Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction

12/14/2020
by   Jiafa He, et al.
10

Automatic blood vessel extraction from 3D medical images is crucial for vascular disease diagnoses. Existing methods based on convolutional neural networks (CNNs) may suffer from discontinuities of extracted vessels when segmenting such thin tubular structures from 3D images. We argue that preserving the continuity of extracted vessels requires to take into account the global geometry. However, 3D convolutions are computationally inefficient, which prohibits the 3D CNNs from sufficiently large receptive fields to capture the global cues in the entire image. In this work, we propose a hybrid representation learning approach to address this challenge. The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image. In inference, the proposed approach extracts local segments of vessels using CNNs, classifies each segment based on global geometry using the point-cloud network, and finally connects all the segments that belong to the same vessel using the shortest-path algorithm. This combination results in an efficient, fully-automatic and template-free approach to centerline extraction from 3D images. We validate the proposed approach on CTA datasets and demonstrate its superior performance compared to both traditional and CNN-based baselines.

READ FULL TEXT

page 3

page 7

page 9

research
03/03/2021

EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation

Point cloud patterns are hard to learn because of the implicit local geo...
research
04/24/2018

Learning 3D Segment Descriptors for Place Recognition

In the absence of global positioning information, place recognition is a...
research
04/10/2023

High Dynamic Range Imaging with Context-aware Transformer

Avoiding the introduction of ghosts when synthesising LDR images as high...
research
05/08/2020

Beyond CNNs: Exploiting Further Inherent Symmetries in Medical Images for Segmentation

Automatic tumor segmentation is a crucial step in medical image analysis...
research
12/12/2019

LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices

Deep convolutional neural networks (CNNs) have shown outstanding perform...
research
08/16/2018

Occlusion Resistant Object Rotation Regression from Point Cloud Segments

Rotation estimation of known rigid objects is important for robotic appl...
research
03/06/2023

Learning multi-scale local conditional probability models of images

Deep neural networks can learn powerful prior probability models for ima...

Please sign up or login with your details

Forgot password? Click here to reset