» Articles » PMID: 32273836

Using Deep Convolutional Neural Networks for Neonatal Brain Image Segmentation

Overview
Journal Front Neurosci
Date 2020 Apr 11
PMID 32273836
Citations 16
Authors
Affiliations
Soon will be listed here.
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.

Citing Articles

Multilabel SegSRGAN-A framework for parcellation and morphometry of preterm brain in MRI.

Dolle G, Loron G, Alloux M, Kraus V, Delannoy Q, Beck J PLoS One. 2024; 19(11):e0312822.

PMID: 39485735 PMC: 11530046. DOI: 10.1371/journal.pone.0312822.


Subject-specific atlas for automatic brain tissue segmentation of neonatal magnetic resonance images.

Noorizadeh N, Kazemi K, Taji S, Danyali H, Aarabi A Sci Rep. 2024; 14(1):19114.

PMID: 39155321 PMC: 11330982. DOI: 10.1038/s41598-024-69995-z.


Artificial intelligence for volumetric measurement of cerebral white matter hyperintensities on thick-slice fluid-attenuated inversion recovery (FLAIR) magnetic resonance images from multiple centers.

Kuwabara M, Ikawa F, Nakazawa S, Koshino S, Ishii D, Kondo H Sci Rep. 2024; 14(1):10104.

PMID: 38698152 PMC: 11065995. DOI: 10.1038/s41598-024-60789-x.


Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images.

Jafrasteh B, Lubian-Gutierrez M, Lubian-Lopez S, Benavente-Fernandez I Neuroinformatics. 2024; 22(4):407-420.

PMID: 38656595 PMC: 11579192. DOI: 10.1007/s12021-024-09661-x.


The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review.

Keles E, Bagci U NPJ Digit Med. 2023; 6(1):220.

PMID: 38012349 PMC: 10682088. DOI: 10.1038/s41746-023-00941-5.


References
1.
Dolz J, Gopinath K, Yuan J, Lombaert H, Desrosiers C, Ben Ayed I . HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation. IEEE Trans Med Imaging. 2018; 38(5):1116-1126. DOI: 10.1109/TMI.2018.2878669. View

2.
Wang L, Shi F, Yap P, Gilmore J, Lin W, Shen D . 4D multi-modality tissue segmentation of serial infant images. PLoS One. 2012; 7(9):e44596. PMC: 3458067. DOI: 10.1371/journal.pone.0044596. View

3.
Chen H, Dou Q, Yu L, Qin J, Heng P . VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images. Neuroimage. 2017; 170:446-455. DOI: 10.1016/j.neuroimage.2017.04.041. View

4.
Shroff M, Soares-Fernandes J, Whyte H, Raybaud C . MR imaging for diagnostic evaluation of encephalopathy in the newborn. Radiographics. 2010; 30(3):763-80. DOI: 10.1148/rg.303095126. View

5.
Moeskops P, Viergever M, Mendrik A, de Vries L, Benders M, Isgum I . Automatic Segmentation of MR Brain Images With a Convolutional Neural Network. IEEE Trans Med Imaging. 2016; 35(5):1252-1261. DOI: 10.1109/TMI.2016.2548501. View