Using Deep Convolutional Neural Networks for Neonatal Brain Image Segmentation (2020-03-26T00:00:00.000000Z)

TL;DR

The evaluation demonstrates that both neural networks can segment neonatal brains, achieving previously reported performance and will be continuously retrained over an increasingly larger repertoire of neonatal brain data and be made available through the Canadian Neonatal Brain Platform.

Abstract

Introduction Deep learning neural networks are especially potent at dealing with structured data, such as images and volumes. Both modified LiviaNET and HyperDense-Net performed well at a prior competition segmenting 6-month-old infant magnetic resonance images, but neonatal cerebral tissue type identification is challenging given its uniquely inverted tissue contrasts. The current study aims to evaluate the two architectures to segment neonatal brain tissue types at term equivalent age. Methods Both networks were retrained over 24 pairs of neonatal T1 and T2 data from the Developing Human Connectome Project public data set and validated on another eight pairs against ground truth. We then reported the best-performing model from training and its performance by computing the Dice similarity coefficient (DSC) for each tissue type against eight test subjects. Results During the testing phase, among the segmentation approaches tested, the dual-modality HyperDense-Net achieved the best statistically significantly test mean DSC values, obtaining 0.94/0.95/0.92 for the tissue types and took 80 h to train and 10 min to segment, including preprocessing. The single-modality LiviaNET was better at processing T2-weighted images than processing T1-weighted images across all tissue types, achieving mean DSC values of 0.90/0.90/0.88 for gray matter, white matter, and cerebrospinal fluid, respectively, while requiring 30 h to train and 8 min to segment each brain, including preprocessing. Discussion Our evaluation demonstrates that both neural networks can segment neonatal brains, achieving previously reported performance. Both networks will be continuously retrained over an increasingly larger repertoire of neonatal brain data and be made available through the Canadian Neonatal Brain Platform to better serve the neonatal brain imaging research community.

References28 items

Benchmark on Automatic Six-Month-Old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge

HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation

Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation

Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions

VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images

A survey on deep learning in medical image analysis

A new neonatal cortical and subcortical brain atlas: the Melbourne Children's Regional Infant Brain (M-CRIB) atlas

3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study

Automatic Segmentation of MR Brain Images With a Convolutional Neural Network

Neonatal Brain Tissue Classification with Morphological Adaptation and Unified Segmentation

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Deep convolutional neural networks for multi-modality isointense infant brain image segmentation

Fully convolutional networks for semantic segmentation

Automatic Whole Brain MRI Segmentation of the Developing Neonatal Brain

ImageNet classification with deep convolutional neural networks

Investigating white matter development in infancy and early childhood using myelin water faction and relaxation time mapping

4D Multi-Modality Tissue Segmentation of Serial Infant Images

Magnetic resonance imaging of the newborn brain: Manual segmentation of labelled atlases in term-born and preterm infants

MR imaging for diagnostic evaluation of encephalopathy in the newborn.

N4ITK: Improved N3 Bias Correction

Automatic segmentation of newborn brain MRI

Automatic segmentation of MR images of the developing newborn brain

Fast robust automated brain extraction

The developing human connectome: announcing the ﬁrst release of open access neonatal brain imaging

SPM12 Manual

Neural Networks for Machine

Conﬂict of Interest: The authors declare that the research was conducted in the absence of any commercial or ﬁnancial relationships that could be construed as a potential conﬂict of interest