Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Neumann, Dominik [VerfasserIn]   i
 Mansi, Tommaso [VerfasserIn]   i
 Itu, Lucian [VerfasserIn]   i
 Georgescu, Bogdan [VerfasserIn]   i
 Kayvanpour, Elham [VerfasserIn]   i
 Sedaghat-Hamedani, Farbod [VerfasserIn]   i
 Amr, Ali [VerfasserIn]   i
 Haas, Jan [VerfasserIn]   i
 Katus, Hugo [VerfasserIn]   i
 Meder, Benjamin [VerfasserIn]   i
 Steidl, Stefan [VerfasserIn]   i
 Hornegger, Joachim [VerfasserIn]   i
 Comaniciu, Dorin [VerfasserIn]   i
Titel:A self-taught artificial agent for multi-physics computational model personalization
Verf.angabe:Dominik Neumann, Tommaso Mansi, Lucian Itu, Bogdan Georgescu, Elham Kayvanpour, Farbod Sedaghat-Hamedani, Ali Amr, Jan Haas, Hugo Katus, Benjamin Meder, Stefan Steidl, Joachim Hornegger, Dorin Comaniciu
E-Jahr:2016
Jahr:21 April 2016
Umfang:13 S.
Fussnoten:Gesehen am 09.10.2020
Titel Quelle:Enthalten in: Medical image analysis
Ort Quelle:Amsterdam [u.a.] : Elsevier Science, 1996
Jahr Quelle:2016
Band/Heft Quelle:34(2016), Seite 52-64
ISSN Quelle:1361-8423
Abstract:Personalization is the process of fitting a model to patient data, a critical step towards application of multi-physics computational models in clinical practice. Designing robust personalization algorithms is often a tedious, time-consuming, model- and data-specific process. We propose to use artificial intelligence concepts to learn this task, inspired by how human experts manually perform it. The problem is reformulated in terms of reinforcement learning. In an off-line phase, Vito, our self-taught artificial agent, learns a representative decision process model through exploration of the computational model: it learns how the model behaves under change of parameters. The agent then automatically learns an optimal strategy for on-line personalization. The algorithm is model-independent; applying it to a new model requires only adjusting few hyper-parameters of the agent and defining the observations to match. The full knowledge of the model itself is not required. Vito was tested in a synthetic scenario, showing that it could learn how to optimize cost functions generically. Then Vito was applied to the inverse problem of cardiac electrophysiology and the personalization of a whole-body circulation model. The obtained results suggested that Vito could achieve equivalent, if not better goodness of fit than standard methods, while being more robust (up to 11% higher success rates) and with faster (up to seven times) convergence rate. Our artificial intelligence approach could thus make personalization algorithms generalizable and self-adaptable to any patient and any model.
DOI:doi:10.1016/j.media.2016.04.003
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

Volltext ; Verlag: https://doi.org/10.1016/j.media.2016.04.003
 Volltext: http://www.sciencedirect.com/science/article/pii/S1361841516300214
 DOI: https://doi.org/10.1016/j.media.2016.04.003
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:Artificial intelligence
 Computational modeling
 Model personalization
 Reinforcement learning
K10plus-PPN:1735248533
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/68646636   QR-Code
zum Seitenanfang