Bayesian Selective Transfer Learning for Patient-Specific Inference in Thyroid Radiotherapy

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F21%3A00549009" target="_blank" >RIV/67985556:_____/21:00549009 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/ISSC52156.2021.9467862" target="_blank" >http://dx.doi.org/10.1109/ISSC52156.2021.9467862</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ISSC52156.2021.9467862" target="_blank" >10.1109/ISSC52156.2021.9467862</a>

Result language
angličtina
Original language name
Bayesian Selective Transfer Learning for Patient-Specific Inference in Thyroid Radiotherapy
Original language description
This paper outlines a selective transfer approach for Bayesian estimation of patient-specific levels of radioiodine activity in the thyroid during the treatment of differentiated thyroid carcinoma. The work addresses some limitations of previous approaches which involved generic, non-selective transfer of archival data. It is proposed that improvements in patient-specific inferences may be space-conditioned, probabilistic data predictor from the sub-population to the specific patient. In addition, the transfer times are chosen to complement the patient's own data. Currently the proposed method yields positive transfer, with stable performance improvements up to 34%. Although this is found to be 9% below the performance of the current state-of-the-art, the proposed method is significant in that it can be applied to other transfer learning applications where inhomogeneous parameter knowledge is available in the source feature space.achieved via transferring external population knowledge selectively. This involves matching the patient to a similar sub-population based on available metadata and formally transferring a feature-
Czech name
—
Czech description
—

Project
<a href="/en/project/GA18-15970S" target="_blank" >GA18-15970S: Optimal Distributional Design for External Stochastic Knowledge Processing</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 32nd Irish Signals and Systems Conference (ISSC) 2021
ISBN
978-1-6654-3429-4
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
9467862
Publisher name
IEEE
Place of publication
Piscataway
Event location
Athlone
Event date
Jun 10, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)