Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images

Andrik Rampun, Deborah Jarvis, Paul D. Griffiths, Reyer Zwiggelaar, Bryan W. Scotney, Paul A. Armitage

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
33 Downloads (Pure)

Abstract

In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively.
Original languageEnglish
Article numbere200
JournalJournal of Imaging
Volume7
Issue number10
Early online date1 Oct 2021
DOIs
Publication statusPublished online - 1 Oct 2021

Bibliographical note

Funding Information:
Funding: This study was part funded by a grant from the National Institute for Health Research (UK), (NIHR HTA 09/06/01).

Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords

  • foetal brain segmentation
  • MRI
  • U-Net
  • HED network
  • deep learning
  • convolutional neural network
  • Deep learning
  • Foetal brain segmentation
  • Convolutional neural network

Fingerprint

Dive into the research topics of 'Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images'. Together they form a unique fingerprint.

Cite this