Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction
This work addresses the challenge of efficiently predicting prognosis for rare cancers in medical imaging by enabling knowledge transfer across cancer types, representing a foundational shift in the field.
The paper tackles the problem of scaling cancer prognosis prediction from Whole-Slide Images (WSIs) beyond cancer-specific models by introducing CROPKT, a systematic study on cross-cancer knowledge transfer, which includes curating a large multi-cancer dataset (UNI2-h-DSS) and proposing a routing-based baseline (ROUPKT) that efficiently utilizes transferred knowledge, though specific performance numbers are not provided.
Whole-Slide Image (WSI) is an important tool for estimating cancer prognosis. Current studies generally follow a conventional cancer-specific paradigm where one cancer corresponds to one model. However, it naturally struggles to scale to rare tumors and cannot utilize the knowledge of other cancers. Although a multi-task learning-like framework has been studied recently, it usually has high demands on computational resources and needs considerable costs in iterative training on ultra-large multi-cancer WSI datasets. To this end, this paper makes a paradigm shift to knowledge transfer and presents the first preliminary yet systematic study on cross-cancer prognosis knowledge transfer in WSIs, called CROPKT. It has three major parts: (i) we curate a large dataset (UNI2-h-DSS) with 26 cancers and use it to measure the transferability of WSI-based prognostic knowledge across different cancers (including rare tumors); (ii) beyond a simple evaluation merely for benchmark, we design a range of experiments to gain deeper insights into the underlying mechanism of transferability; (iii) we further show the utility of cross-cancer knowledge transfer, by proposing a routing-based baseline approach (ROUPKT) that could often efficiently utilize the knowledge transferred from off-the-shelf models of other cancers. We hope CROPKT could serve as an inception and lay the foundation for this nascent paradigm, i.e., WSI-based prognosis prediction with cross-cancer knowledge transfer. Our source code is available at https://github.com/liupei101/CROPKT.