Fast fully automatic segmentation of the severely abnormal human right ventricle from cardiovascular magnetic resonance images using a multi-scale 3D convolutional neural network

Giannakidis, A ORCID logoORCID: https://orcid.org/0000-0001-7403-923X, Kamnitsas, K, Spadotto, V, Keegan, J, Smith, G, Glocker, B, Rueckert, D, Ernst, S, Gatzoulis, MA, Pennell, DJ, Babu-Narayan, S and Firmin, DN, 2016. Fast fully automatic segmentation of the severely abnormal human right ventricle from cardiovascular magnetic resonance images using a multi-scale 3D convolutional neural network. In: Yetongnon, K, Dipanda, A, Chbeir, R, De Pietro, G and Gallo, L, eds., Proceedings of the 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Naples, Italy, 2016. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), pp. 42-46. ISBN 9781509056989

[thumbnail of PubSub10550_Giannakidis.pdf]
Preview
Text
PubSub10550_Giannakidis.pdf - Post-print

Download (645kB) | Preview

Abstract

Cardiac magnetic resonance (CMR) is regarded as the reference examination for cardiac morphology in tetralogy of Fallot (ToF) patients allowing images of high spatial resolution and high contrast. The detailed knowledge of the right ventricular anatomy is critical in ToF management. The segmentation of the right ventricle (RV) in CMR images from ToF patients is a challenging task due to the high shape and image quality variability. In this paper we propose a fully automatic deep learning-based framework to segment the RV from CMR anatomical images of the whole heart. We adopt a 3D multi-scale deep convolutional neural network to identify pixels that belong to the RV. Our robust segmentation framework was tested on 26 ToF patients achieving a Dice similarity coefficient of 0.8281±0.1010 with reference to manual annotations performed by expert cardiologists. The proposed technique is also computationally efficient, which may further facilitate its adoption in the clinical routine.

Item Type: Chapter in book
Creators: Giannakidis, A., Kamnitsas, K., Spadotto, V., Keegan, J., Smith, G., Glocker, B., Rueckert, D., Ernst, S., Gatzoulis, M.A., Pennell, D.J., Babu-Narayan, S. and Firmin, D.N.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Place of Publication: Piscataway, NJ
Date: November 2016
ISBN: 9781509056989
Identifiers:
Number
Type
10.1109/SITIS.2016.16
DOI
Divisions: Schools > School of Science and Technology
Record created by: Linda Sullivan
Date Added: 04 Apr 2018 08:05
Last Modified: 04 Apr 2018 10:05
URI: https://irep.ntu.ac.uk/id/eprint/33160

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year