Make U-Net Greater: An Easy-to-Embed Approach to Improve Segmentation Performance Using Hypergraph
Authors:
Open Access
- 1 January 2022
- journal article
- research article
- Published by Tech Science Press in Computer Systems Science and Engineering
- Vol. 42 (1) , 319-333
Abstract
Cardiac anatomy segmentation is essential for cardiomyopathy clinical diagnosis and treatment planning. Thus, accurate delineation of target volumes at risk in cardiac anatomy is important. However, manual delineation is a time-consuming and labor-intensive process for cardiologists and has been shown to lead to significant inter-and intra-practitioner variability. Thus, computer-aided or fully automatic segmentation methods are required. They can significantly economize on manpower and improve treatment efficiency. Recently, deep convolutional neural network (CNN) based methods have achieved remarkable successes in various kinds of vision tasks, such as classification, segmentation and object detection. Semantic segmentation can be considered as a pixel-wise task, it requires high-level abstract semantics information while maintaining spatial detail contexts. Long-range context information plays a crucial role in this scenario. However, the traditional convolution kernel only provides the local and small size of the receptive field. To address the problem, we propose a plug-and-play module aggregating both local and global information (aka LGIA module) to capture the high-order relationship between nodes that are far apart. We incorporate both local and global correlations into hypergraph which is able to capture high-order relationships between nodes via the concept of a hyperedge connecting a subset of nodes. The local correlation considers neighborhood nodes that are spatially adjacent and similar in the same CNN feature maps of magnetic resonance (MR) image; and the global correlation is searched from a batch of CNN feature maps of MR images in feature space. The influence of these two correlations on semantic segmentation is complementary. We validated our LGIA module on various CNN segmentation models with the cardiac MR images dataset. Experimental results demonstrate that our approach outperformed several baseline models.Keywords
This publication has 10 references indexed in Scilit:
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- A Review of Object Detectors in Deep LearningJournal on Artificial Intelligence, 2020
- Online Multi-Expert Learning for Visual TrackingIEEE Transactions on Image Processing, 2019
- A Review on Deep Learning Approaches to Image Classification and Object SegmentationComputers, Materials & Continua, 2019
- Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context LearningIEEE Transactions on Image Processing, 2018
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Multiscale CNNs for Brain Tumor Segmentation and DiagnosisComputational and Mathematical Methods in Medicine, 2016
- Metrics for evaluating 3D medical image segmentation: analysis, selection, and toolBMC Medical Imaging, 2015
- A Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR ImagesIEEE Transactions on Medical Imaging, 2013
- Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentationNeuroImage, 2011