Clustering-based deconvolution of brain CT perfusion data

Simple item page
dc.contributor.authorWu, Qi
dc.contributor.authorHuang, Jian
dc.contributor.authorWolsztynski, Eric
dc.contributor.funderResearch Ireland, (12/RC/2289-P2)
dc.date.accessioned2026-03-03T16:50:06Z
dc.date.available2026-03-03T16:50:06Z
dc.date.issued2025-07-18
dc.description.abstractComputed Tomography Perfusion (CTP) imaging relies on robust deconvolution methods to estimate kinetic parameters, from separation of the arterial input function and residue (i.e. tissue retention) function. While techniques based on singular value decomposition (SVD) provide computational efficiency, their lack of physiological constraints on the residue function can reduce accuracy of perfusion parameter estimation. We propose a clustering-based deconvolution framework, representing voxel-level time density curves (TDCs) as linear combinations of physiologically informed basis functions. Features extracted from TDCs guide optimal basis selection via clustering, which mitigates the high noise inherent in individual voxels, while non-negative linear least-squares and grid-search are used to estimate physiological parameters of interest. Results demonstrate improved stability and alignment with physiological expectations.en
dc.description.versionAccepted Version
dc.format.extent4
dc.format.mimetypeapplication/pdfen
dc.identifier.authororcidWu, Qi
dc.identifier.authororcidHuang, Jian§0000-0002-0862-1384
dc.identifier.authororcidWolsztynski, Eric§0000-0001-9770-9769
dc.identifier.citationWu, Q, Huang, J & Wolsztynski, E 2025, Clustering-based deconvolution of brain CT perfusion data. in 39th International Workshop on Statistical Modelling.
dc.identifier.otherORCID: /0000-0002-0862-1384/work/207324809
dc.identifier.otherORCID: /0000-0001-9770-9769/work/207325657
dc.identifier.urihttps://hdl.handle.net/10468/18595
dc.language.isoen
dc.rights© 2025, the Authors.
dc.rights.accessrightsopen access
dc.statusPeer reviewed
dc.subjectCT perfusion
dc.subjectKinetic analysis
dc.subjectClustering
dc.subjectStroke
dc.subject[Maths]
dc.subject[ComputerScience]
dc.subject[Insight]
dc.titleClustering-based deconvolution of brain CT perfusion dataen
dc.typeConference item
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
WuQi_Cluster_based_deconvolution_of_brain_CTP.pdf
Size:
1.76 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
Collections
Insight Research Ireland Centre for Data Analytics
School of Computer Science and Information Technology
School of Mathematical Sciences