首页 > AI前沿 > Faithful, Interpretable Chest X-ray Diagnosis with Artifact-free B-cos Networks

Faithful, Interpretable Chest X-ray Diagnosis with Artifact-free B-cos Networks

arXiv机器学习 2025-07-23 00:56 5 阅读 查看原文

Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical image analysis.

B-cos networks modify the parameterization of convolutional and classification layers to measure class evidence via feature-weight alignment, enabling built-in, class-specific contribution maps without post-hoc explanations.

While maintaining diagnostic performance competitive with state-of-the-art DNNs, standard B-cos networks exhibit severe aliasing artifacts in their explanation maps, rendering them unsuitable for clinical use, where clarity is essential.

In this work

We address this limitation by introducing anti-aliasing strategies using ASAP and BlurPool (BP) to significantly improve explanation quality.

Our experiments on chest X-ray datasets demonstrate that the modified $\text{B-cos}_\mathrm{ASAP}$ and $\text{B-cos}_\mathrm{BP}$ preserve strong predictive performance while providing faithful and artifact-free explanations suitable for clinical application in multi-class and multi-label settings.

Code is available at: https://github.com/shrebox/Artifact-free-B-cos-Networks.