DA-SSL: self-supervised domain adaptor to leverage foundational models in turbt histopathology slides

TL;DR

This paper introduces DA-SSL, a lightweight self-supervised domain adaptor that improves foundational model performance on TURBT histopathology slides by addressing domain shifts without fine-tuning the entire model.

Contribution

The study proposes a novel domain-adaptive self-supervised adaptor (DA-SSL) that realigns pretrained models to specific histopathology domains, enhancing performance without full model fine-tuning.

Findings

DA-SSL achieved an AUC of 0.77 in cross-validation.

External test accuracy was 0.84 with sensitivity 0.71 and specificity 0.91.

Lightweight domain adaptation improves model performance on challenging histopathology tasks.

Abstract

Recent deep learning frameworks in histopathology, particularly multiple instance learning (MIL) combined with pathology foundational models (PFMs), have shown strong performance. However, PFMs exhibit limitations on certain cancer or specimen types due to domain shifts - these cancer types were rarely used for pretraining or specimens contain tissue-based artifacts rarely seen within the pretraining population. Such is the case for transurethral resection of bladder tumor (TURBT), which are essential for diagnosing muscle-invasive bladder cancer (MIBC), but contain fragmented tissue chips and electrocautery artifacts and were not widely used in publicly available PFMs. To address this, we propose a simple yet effective domain-adaptive self-supervised adaptor (DA-SSL) that realigns pretrained PFM features to the TURBT domain without fine-tuning the foundational model itself. We pilot this framework for predicting treatment response in TURBT, where histomorphological features are currently underutilized and identifying patients who will benefit from neoadjuvant chemotherapy (NAC) is challenging. In our multi-center study, DA-SSL achieved an AUC of 0.77+/-0.04 in five-fold cross-validation and an external test accuracy of 0.84, sensitivity of 0.71, and specificity of 0.91 using majority voting. Our results demonstrate that lightweight domain adaptation with self-supervision can effectively enhance PFM-based MIL pipelines for clinically challenging histopathology tasks. Code is Available at https://github.com/zhanghaoyue/DA_SSL_TURBT.