Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder
arXiv:2408.01571 · doi:10.59275/j.melba.2024-4862
Abstract
Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and are typically constrained to binary counterfactuals. In contrast, we propose a novel method that operates directly on the latent space of a generative model, specifically a Diffusion Autoencoder (DAE). This approach offers inherent interpretability by enabling the generation of CEs and the continuous visualization of the model's internal representation across decision boundaries. Our method leverages the DAE's ability to encode images into a semantically rich latent space in an unsupervised manner, eliminating the need for labeled data or separate feature extraction models. We show that these latent representations are helpful for medical condition classification and the ordinal regression of severity pathologies, such as vertebral compression fractures (VCF) and diabetic retinopathy (DR). Beyond binary CEs, our method supports the visualization of ordinal CEs using a linear model, providing deeper insights into the model's decision-making process and enhancing interpretability. Experiments across various medical imaging datasets demonstrate the method's advantages in interpretability and versatility. The linear manifold of the DAE's latent space allows for meaningful interpolation and manipulation, making it a powerful tool for exploring medical image properties. Our code is available at https://doi.org/10.5281/zenodo.13859266.
Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2024:024. arXiv admin note: text overlap with arXiv:2303.12031
References in corpus (14)
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
- Classifier-Free Diffusion Guidance
- VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images
- Lumbar spine segmentation in MR images: a dataset and a public benchmark
- Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
- Diffusion Models already have a Semantic Latent Space
- Unsupervised and semi-supervised learning with Categorical Generative Adversarial Networks assisted by Wasserstein distance for dermoscopy image Classification
- Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images
- Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis
- GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images
- CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN
- Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessment
- Faint Features Tell: Automatic Vertebrae Fracture Screening Assisted by Contrastive Learning