Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields
This work addresses the challenge of ensuring topology guarantees in medical image segmentation, which is incremental as it integrates existing methods (CNNs and CRFs) for a specific domain.
The paper tackles the problem of automated surface segmentation in medical images by proposing a novel model combining 3-D CNNs and Conditional Random Fields for end-to-end training, achieving promising results on prostate and spleen datasets.
Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based approach (e.g., U-net), which predicts the probability of being target object or background for each voxel. One problem of those methods is lacking of topology guarantee for segmented objects, and usually post processing is needed to infer the boundary surface of the object. In this paper, a novel model based on 3-D convolutional neural networks (CNNs) and Conditional Random Fields (CRFs) is proposed to tackle the surface segmentation problem with end-to-end training. To the best of our knowledge, this is the first study to apply a 3-D neural network with a CRFs model for direct surface segmentation. Experiments carried out on NCI-ISBI 2013 MR prostate dataset and Medical Segmentation Decathlon Spleen dataset demonstrated promising segmentation results.