# ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping

arXiv: https://arxiv.org/abs/2006.08287 · HTML: https://mlsanity.com/paper/2006.08287/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 20 of 20)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans](https://mlsanity.com/paper/2103.02561/) (2021)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model](https://mlsanity.com/paper/2108.09451/) (2021)
- [Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2303.00500/) (2023)
- [Disentangling representations of retinal images with generative models](https://mlsanity.com/paper/2402.19186/) (2024)
- [Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence](https://mlsanity.com/paper/2206.03247/) (2022)
- [Distinguishing Healthy Ageing from Dementia: a Biomechanical Simulation of Brain Atrophy using Deep Networks](https://mlsanity.com/paper/2108.08214/) (2021)
- [Applications of interpretable deep learning in neuroimaging: a comprehensive review](https://mlsanity.com/paper/2406.17792/) (2024)
- [Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions](https://mlsanity.com/paper/2106.10947/) (2021)
- [Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey](https://mlsanity.com/paper/2307.09615/) (2023)
- [How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?](https://mlsanity.com/paper/2310.18496/) (2023)
- [A Deep Generative Model of Neonatal Cortical Surface Development](https://mlsanity.com/paper/2206.07542/) (2022)
- [Anatomy-Guided Surface Diffusion Model for Alzheimer's Disease Normative Modeling](https://mlsanity.com/paper/2403.04531/) (2024)
- [Text-guided Feature Disentanglement for Cross-modal Gait Recognition](https://mlsanity.com/paper/2605.30784/) (2026)
- [Visual Interpretable and Explainable Deep Learning Models for Brain Tumor MRI and COVID-19 Chest X-ray Images](https://mlsanity.com/paper/2208.00953/) (2022)
- [Interpret the Predictions of Deep Networks via Re-Label Distillation](https://mlsanity.com/paper/2409.13137/) (2024)
- [On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines](https://mlsanity.com/paper/2508.14482/) (2025)

## Abstract (arXiv)

Feature attribution (FA), or the assignment of class-relevance to different locations in an image, is important for many classification problems but is particularly crucial within the neuroscience domain, where accurate mechanistic models of behaviours, or disease, require knowledge of all features discriminative of a trait. At the same time, predicting class relevance from brain images is challenging as phenotypes are typically heterogeneous, and changes occur against a background of significant natural variation. Here, we present a novel framework for creating class specific FA maps through image-to-image translation. We propose the use of a VAE-GAN to explicitly disentangle class relevance from background features for improved interpretability properties, which results in meaningful FA maps. We validate our method on 2D and 3D brain image datasets of dementia (ADNI dataset), ageing (UK Biobank), and (simulated) lesion detection. We show that FA maps generated by our method outperform baseline FA methods when validated against ground truth. More significantly, our approach is the first to use latent space sampling to support exploration of phenotype variation. Our code will be available online at https://github.com/CherBass/ICAM.