Does context matter in digital pathology?
This addresses the reliability of AI in healthcare by highlighting potential spurious reasoning in pathology models, though it is incremental as it focuses on a specific domain issue.
The study investigated whether deep learning models in digital pathology incorporate contextual tissue information like human experts, finding that model performance significantly decreases with limited context and that predictions can be unstable with varying context sizes.
The development of Artificial Intelligence for healthcare is of great importance. Models can sometimes achieve even superior performance to human experts, however, they can reason based on spurious features. This is not acceptable to the experts as it is expected that the models catch the valid patterns in the data following domain expertise. In the work, we analyse whether Deep Learning (DL) models for vision follow the histopathologists' practice so that when diagnosing a part of a lesion, they take into account also the surrounding tissues which serve as context. It turns out that the performance of DL models significantly decreases when the amount of contextual information is limited, therefore contextual information is valuable at prediction time. Moreover, we show that the models sometimes behave in an unstable way as for some images, they change the predictions many times depending on the size of the context. It may suggest that partial contextual information can be misleading.