Published on Thu Oct 17 2019

Detecting intracranial aneurysm rupture from 3D surfaces using a novel GraphNet approach

Z. Ma, L. Song, X. Feng, G. Yang, W. Zhu, J. Liu, Y. Zhang, X. Yang, Y. Yin

GraphNet is based on graph convolution network (GCN) and is designed for graph-level classification and node-level segmentation. 1250 patient data including 385 ruptured and 865 unruptured IAs were collected from clinic for experiments.

0
0
0
Abstract

Intracranial aneurysm (IA) is a life-threatening blood spot in human's brain if it ruptures and causes cerebral hemorrhage. It is challenging to detect whether an IA has ruptured from medical images. In this paper, we propose a novel graph based neural network named GraphNet to detect IA rupture from 3D surface data. GraphNet is based on graph convolution network (GCN) and is designed for graph-level classification and node-level segmentation. The network uses GCN blocks to extract surface local features and pools to global features. 1250 patient data including 385 ruptured and 865 unruptured IAs were collected from clinic for experiments. The performance on randomly selected 234 test patient data was reported. The experiment with the proposed GraphNet achieved accuracy of 0.82, area-under-curve (AUC) of receiver operating characteristic (ROC) curve 0.82 in the classification task, significantly outperforming the baseline approach without using graph based networks. The segmentation output of the model achieved mean graph-node-based dice coefficient (DSC) score 0.88.

Sat Jul 11 2020
Machine Learning
Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement
Automatically labeling intracranial arteries (ICA) is beneficial for feature extraction and detailed analysis of vascular structures. We construct a comprehensive dataset with 729 Magnetic Resonance Angiography scans and propose a Graph Neural Network (GNN) method to label arteries.
0
0
0
Mon Mar 02 2020
Machine Learning
IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
medicine is an important application area for deep learning models. This paper introduces an open-access 3Dintracranial aneurysm dataset, IntrA, that makes the application of point-based and mesh-based models available.
0
0
0
Thu Sep 10 2020
Machine Learning
MedMeshCNN -- Enabling MeshCNN for Medical Surface Models
MedMeshCNN outperformed state-of-the-art methods within classification and segmentation tasks. It enables the segmentation of pathological structures that often come with highly imbalanced class distributions. MedMeshCNN is an expansion for complex, diverse, and fine-grained medical data.
0
0
0
Fri May 22 2020
Machine Learning
Deep Learning Based Detection and Localization of Cerebal Aneurysms in Computed Tomography Angiography
DeepBrain is a deep learning based cerebral aneurysm detection and localization algorithm. It was trained and tested on 550 brain CTA scans and achieved sensitivity of 93.3% with 0.3 false positives per patient.
0
0
0
Mon Jun 29 2020
Machine Learning
Surface-based 3D Deep Learning Framework for Segmentation of Intracranial Aneurysms from TOF-MRA Images
Segmentation of intracranial aneurysms is an important task in medical diagnosis and surgical planning. Volume-based deep learning frameworks have been proposed for this task; however, they are not effective. In this study, we propose a surface- based deep learning framework that
0
0
0
Wed Dec 30 2020
Computer Vision
Exploring Large Context for Cerebral Aneurysm Segmentation
Automated segmentation of aneurysms from 3D CT is important for the diagnosis, monitoring, and treatment planning of the cerebral aneurYSm disease. Our method ranked second on the MICCAI 2020 CADA testing dataset with an average Jaccard of 0.7593.
0
0
0