Explaining 3D Computed Tomography Classifiers with Counterfactuals
Journal:
arXiv
Published Date:
Feb 11, 2025
Abstract
Counterfactual explanations enhance the interpretability of deep learning
models in medical imaging, yet adapting them to 3D CT scans poses challenges
due to volumetric complexity and resource demands. We extend the Latent Shift
counterfactual generation method from 2D applications to explain 3D computed
tomography (CT) scans classifiers. We address the challenges associated with 3D
classifiers, such as limited training samples and high memory demands, by
implementing a slice-based autoencoder and gradient blocking except for
specific chunks of slices. This method leverages a 2D encoder trained on CT
slices, which are subsequently combined to maintain 3D context. We demonstrate
this technique on two models for clinical phenotype prediction and lung
segmentation. Our approach is both memory-efficient and effective for
generating interpretable counterfactuals in high-resolution 3D medical imaging.
