# Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images

arXiv: https://arxiv.org/abs/2101.07563 · HTML: https://mlsanity.com/paper/2101.07563/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Inclusive GAN: Improving Data and Minority Coverage in Generative Models](https://mlsanity.com/paper/2004.03355/) (2020)
- [Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification](https://mlsanity.com/paper/2009.07652/) (2020)

## Built on by (most cited first, 30 of 35)

- [AUC Maximization in the Era of Big Data and AI: A Survey](https://mlsanity.com/paper/2203.15046/) (2022)
- [Diffusion Visual Counterfactual Explanations](https://mlsanity.com/paper/2210.11841/) (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)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Explainable Deep Learning Methods in Medical Image Classification: A Survey](https://mlsanity.com/paper/2205.04766/) (2022)
- [Sparse Visual Counterfactual Explanations in Image Space](https://mlsanity.com/paper/2205.07972/) (2022)
- [Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images](https://mlsanity.com/paper/2308.02062/) (2023)
- [Explaining Chest X-ray Pathologies in Natural Language](https://mlsanity.com/paper/2207.04343/) (2022)
- [ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans](https://mlsanity.com/paper/2103.02561/) (2021)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations](https://mlsanity.com/paper/2302.12689/) (2023)
- [DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations](https://mlsanity.com/paper/2311.17833/) (2023)
- [medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space](https://mlsanity.com/paper/2204.05376/) (2022)
- [Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2303.00500/) (2023)
- [Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder](https://mlsanity.com/paper/2408.01571/) (2024)
- [A Framework for Interpretability in Machine Learning for Medical Imaging](https://mlsanity.com/paper/2310.01685/) (2023)
- [Deep AUC Maximization for Medical Image Classification: Challenges and Opportunities](https://mlsanity.com/paper/2111.02400/) (2021)
- [DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation](https://mlsanity.com/paper/2406.15182/) (2024)
- [Translational Lung Imaging Analysis Through Disentangled Representations](https://mlsanity.com/paper/2203.01668/) (2022)
- [Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problems](https://mlsanity.com/paper/2202.05311/) (2022)
- [Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rays](https://mlsanity.com/paper/2102.09475/) (2021)
- [A Brief Review of Explainable Artificial Intelligence in Healthcare](https://mlsanity.com/paper/2304.01543/) (2023)
- [Identifying Spurious Correlations using Counterfactual Alignment](https://mlsanity.com/paper/2312.02186/) (2023)
- [Shaping History: Advanced Machine Learning Techniques for the Analysis and Dating of Cuneiform Tablets over Three Millennia](https://mlsanity.com/paper/2406.04039/) (2024)
- [Rapid Review of Generative AI in Smart Medical Applications](https://mlsanity.com/paper/2406.06627/) (2024)
- [Explainability Requires Interactivity](https://mlsanity.com/paper/2109.07869/) (2021)
- [Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2406.05477/) (2024)
- [Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery](https://mlsanity.com/paper/2406.18552/) (2024)
- [Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation](https://mlsanity.com/paper/2411.05261/) (2024)

## Abstract (arXiv)

As AI-based medical devices are becoming more common in imaging fields like radiology and histology, interpretability of the underlying predictive models is crucial to expand their use in clinical practice. Existing heatmap-based interpretability methods such as GradCAM only highlight the location of predictive features but do not explain how they contribute to the prediction. In this paper, we propose a new interpretability method that can be used to understand the predictions of any black-box model on images, by showing how the input image would be modified in order to produce different predictions. A StyleGAN is trained on medical images to provide a mapping between latent vectors and images. Our method identifies the optimal direction in the latent space to create a change in the model prediction. By shifting the latent representation of an input image along this direction, we can produce a series of new synthetic images with changed predictions. We validate our approach on histology and radiology images, and demonstrate its ability to provide meaningful explanations that are more informative than GradCAM heatmaps. Our method reveals the patterns learned by the model, which allows clinicians to build trust in the model's predictions, discover new biomarkers and eventually reveal potential biases.