Integrating Clinical Knowledge into Concept Bottleneck Models

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 introdu...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Pang, Winnie, Ke, Xueyi, Tsutsui, Satoshi, Bihan Wen
Format: Article
Language:English
Subjects:
Datasets
Decision making
Image acquisition
Image classification
Medical imaging
Performance evaluation
Predictions
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422