Survival-oriented embeddings for improving accessibility to complex data structures
This addresses the need for interpretable AI in high-criticality medical applications like radiology, where black-box models are unacceptable for decision-making.
The paper tackled the problem of interpreting deep learning models in survival analysis for clinical radiology by proposing a hazard-regularized variational autoencoder, which was applied to abdominal CT scans of liver tumor patients to relate images to survival times.
Deep learning excels in the analysis of unstructured data and recent advancements allow to extend these techniques to survival analysis. In the context of clinical radiology, this enables, e.g., to relate unstructured volumetric images to a risk score or a prognosis of life expectancy and support clinical decision making. Medical applications are, however, associated with high criticality and consequently, neither medical personnel nor patients do usually accept black box models as reason or basis for decisions. Apart from averseness to new technologies, this is due to missing interpretability, transparency and accountability of many machine learning methods. We propose a hazard-regularized variational autoencoder that supports straightforward interpretation of deep neural architectures in the context of survival analysis, a field highly relevant in healthcare. We apply the proposed approach to abdominal CT scans of patients with liver tumors and their corresponding survival times.