loading
Documents

Research.Publish.Connect.

Paper

Authors: Patricio Astudillo 1 ; Peter Mortier 1 ; Matthieu De Beule 1 and Francis Wyffels 2

Affiliations: 1 FEops, Technologiepark 122, Zwijnaarde 9052, Belgium ; 2 Department of Electronics and Information Systems, UGent - imec, Technologiepark 126, Zwijnaarde 9052, Belgium

ISBN: 978-989-758-398-8

ISSN: 2184-4305

Keyword(s): Biomedical Informatics, Cardiography, Medical Information Systems, Semi-supervised Learning.

Abstract: Transcatheter aortic valve implantation (TAVI) is associated with conduction abnormalities and the mechanical interaction between the prosthesis and the atrioventricular (AV) conduction path cause these life-threatening arrhythmias. Pre-operative assessment of the location of the AV conduction path can help to understand the risk of post-TAVI conduction abnormalities. As the AV conduction path is not visible on cardiac CT, the inferior border of the membranous septum can be used as an anatomical landmark. Detecting this border automatically, accurately and efficiently would save operator time and thus benefit pre-operative planning. This preliminary study was performed to identify the feasibility of 3D landmark detection in cardiac CT images with curriculum deep Q-learning. In this study, curriculum learning was used to gradually teach an artificial agent to detect this anatomical landmark from cardiac CT. This agent was equipped with a small field of view and burdened with a large ac tion-space. Moreover, we introduced two novel action-selection strategies: α-decay and action-dropout. We compared these two strategies to the already established ε-decay strategy and observed that α-decay yielded the most accurate results. Limited computational resources were used to ensure reproducibility. In order to maximize the amount of patient data, the method was cross-validated with k-folding for all three action-selection strategies. An inter-operator variability study was conducted to assess the accuracy of the method. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.235.172.213

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Astudillo, P.; Mortier, P.; De Beule, M. and Wyffels, F. (2020). Curriculum Deep Reinforcement Learning with Different Exploration Strategies: A Feasibility Study on Cardiac Landmark Detection.In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2 BIOIMAGING: BIOIMAGING, ISBN 978-989-758-398-8, ISSN 2184-4305, pages 37-45. DOI: 10.5220/0008948900370045

@conference{bioimaging20,
author={Patricio Astudillo. and Peter Mortier. and Matthieu De Beule. and Francis Wyffels.},
title={Curriculum Deep Reinforcement Learning with Different Exploration Strategies: A Feasibility Study on Cardiac Landmark Detection},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2 BIOIMAGING: BIOIMAGING,},
year={2020},
pages={37-45},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008948900370045},
isbn={978-989-758-398-8},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2 BIOIMAGING: BIOIMAGING,
TI - Curriculum Deep Reinforcement Learning with Different Exploration Strategies: A Feasibility Study on Cardiac Landmark Detection
SN - 978-989-758-398-8
AU - Astudillo, P.
AU - Mortier, P.
AU - De Beule, M.
AU - Wyffels, F.
PY - 2020
SP - 37
EP - 45
DO - 10.5220/0008948900370045

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.