Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

Anna Kuzina, Evgenii Egorov, Evgeny Burnaev

Keywords: Brain Tumor Segmentation, Brain lesion segmentation, Transfer Learning, Variational Inference, Bayesian Neural Networks, Variational Autoencoder, 3D CNN

TL;DR: Transfer learning for DNN based segmentation between illnesses by learning generative prior in conv-filter space is better than pretrain.

Track: short paper

Paper Type: methodological development

Abstract: Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods. Nevertheless, these methods are inapplicable for small datasets, which are very common in medical problems. To this end, we propose a knowledge transfer method between diseases via the Generative Bayesian Prior network. Our approach is compared to a pre-train approach and random initialization and obtains the best results in terms of Dice Similarity Coefficient metric for the small subsets of the Brain Tumor Segmentation 2018 database (BRATS2018).

Presentation Upload Agreement: I agree that my presentation material (videos and slides) will be made public.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2005.12639/code)