MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification

TL;DR

MVP-CBM enhances explainability in medical image classification by modeling concept preferences across multiple visual layers, leading to more accurate and interpretable predictions.

Contribution

It introduces a novel multi-layer concept preference modeling approach that captures diverse concept associations at different visual layers, improving interpretability.

Findings

Achieves state-of-the-art accuracy on medical benchmarks.

Provides more nuanced and accurate explanations.

Demonstrates improved interpretability over traditional CBMs.

Abstract

The concept bottleneck model (CBM), as a technique improving interpretability via linking predictions to human-understandable concepts, makes high-risk and life-critical medical image classification credible. Typically, existing CBM methods associate the final layer of visual encoders with concepts to explain the model's predictions. However, we empirically discover the phenomenon of concept preference variation, that is, the concepts are preferably associated with the features at different layers than those only at the final layer; yet a blind last-layer-based association neglects such a preference variation and thus weakens the accurate correspondences between features and concepts, impairing model interpretability. To address this issue, we propose a novel Multi-layer Visual Preference-enhanced Concept Bottleneck Model (MVP-CBM), which comprises two key novel modules: (1) intra-layer concept preference modeling, which captures the preferred association of different concepts with features at various visual layers, and (2) multi-layer concept sparse activation fusion, which sparsely aggregates concept activations from multiple layers to enhance performance. Thus, by explicitly modeling concept preferences, MVP-CBM can comprehensively leverage multi-layer visual information to provide a more nuanced and accurate explanation of model decisions. Extensive experiments on several public medical classification benchmarks demonstrate that MVP-CBM achieves state-of-the-art accuracy and interoperability, verifying its superiority. Code is available at https://github.com/wcj6/MVP-CBM.