Accurate segmentation of neonatal brain MRI with deep learning
File(s)
Published version
Author(s)
Richter, Leo
Fetit, Ahmed
Type
Journal Article
Abstract
An important step towards delivering an accurate connectome of the human brain is robust segmentation of 3D Magnetic
Resonance Imaging (MRI) scans, which is particularly challenging when carried out on perinatal data. In this paper, we present an
automated, deep learned-based pipeline for accurate segmentation of tissues from neonatal brain MRI, and extend it to carry out
accurate age prediction. A major constraint to using deep learning techniques on developing brain data is the need to collect large
numbers of ground truth labels. We therefore also investigate two practical approaches that can help alleviate the problem of label
scarcity without loss of segmentation performance. First, we examine the efficiency of different strategies of distributing a
limited budget of annotated 2D slices over 3D training images. In the second approach, we compare the segmentation performance
of pre-trained models with different strategies of fine-tuning on a small subset of preterm infants. Our results indicate that
distributing labels over a larger number of brain scans can improve segmentation performance. We also show that even partial
fine-tuning can be superior in performance to a model trained from scratch, highlighting the relevance of transfer learning
strategies under conditions of label scarcity. We illustrate our findings on large, publicly available T1- and T2-weighted MRI scans
(n=709, range of ages at scan: 26-45 weeks) obtained retrospectively from the Developing Human Connectome Project cohort.
Resonance Imaging (MRI) scans, which is particularly challenging when carried out on perinatal data. In this paper, we present an
automated, deep learned-based pipeline for accurate segmentation of tissues from neonatal brain MRI, and extend it to carry out
accurate age prediction. A major constraint to using deep learning techniques on developing brain data is the need to collect large
numbers of ground truth labels. We therefore also investigate two practical approaches that can help alleviate the problem of label
scarcity without loss of segmentation performance. First, we examine the efficiency of different strategies of distributing a
limited budget of annotated 2D slices over 3D training images. In the second approach, we compare the segmentation performance
of pre-trained models with different strategies of fine-tuning on a small subset of preterm infants. Our results indicate that
distributing labels over a larger number of brain scans can improve segmentation performance. We also show that even partial
fine-tuning can be superior in performance to a model trained from scratch, highlighting the relevance of transfer learning
strategies under conditions of label scarcity. We illustrate our findings on large, publicly available T1- and T2-weighted MRI scans
(n=709, range of ages at scan: 26-45 weeks) obtained retrospectively from the Developing Human Connectome Project cohort.
Date Issued
2022-09-28
Date Acceptance
2022-07-29
Citation
Frontiers in Neuroinformatics, 2022, 16, pp.1-18
ISSN
1662-5196
Publisher
Frontiers Media
Start Page
1
End Page
18
Journal / Book Title
Frontiers in Neuroinformatics
Volume
16
Copyright Statement
© 2022 Richter and Fetit. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
License URL
Sponsor
Engineering and Physical Sciences Research Council
Identifier
https://www.frontiersin.org/articles/10.3389/fninf.2022.1006532/full
Grant Number
EP/S023283/1
Subjects
MRI
deep learning
label budget
neonates
semantic segmentation
transfer learning
1109 Neurosciences
1702 Cognitive Sciences
Publication Status
Published
Article Number
1006532
Date Publish Online
2022-09-28