DeepAI AI Chat
Log In Sign Up

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

by   Kathryn Schutte, et al.

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.


page 2

page 4


medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space

Despite the surge of deep learning in the past decade, some users are sk...

What do Deep Neural Networks Learn in Medical Images?

Deep learning is increasingly gaining rapid adoption in healthcare to he...

Global and Local Interpretability for Cardiac MRI Classification

Deep learning methods for classifying medical images have demonstrated i...

An unexpected unity among methods for interpreting model predictions

Understanding why a model made a certain prediction is crucial in many d...

Topological Interpretability for Deep-Learning

With the increasing adoption of AI-based systems across everyday life, t...

Unsupervised deep clustering for predictive texture pattern discovery in medical images

Predictive marker patterns in imaging data are a means to quantify disea...

Explaining Latent Representations with a Corpus of Examples

Modern machine learning models are complicated. Most of them rely on con...