Uncertainty Quantification using Variational Inference for Biomedical Image Segmentation
share
Deep learning motivated by convolutional neural networks has been highly suc- cessful in a range of medical imaging problems like image classification, image segmentation, image synthesis etc. However for validation and interpretability, not only do we need the predictions made from the model but also how confident it is while making those predictions. This is important in safety critical applications for the people to accept it. In this work, we used an encoder decoder architecture based on variational inference techniques for segmenting brain tumour images. We compared different backbones architectures like U-Net, V-Net and FCN as sampling data from the conditional distribution for the encoder. We validated our work on BRATS dataset using Dice Similarity Coefficient and Intersection Over Union as the evaluation metrics. Our model achieves state of the art results while making use of a principled way of uncertainty quantification.
READ FULL TEXT