DA-SSL: self-supervised domain adaptor to leverage foundational models in turbt histopathology slides
This addresses the challenge of leveraging PFMs for clinically difficult histopathology tasks like predicting neoadjuvant chemotherapy benefit in bladder cancer, where domain shifts limit performance, but it is incremental as it adapts existing methods to a specific domain.
The paper tackled the problem of domain shifts in pathology foundational models (PFMs) for transurethral resection of bladder tumor (TURBT) histopathology, which contain artifacts and were underrepresented in pretraining, by proposing a domain-adaptive self-supervised adaptor (DA-SSL) that realigns PFM features without fine-tuning, achieving an AUC of 0.77±0.04 in cross-validation and external test accuracy of 0.84 with sensitivity of 0.71 and specificity of 0.91 for predicting treatment response.
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.