Federated optimisation of kinetic analysis problems

Dowson, Nicholas, Baker, Charles, Thomas, Paul, Smith, Jye, Puttick, Simon, Bell, Christopher, Salvado, Olivier and Rose, Stephen (2017) Federated optimisation of kinetic analysis problems. Medical Image Analysis, 35 116-132. doi:10.1016/j.media.2016.06.019

Author Dowson, Nicholas
Baker, Charles
Thomas, Paul
Smith, Jye
Puttick, Simon
Bell, Christopher
Salvado, Olivier
Rose, Stephen
Title Federated optimisation of kinetic analysis problems
Journal name Medical Image Analysis   Check publisher's open access policy
ISSN 1361-8415
Publication date 2017-01
Year available 2016
Sub-type Article (original research)
DOI 10.1016/j.media.2016.06.019
Open Access Status Not Open Access
Volume 35
Start page 116
End page 132
Total pages 17
Place of publication Amsterdam, Netherlands
Publisher Elsevier
Collection year 2017
Language eng
Abstract Positron Emission Tomography (PET) data is intrinsically dynamic, and kinetic analysis of dynamic PET data can substantially augment the information provided by static PET reconstructions. Yet despite the insights into disease that kinetic analysis offers, it is not used clinically and seldom used in research beyond the preclinical stage. The utility of PET kinetic analysis is hampered by several factors including spatial inconsistency within regions of homogeneous tissue and relative computational expense when fitting complex models to individual voxels. Even with sophisticated algorithms inconsistencies can arise because local optima frequently have narrow basins of convergence, are surrounded by relatively flat (uninformative) regions, have relatively low-gradient valley floors, or combinations thereof. Based on the observation that cost functions for individual voxels frequently bear some resemblance to each-other, this paper proposes the federated optimisation of the individual kinetic analysis problems within a given image. This approach shares parameters proposed during optimisation with other, similar voxels. Federated optimisation exploits the redundancy typical of large medical images to improve the optimisation residuals, computational efficiency and, to a limited extent, image consistency. This is achieved without restricting the formulation of the kinetic model, resorting to an explicit regularisation parameter, or limiting the resolution at which parameters are computed.
Keyword Dynamic images
Kinetic analysis
Magnetic resonance imaging
Positron emission tomography
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 19 Jul 2016, 11:11:22 EST by Simon Puttick on behalf of Aust Institute for Bioengineering & Nanotechnology