Stroke Diagnosis from Field-Cycling Imaging using Machine Learning

Adamu Ali-Gombe; Nicholas Senn; Lionel Broche; Vasiliki Mallikourti; James Ross; Gordon Waiter; Mary Macleod

doi:10.1177/17474930251379781

Stroke Diagnosis from Field-Cycling Imaging using Machine Learning

Adamu Ali-Gombe^* (Corresponding Author)
, Nicholas Senn
, Lionel Broche
, Vasiliki Mallikourti
, James Ross
, Gordon Waiter
, Mary Macleod

^*Corresponding author for this work

Research output: Contribution to journal › Abstract › peer-review

Abstract

Field-Cycling Imaging (FCI) is a new type of scan where the magnetic field can be varied. We have demonstrated its potential in stroke diagnosis using a novel biomarker, R1 dispersion. This current study tested whether a machine learning model can detect stroke lesions in FCI images and whether the model can distinguish intracerebral haemorrhage (ICH) from ischaemic stroke (IS)...

Original language	English
Pages (from-to)	41
Number of pages	1
Journal	International Journal of Stroke
Volume	20
Issue number	Issue 3_suppl
DOIs	https://doi.org/10.1177/17474930251379781
Publication status	Published - 10 Nov 2025
Event	UK Stroke Forum - Aberdeen Duration: 25 Nov 2025 → 27 Nov 2025

Access to Document

10.1177/17474930251379781Licence: Unspecified

Aberdeen Biomedical Imaging Centre
Waiter, G. (Manager) & Morris, T. (Facilities Co-ordinator)
Aberdeen Biomedical Imaging Centre
Research Facilities: Facility

Cite this

@article{6cbcfdf389b74cb2a69cdff2e76b3761,

title = "Stroke Diagnosis from Field-Cycling Imaging using Machine Learning",

abstract = "Field-Cycling Imaging (FCI) is a new type of scan where the magnetic field can be varied. We have demonstrated its potential in stroke diagnosis using a novel biomarker, R1 dispersion. This current study tested whether a machine learning model can detect stroke lesions in FCI images and whether the model can distinguish intracerebral haemorrhage (ICH) from ischaemic stroke (IS)...",

author = "Adamu Ali-Gombe and Nicholas Senn and Lionel Broche and Vasiliki Mallikourti and James Ross and Gordon Waiter and Mary Macleod",

year = "2025",

month = nov,

day = "10",

doi = "10.1177/17474930251379781",

language = "English",

volume = "20",

pages = "41",

journal = "International Journal of Stroke",

issn = "1747-4930",

publisher = "SAGE Publications Ltd",

number = "Issue 3\_suppl",

note = "UK Stroke Forum ; Conference date: 25-11-2025 Through 27-11-2025",

}

TY - JOUR

T1 - Stroke Diagnosis from Field-Cycling Imaging using Machine Learning

AU - Ali-Gombe, Adamu

AU - Senn, Nicholas

AU - Broche, Lionel

AU - Mallikourti, Vasiliki

AU - Ross, James

AU - Waiter, Gordon

AU - Macleod, Mary

PY - 2025/11/10

Y1 - 2025/11/10

N2 - Field-Cycling Imaging (FCI) is a new type of scan where the magnetic field can be varied. We have demonstrated its potential in stroke diagnosis using a novel biomarker, R1 dispersion. This current study tested whether a machine learning model can detect stroke lesions in FCI images and whether the model can distinguish intracerebral haemorrhage (ICH) from ischaemic stroke (IS)...

AB - Field-Cycling Imaging (FCI) is a new type of scan where the magnetic field can be varied. We have demonstrated its potential in stroke diagnosis using a novel biomarker, R1 dispersion. This current study tested whether a machine learning model can detect stroke lesions in FCI images and whether the model can distinguish intracerebral haemorrhage (ICH) from ischaemic stroke (IS)...

U2 - 10.1177/17474930251379781

DO - 10.1177/17474930251379781

M3 - Abstract

SN - 1747-4930

VL - 20

SP - 41

JO - International Journal of Stroke

JF - International Journal of Stroke

IS - Issue 3_suppl

T2 - UK Stroke Forum

Y2 - 25 November 2025 through 27 November 2025

ER -

Stroke Diagnosis from Field-Cycling Imaging using Machine Learning

Abstract

Access to Document

Fingerprint

Equipment

Aberdeen Biomedical Imaging Centre

Cite this