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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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-

Název v anglickém jazyce

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

Popis výsledku anglicky

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-

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

<a href="/cs/project/GA18-15970S" target="_blank" >GA18-15970S: Optimální zpracování externí stochastické znalosti vyjádřené pomocí pravděpodobnostních distribucí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 32nd Irish Signals and Systems Conference (ISSC) 2021

ISBN

978-1-6654-3429-4

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

9467862

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Athlone

Datum konání akce

10. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—