect of domain-specific pre-training on WSI classification. To investigate the effect of domain-specific pre-training, we considered the current state-of-the-art multiple-instance learning models, 1) CLAM, an attention-based model, and 2) TransMIL, a self-attention-based model, and evaluated the models' confidence and predictive performance in detecting primary brain tumors - gliomas. Domain-specific pre-training improves the confidence of the models and also achieves a new state-of-the-art performance of WSI-based glioma subtype classification, showing a high clinical applicability in assisting glioma diagnosis. We will publicly share our code and experimental results at https://github.com/soham-chitnis10/WSI-domain-specific.