Conditional Random Fields as Recurrent Neural Networks for 3D Medical Imaging Segmentation

19 Jul 2018  ·  Miguel Monteiro, Mário A. T. Figueiredo, Arlindo L. Oliveira ·

The Conditional Random Field as a Recurrent Neural Network layer is a recently proposed algorithm meant to be placed on top of an existing Fully-Convolutional Neural Network to improve the quality of semantic segmentation. In this paper, we test whether this algorithm, which was shown to improve semantic segmentation for 2D RGB images, is able to improve segmentation quality for 3D multi-modal medical images. We developed an implementation of the algorithm which works for any number of spatial dimensions, input/output image channels, and reference image channels. As far as we know this is the first publicly available implementation of this sort. We tested the algorithm with two distinct 3D medical imaging datasets, we concluded that the performance differences observed were not statistically significant. Finally, in the discussion section of the paper, we go into the reasons as to why this technique transfers poorly from natural images to medical images.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Volumetric Medical Image Segmentation PROMISE 2012 Fully-connected CRF Dice Score 0.780 # 2


No methods listed for this paper. Add relevant methods here