Semi-Supervised Variational Autoencoder for Survival Prediction
This work addresses survival prediction in brain tumor patients, offering a domain-specific incremental improvement by leveraging semi-supervised learning to reduce labeled data needs.
The paper tackles survival prediction from tumor segmentation masks using a semi-supervised variational autoencoder, achieving generalization across scanning platforms and pulse sequences while requiring few labeled subjects, validated on the BraTS 2019 dataset.
In this paper we propose a semi-supervised variational autoencoder for classification of overall survival groups from tumor segmentation masks. The model can use the output of any tumor segmentation algorithm, removing all assumptions on the scanning platform and the specific type of pulse sequences used, thereby increasing its generalization properties. Due to its semi-supervised nature, the method can learn to classify survival time by using a relatively small number of labeled subjects. We validate our model on the publicly available dataset from the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019.