Database Annotation with few Examples: An Atlas-based Framework using Diffeomorphic Registration of 3D Trees

09/25/2020
by   Pierre-Louis Antonsanti, et al.
0

Automatic annotation of anatomical structures can help simplify workflow during interventions in numerous clinical applications but usually involves a large amount of annotated data. The complexity of the labeling task, together with the lack of representative data, slows down the development of robust solutions. In this paper, we propose a solution requiring very few annotated cases to label 3D pelvic arterial trees of patients with benign prostatic hyperplasia. We take advantage of Large Deformation Diffeomorphic Metric Mapping (LDDMM) to perform registration based on meaningful deformations from which we build an atlas. Branch pairing is then computed from the atlas to new cases using optimal transport to ensure one-to-one correspondence during the labeling process. To tackle topological variations in the tree, which usually degrades the performance of atlas-based techniques, we propose a simple bottom-up label assignment adapted to the pelvic anatomy. The proposed method achieves 97.6% labeling precision with only 5 cases for training, while in comparison learning-based methods only reach 82.2% on such small training sets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2020

CNN-Driven Quasiconformal Model for Large Deformation Image Registration

Image registration has been widely studied over the past several decades...
research
11/29/2020

A method for large diffeomorphic registration via broken geodesics

Anatomical variabilities seen in longitudinal data or inter-subject data...
research
11/27/2021

Label Assistant: A Workflow for Assisted Data Annotation in Image Segmentation Tasks

Recent research in the field of computer vision strongly focuses on deep...
research
03/23/2021

Partial Matching in the Space of Varifolds

In computer vision and medical imaging, the problem of matching structur...
research
12/01/2022

Automated Coronary Arteries Labeling Via Geometric Deep Learning

Automatic labelling of anatomical structures, such as coronary arteries,...
research
03/13/2019

Animating an Autonomous 3D Talking Avatar

One of the main challenges with embodying a conversational agent is anno...

Please sign up or login with your details

Forgot password? Click here to reset