Customized Handmade Pulmonary Valved Conduit Reconstruction for Children and Adult Patients Using Meta-Learning Based Intelligent Model

Chung-Dann Kan, Wei Ling Chen, Chia Hung Lin, Jieh-Neng Wang, Pong Jeu Lu, Ming Yao Chan, Jui Te Wu

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Percutaneous pulmonary valve implantation is an improved technique that is used to treat narrowed pulmonary valves or leaky pulmonary valves in patients with congenital heart disease. This technique represents a promising strategy to reduce surgical risk and operation. In clinical cases, commercial valve stents are sometimes not available for children or special subjects due to restrictions in stent size. Hence, the handmade pulmonary valved conduit provides a strategy to design stents with customized size for valve replacement. In this paper, we propose a meta-learning-based intelligent model to train an estimator (including two sub-estimators) to determine optimal trileaflet parameters for customized trileaflet valve reconstruction. This estimation model overcomes the problem of empirical parameter determination. The meta-learning model possesses learning-to-optimization capability for training generalized regression neural network by particle swarm optimization algorithm. Through incremental training patterns, this scheme can gradually enhance optimization to provide refined parameters for customized designs that can be applicable to individuals of all age groups. The customized handmade pulmonary valved conduit was validated by assessing the regurgitation fraction and the heart pump efficiency using an experimental cardiopulmonary circulation loop system.

Original languageEnglish
Pages (from-to)21381-21396
Number of pages16
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018 Mar 12

Fingerprint

Stents
Particle swarm optimization (PSO)
Pumps
Neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Kan, Chung-Dann ; Chen, Wei Ling ; Lin, Chia Hung ; Wang, Jieh-Neng ; Lu, Pong Jeu ; Chan, Ming Yao ; Wu, Jui Te. / Customized Handmade Pulmonary Valved Conduit Reconstruction for Children and Adult Patients Using Meta-Learning Based Intelligent Model. In: IEEE Access. 2018 ; Vol. 6. pp. 21381-21396.
@article{c74a40eb51a346828de4d774b521a537,
title = "Customized Handmade Pulmonary Valved Conduit Reconstruction for Children and Adult Patients Using Meta-Learning Based Intelligent Model",
abstract = "Percutaneous pulmonary valve implantation is an improved technique that is used to treat narrowed pulmonary valves or leaky pulmonary valves in patients with congenital heart disease. This technique represents a promising strategy to reduce surgical risk and operation. In clinical cases, commercial valve stents are sometimes not available for children or special subjects due to restrictions in stent size. Hence, the handmade pulmonary valved conduit provides a strategy to design stents with customized size for valve replacement. In this paper, we propose a meta-learning-based intelligent model to train an estimator (including two sub-estimators) to determine optimal trileaflet parameters for customized trileaflet valve reconstruction. This estimation model overcomes the problem of empirical parameter determination. The meta-learning model possesses learning-to-optimization capability for training generalized regression neural network by particle swarm optimization algorithm. Through incremental training patterns, this scheme can gradually enhance optimization to provide refined parameters for customized designs that can be applicable to individuals of all age groups. The customized handmade pulmonary valved conduit was validated by assessing the regurgitation fraction and the heart pump efficiency using an experimental cardiopulmonary circulation loop system.",
author = "Chung-Dann Kan and Chen, {Wei Ling} and Lin, {Chia Hung} and Jieh-Neng Wang and Lu, {Pong Jeu} and Chan, {Ming Yao} and Wu, {Jui Te}",
year = "2018",
month = "3",
day = "12",
doi = "10.1109/ACCESS.2018.2815599",
language = "English",
volume = "6",
pages = "21381--21396",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Customized Handmade Pulmonary Valved Conduit Reconstruction for Children and Adult Patients Using Meta-Learning Based Intelligent Model. / Kan, Chung-Dann; Chen, Wei Ling; Lin, Chia Hung; Wang, Jieh-Neng; Lu, Pong Jeu; Chan, Ming Yao; Wu, Jui Te.

In: IEEE Access, Vol. 6, 12.03.2018, p. 21381-21396.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Customized Handmade Pulmonary Valved Conduit Reconstruction for Children and Adult Patients Using Meta-Learning Based Intelligent Model

AU - Kan, Chung-Dann

AU - Chen, Wei Ling

AU - Lin, Chia Hung

AU - Wang, Jieh-Neng

AU - Lu, Pong Jeu

AU - Chan, Ming Yao

AU - Wu, Jui Te

PY - 2018/3/12

Y1 - 2018/3/12

N2 - Percutaneous pulmonary valve implantation is an improved technique that is used to treat narrowed pulmonary valves or leaky pulmonary valves in patients with congenital heart disease. This technique represents a promising strategy to reduce surgical risk and operation. In clinical cases, commercial valve stents are sometimes not available for children or special subjects due to restrictions in stent size. Hence, the handmade pulmonary valved conduit provides a strategy to design stents with customized size for valve replacement. In this paper, we propose a meta-learning-based intelligent model to train an estimator (including two sub-estimators) to determine optimal trileaflet parameters for customized trileaflet valve reconstruction. This estimation model overcomes the problem of empirical parameter determination. The meta-learning model possesses learning-to-optimization capability for training generalized regression neural network by particle swarm optimization algorithm. Through incremental training patterns, this scheme can gradually enhance optimization to provide refined parameters for customized designs that can be applicable to individuals of all age groups. The customized handmade pulmonary valved conduit was validated by assessing the regurgitation fraction and the heart pump efficiency using an experimental cardiopulmonary circulation loop system.

AB - Percutaneous pulmonary valve implantation is an improved technique that is used to treat narrowed pulmonary valves or leaky pulmonary valves in patients with congenital heart disease. This technique represents a promising strategy to reduce surgical risk and operation. In clinical cases, commercial valve stents are sometimes not available for children or special subjects due to restrictions in stent size. Hence, the handmade pulmonary valved conduit provides a strategy to design stents with customized size for valve replacement. In this paper, we propose a meta-learning-based intelligent model to train an estimator (including two sub-estimators) to determine optimal trileaflet parameters for customized trileaflet valve reconstruction. This estimation model overcomes the problem of empirical parameter determination. The meta-learning model possesses learning-to-optimization capability for training generalized regression neural network by particle swarm optimization algorithm. Through incremental training patterns, this scheme can gradually enhance optimization to provide refined parameters for customized designs that can be applicable to individuals of all age groups. The customized handmade pulmonary valved conduit was validated by assessing the regurgitation fraction and the heart pump efficiency using an experimental cardiopulmonary circulation loop system.

UR - http://www.scopus.com/inward/record.url?scp=85043779296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043779296&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2815599

DO - 10.1109/ACCESS.2018.2815599

M3 - Article

AN - SCOPUS:85043779296

VL - 6

SP - 21381

EP - 21396

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -