Identification of Thyroid Gland Activity in Radioiodine Therapy
File Type:
PDFItem Type:
Journal ArticleDate:
2017Access:
openAccessCitation:
Jirsa, L., Varga, F. & Quinn, A., Identification of Thyroid Gland Activity in Radioiodine Therapy, 2017, Informatics in Medicine Unlocked, 7Download Item:
Abstract:
The Bayesian identification of a linear regression model (called the biphasic model) for time dependence of
thyroid gland activity in
131
I radioiodine therapy is presented. Prior knowledge is elicited via hard parameter
constraints and via the merging of external information from an archive of patient records. This prior
regularization is shown to be crucial in the reported context, where data typically comprise only two or three
high-noise measurements. The posterior distribution is simulated via a Langevin di
ff
usion algorithm, whose
optimization for the thyroid activity application is explained. Excellent patient-speci
fi
c predictions of thyroid
activity are reported. The posterior inference of the patient-speci
fi
c total radiation dose is computed, allowing
the uncertainty of the dose to be quanti
fi
ed in a consistent form. The relevance of this work in clinical practice is
explained
URI:
https://www.sciencedirect.com/science/article/pii/S2352914816300338?via%3Dihubhttps://doi.org/10.1016/j.imu.2017.02.004
http://hdl.handle.net/2262/90794
Sponsor
Grant Number
science foundation ireland
10/ RFP/2877
Author's Homepage:
http://people.tcd.ie/aquinnDescription:
PUBLISHEDType of material:
Journal ArticleURI:
https://www.sciencedirect.com/science/article/pii/S2352914816300338?via%3Dihubhttps://doi.org/10.1016/j.imu.2017.02.004
http://hdl.handle.net/2262/90794
Series/Report no:
Informatics in Medicine Unlocked;7;
Availability:
Full text availableMetadata
Show full item recordLicences: