Survival-oriented embeddings for improving accessibility to complex data structures
arXiv:2110.11303
Abstract
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.
arXiv commentNeurIPS 2021 Workshop, Bridging the Gap: From Machine Learning Research to Clinical Practice
References in corpus (9)
- Auto-Encoding Variational Bayes
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network
- Grad-CAM: Why did you say that?
- nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
- A Scalable Discrete-Time Survival Model for Neural Networks
- Deep Learning for Patient-Specific Kidney Graft Survival Analysis
- Semi-Structured Deep Piecewise Exponential Models
- A General Framework for Survival Analysis and Multi-State Modelling