Uncertainty-based graph convolutional networks for organ segmentation refinement

Abstract

Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this problem presents a challenging environment due to high variability in the organ's shape and similarity between tissues, the generation of false negative and false positive regions in the output segmentation is a common issue. Recent works have shown that the uncertainty analysis of the model can provide us with useful information about potential errors in the segmentation. In this context, we proposed a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem that is solved by training a graph convolutional network. To test our method we refine the initial output of a 2D U-Net. We validate our framework with the NIH pancreas dataset and the spleen dataset of the medical segmentation decathlon. We show that our method outperforms the state-of-the art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen, with respect to the original U-Net's prediction. Finally, we discuss the results and current limitations of the model for future work in this research direction. For reproducibility purposes, we make our code publicly available.

arXiv commentAccepted at MIDL 2020

References in corpus (11)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
• Domain and Geometry Agnostic CNNs for Left Atrium Segmentation in 3D Ultrasound
• Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
• 3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training
• Learn to Estimate Labels Uncertainty for Quality Assurance