UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

XmoNet: A Fully Convolutional Network for Cross-Modality MR Image Inference

Bano, S; Asad, M; Fetit, AE; Rekik, I; (2018) XmoNet: A Fully Convolutional Network for Cross-Modality MR Image Inference. In: Rekik, I and Unal, G and Adeli, E and Park, SH, (eds.) PRedictive Intelligence in MEdicine: First International Workshop, PRIME 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings. (pp. pp. 129-137). Springer: Cham, Switzerland. Green open access

[thumbnail of Bano_XmoNet_cameraready_SB.pdf]
Preview
Text
Bano_XmoNet_cameraready_SB.pdf - Accepted version

Download (1MB) | Preview

Abstract

Magnetic resonance imaging (MRI) can generate multimodal scans with complementary contrast information, capturing various anatomical or functional properties of organs of interest. But whilst the acquisition of multiple modalities is favourable in clinical and research settings, it is hindered by a range of practical factors that include cost and imaging artefacts. We propose XmoNet, a deep-learning architecture based on fully convolutional networks (FCNs) that enables cross-modality MR image inference. This multiple branch architecture operates on various levels of image spatial resolutions, encoding rich feature hierarchies suited for this image generation task. We illustrate the utility of XmoNet in learning the mapping between heterogeneous T1- and T2-weighted MRI scans for accurate and realistic image synthesis in a preliminary analysis. Our findings support scaling the work to include larger samples and additional modalities.

Type: Proceedings paper
Title: XmoNet: A Fully Convolutional Network for Cross-Modality MR Image Inference
Event: First International Workshop, PRIME 2018, Held in Conjunction with MICCAI 2018, 16 September 2018, Granada, Spain
Location: Granada, Spain
Dates: 16 September 2018 - 16 September 2018
ISBN-13: 978-3-030-00320-3
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-00320-3_16
Publisher version: https://doi.org/10.1007/978-3-030-00320-3_16
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Fully convolutional networks · MRI · multimodal · image generation
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10068425
Downloads since deposit
65Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item