GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately ...

Nov 14, 2019 · In this work, we propose a deep-learning approach, called DeepBundle, to parcellate whole-brain tractograms without the time-consuming ...

GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately ...

This repository contains code that emulates the DeepBundle [1] framework, visualizes its features, and explores the addition of an SVM on top of the network and ...

Abstract: Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure.

Jun 7, 2019 · A novel deep learning method, called DeepBundle, for registration-free fiber parcellation that utilizes graph convolution neural networks ...

GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately ...

Dive into the research topics of 'DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks'. Together they form a unique fingerprint. Sort ...

DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks. Feihong Liu; , Jun Feng; , Geng Chen; , Ye Wu; , Yoonmi Hong; , Pew-Thian Yap ...

We propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem.