Scientific Discovery by Generating Counterfactuals using Image Translation
This work addresses the challenge of bridging model performance and human understanding in medical imaging, though it appears incremental as it builds on existing explanation techniques.
The authors tackled the problem of using model explanation techniques for scientific discovery by proposing a framework that converts explanations into a discovery mechanism, applying it to retinal image classification for Diabetic Macular Edema (DME) to explain the underlying scientific mechanism.
Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation techniques can also be used as a mechanism for scientific discovery. We make three contributions: first, we propose a framework to convert predictions from explanation techniques to a mechanism of discovery. Second, we show how generative models in combination with black-box predictors can be used to generate hypotheses (without human priors) that can be critically examined. Third, with these techniques we study classification models for retinal images predicting Diabetic Macular Edema (DME), where recent work showed that a CNN trained on these images is likely learning novel features in the image. We demonstrate that the proposed framework is able to explain the underlying scientific mechanism, thus bridging the gap between the model's performance and human understanding.