Impact of variation in tissue staining and scanning devices on performance of pan-cancer AI models: a study of sarcoma and their mimics
Chai, B.; Chen, J.; Cool, P.; Oumlil, F.; Tollitt, A.; Steiner, D. F.; Chakraborti, T.; Flanagan, A. M.
Show abstract
Histopathological analysis is considered the gold standard for the diagnosis and prognostication of cancer. Recent advances in AI, driven by large-scale digitisation and pan-cancer foundation models, are opening new opportunities for clinical integration. However, it remains unclear how robust these foundation models are to real-world sources of variability, particularly in H&E staining and scanning protocols. In this study, we use soft tissue tumours, a rare and morphologically diverse tumour type, as a challenging test case to systematically investigate the colour-related robustness and generalisability of seven AI models. Controlled staining and scanning experiments were utilised to assess model performance across diverse real-world data sources. Foundation models, particularly UNI-v2, Virchow and TITAN, demonstrated encouraging robustness to staining and scanning variation, particularly when a small number of stain-varied slides were included in the training loop, highlighting their potential as adaptable and data-efficient tools for real-world digital pathology workflows.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media 96%
- Genomic Characterization of Lung Cancer in Never-Smokers Using Deep Learning 95%
- Attention-based whole-slide image compression achieves pathologist-level pre-screening of multi-organ routine histopathology biopsies 95%
Similar papers in this journal
Similar papers in this journal
- A tool for federated training of segmentation models on whole slide images. 94%
- Deep learning accurately quantifies plasma cell percentages on CD138-stained bone marrow samples 94%
- Independent assessment of a deep learning system for lymph node metastasis detection on the Augmented Reality Microscope 93%
Similar papers in this journal
- A histomorphological atlas of resected mesothelioma discovered by self-supervised learning from 3446 whole-slide images 96%
- The Impact of Digital Histopathology Batch Effect on Deep Learning Model Accuracy and Bias 95%
- Artificial intelligence-based histopathology image analysis identifies a novel subset of endometrial cancers with distinct genomic features and unfavourable outcome 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.