Multi-stage prediction networks for data harmonization

Blumberg, Stefano B., Palombo, Marco ORCID: https://orcid.org/0000-0003-4892-7967, Khoo, Can Son, Tax, Chantal M. W. ORCID: https://orcid.org/0000-0002-7480-8817, Tanno, Ryutaro and Alexander, Daniel C. 2019. Multi-stage prediction networks for data harmonization. Presented at: Medical Image Computing and Computer Assisted Intervention – MICCAI, Shenzhen, China, 13-17 Oct 2019. Medical Image Computing and Computer Assisted Intervention – MICCAI Proceedings. Lecture Notes in Computer Science. Lecture Notes in Computer Science , vol.11767 Springer, pp. 411-419. 10.1007/978-3-030-32251-9_45

Full text not available from this repository.

Abstract

In this paper, we introduce multi-task learning (MTL) to data harmonization (DH); where we aim to harmonize images across different acquisition platforms and sites. This allows us to integrate information from multiple acquisitions and improve the predictive performance and learning efficiency of the harmonization model. Specifically, we introduce the Multi Stage Prediction (MSP) Network, a MTL framework that incorporates neural networks of potentially disparate architectures, trained for different individual acquisition platforms, into a larger architecture that is refined in unison. The MSP utilizes high-level features of single networks for individual tasks, as inputs of additional neural networks to inform the final prediction, therefore exploiting redundancy across tasks to make the most of limited training data. We validate our methods on a dMRI harmonization challenge dataset, where we predict three modern platform types, from one obtained from an old scanner. We show how MTL architectures, such as the MSP, produce around 20% improvement of patch-based mean-squared error over current state-of-the-art methods and that our MSP outperforms off-the-shelf MTL networks. Our code is available [1].

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Psychology Cardiff University Brain Research Imaging Centre (CUBRIC)
Publisher:	Springer
ISBN:	9783030322502
ISSN:	0302-9743
Last Modified:	10 Nov 2022 10:42
URI:	https://orca.cardiff.ac.uk/id/eprint/147863

Citation Data

Cited 9 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item