A Joint 3D UNet-Graph Neural Network-Based Method for Airway Segmentation from Chest CTs
Antonio Garcia-Uceda Juarez,Raghavendra Selvan,Zaigham Saghir,Marleen de Bruijne +3 more
- pp 583-591
Reads0
Chats0
TLDR
An end-to-end deep learning segmentation method by combining a 3D UNet architecture with a graph neural network (GNN) model with two types of graph adjacency, which is applied to the task of segmenting the airway tree from chest CT scans.Abstract:
We present an end-to-end deep learning segmentation method by combining a 3D UNet architecture with a graph neural network (GNN) model. In this approach, the convolutional layers at the deepest level of the UNet are replaced by a GNN-based module with a series of graph convolutions. The dense feature maps at this level are transformed into a graph input to the GNN module. The incorporation of graph convolutions in the UNet provides nodes in the graph with information that is based on node connectivity, in addition to the local features learnt through the downsampled paths. This information can help improve segmentation decisions. By stacking several graph convolution layers, the nodes can access higher order neighbourhood information without substantial increase in computational expense. We propose two types of node connectivity in the graph adjacency: (i) one predefined and based on a regular node neighbourhood, and (ii) one dynamically computed during training and using the nearest neighbour nodes in the feature space. We have applied this method to the task of segmenting the airway tree from chest CT scans. Experiments have been performed on 32 CTs from the Danish Lung Cancer Screening Trial dataset. We evaluate the performance of the UNet-GNN models with two types of graph adjacency and compare it with the baseline UNet.read more
Citations
More filters
Journal ArticleDOI
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
TL;DR: A survey of different types of graph architectures and their applications in healthcare can be found in this article, where the authors provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure and electrical-based analysis.
Posted Content
Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation
TL;DR: A General Union loss function is designed that obviates the impact of airway size by distance-based weights and adaptively tunes the gradient ratio based on the learning process and can predict the airway structures with higher accuracy and better morphological completeness than the baselines.
Posted Content
Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
Yulei Qin,Hao Zheng,Yun Gu,Xiaolin Huang,Jie Yang,Lihui Wang,Feng Yao,Yuemin Zhu,Guang-Zhong Yang +8 more
TL;DR: A CNNs-based method for accurate airway and artery-vein segmentation in non-contrast computed tomography that extracted much more branches while maintaining competitive overall segmentation performance.
Journal ArticleDOI
Anatomy-aided deep learning for medical image segmentation: a review
TL;DR: A review of anatomical-aided DL for medical image segmentation is provided in this paper, which covers systematically summarized anatomical information categories and corresponding representation methods and addresses known and potentially solvable challenges in anatomy-a-aid DL and presents a categorized methodology overview on using anatomical information with DL from over 70 papers.
Book ChapterDOI
Learning Bronchiole-Sensitive Airway Segmentation CNNs by Feature Recalibration and Attention Distillation.
TL;DR: This work proposes a CNNs-based airway segmentation method that enjoys superior sensitivity to tenuous peripheral bronchioles, and presents a feature recalibration module to make the best use of learned features.
References
More filters
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Posted Content
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
TL;DR: A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
Journal ArticleDOI
The Graph Neural Network Model
TL;DR: A new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains, and implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space.