Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation (2021-08-06T00:00:00.000000Z)

TL;DR

According to the experimental results on pancreas segmentation from Computed Tomography images, improvement in the quantitative measures is demonstrated and the proposed method shows qualitative enhancements in the segmentation maps, as demonstrated in the visual results.

Abstract

In recent years, deep learning based methods have shown success in essential medical image analysis tasks such as segmentation. Post-processing and refining the results of segmentation is a common practice to decrease the misclassifications originating from the segmentation network. In addition to widely used methods like Conditional Random Fields (CRFs) which focus on the structure of the segmented volume/area, a graph-based recent approach makes use of certain and uncertain points in a graph and refines the segmentation according to a small graph convolutional network (GCN). However, there are two drawbacks of the approach: most of the edges in the graph are assigned randomly and the GCN is trained independently from the segmentation network. To address these issues, we define a new neighbor-selection mechanism according to feature distances and combine the two networks in the training procedure. According to the experimental results on pancreas segmentation from Computed Tomography (CT) images, we demonstrate improvement in the quantitative measures. Also, examining the dynamic neighbors created by our method, edges between semantically similar image parts are observed. The proposed method also shows qualitative enhancements in the segmentation maps, as demonstrated in the visual results.

Authors

U. Demir

1 papers

Atahan Ozer

1 papers

Y. Sahin

1 papers

Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation

TL;DR

Abstract

Authors

References27 items

Principal Neighbourhood Aggregation for Graph Nets

Uncertainty-Aware Training of Neural Networks for Selective Medical Image Segmentation

Interactive 3D U-net for the segmentation of the pancreas in computed tomography scans

An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation

Fast Graph Representation Learning with PyTorch Geometric

How Powerful are Graph Neural Networks?

Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks

A Graph-CNN for 3D Point Cloud Classification

Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detections

Dynamic Graph CNN for Learning on Point Clouds

Graph Attention Networks

Medical Image Analysis using Convolutional Neural Networks: A Review

Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Inductive Representation Learning on Large Graphs

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

Semi-Supervised Classification with Graph Convolutional Networks

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound

U-Net: Convolutional Networks for Biomedical Image Segmentation

Adam: A Method for Stochastic Optimization

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Regression of Instance Boundary by Aggregated CNN and GCN

Study on MRI Medical Image Segmentation Technology Based on CNN-CRF Model

Data from pancreas-ct

Uncertainty-Based Dynamic Graph

Field of Study

Journal Information

Name

Volume