Integrating Clinical Knowledge into Concept Bottleneck Models
This addresses the issue of model reliability for clinicians in medical imaging by improving out-of-domain generalization, though it is incremental as it refines existing CBMs with domain-specific guidance.
The paper tackled the problem of biases in concept bottleneck models (CBMs) trained data-driven, which reduce performance on out-of-domain medical images, by integrating clinical knowledge to prioritize clinician-relevant concepts, resulting in enhanced classification performance on unseen datasets with varying preparation methods.
Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model. However, training CBMs solely in a data-driven manner can introduce undesirable biases, which may compromise prediction performance, especially when the trained models are evaluated on out-of-domain images (e.g., those acquired using different devices). To mitigate this challenge, we propose integrating clinical knowledge to refine CBMs, better aligning them with clinicians' decision-making processes. Specifically, we guide the model to prioritize the concepts that clinicians also prioritize. We validate our approach on two datasets of medical images: white blood cell and skin images. Empirical validation demonstrates that incorporating medical guidance enhances the model's classification performance on unseen datasets with varying preparation methods, thereby increasing its real-world applicability.