Deep Learning for Medical Imaging From Diagnosis Prediction to its Counterfactual Explanation
This work targets the medical imaging domain by developing tailored deep learning methods, which is incremental as it adapts existing approaches to specific constraints.
The dissertation addresses the gap in applying deep neural networks to medical imaging by proposing novel architectures that integrate domain-specific constraints into model and explanation design, aiming to improve both diagnosis prediction and counterfactual explanations.
Deep neural networks (DNN) have achieved unprecedented performance in computer-vision tasks almost ubiquitously in business, technology, and science. While substantial efforts are made to engineer highly accurate architectures and provide usable model explanations, most state-of-the-art approaches are first designed for natural vision and then translated to the medical domain. This dissertation seeks to address this gap by proposing novel architectures that integrate the domain-specific constraints of medical imaging into the DNN model and explanation design.