Simulator-generated training datasets as an alternative to using patient data for machine learning: An example in myocardial segmentation with MRI.


Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
Jan 2021
Historique:
received: 03 06 2020
accepted: 21 10 2020
pubmed: 9 11 2020
medline: 15 5 2021
entrez: 8 11 2020
Statut: ppublish

Résumé

Supervised Machine Learning techniques have shown significant potential in medical image analysis. However, the training data that need to be collected for these techniques in the field of MRI 1) may not be available, 2) may be available but the size is small, 3) may be available but not representative and 4) may be available but with weak labels. The aim of this study was to overcome these limitations through advanced MR simulations on a realistic computer model of human anatomy without using a real MRI scanner, without scanning patients and without having personnel and the associated expenses. The 4D-XCAT model was used with the coreMRI simulation platform for generating artificial short-axis MR-images for training a neural-network to automatic delineate the LV endocardium and epicardium. Its performance was assessed on real MR-images acquired from eight healthy volunteers. The neural-network was also trained on real MR-images from a publicly available dataset and its performance was assessed on the same volunteers' data. The proposed solution demonstrated a performance of 94% (endocardium) and 90% DICE (epicardium) in real mid-ventricular slices, whereas a 10% addition of real MR-images in the artificial training dataset increased the performance to 97% DICE. The use of artificial MR-images that cover the entire LV yielded 85% (endocardium) and 88% DICE (epicardium) when combined with real MR data with an 80%-20% mix respectively. This study suggests a low-cost solution for constructing artificial training datasets for supervised learning techniques in the field of MR by using advanced MR simulations without the use of a real MRI scanner, without scanning patients and without having to use specialized personnel, such as technologists and radiologists.

Sections du résumé

BACKGROUND AND OBJECTIVE OBJECTIVE
Supervised Machine Learning techniques have shown significant potential in medical image analysis. However, the training data that need to be collected for these techniques in the field of MRI 1) may not be available, 2) may be available but the size is small, 3) may be available but not representative and 4) may be available but with weak labels. The aim of this study was to overcome these limitations through advanced MR simulations on a realistic computer model of human anatomy without using a real MRI scanner, without scanning patients and without having personnel and the associated expenses.
METHODS METHODS
The 4D-XCAT model was used with the coreMRI simulation platform for generating artificial short-axis MR-images for training a neural-network to automatic delineate the LV endocardium and epicardium. Its performance was assessed on real MR-images acquired from eight healthy volunteers. The neural-network was also trained on real MR-images from a publicly available dataset and its performance was assessed on the same volunteers' data.
RESULTS RESULTS
The proposed solution demonstrated a performance of 94% (endocardium) and 90% DICE (epicardium) in real mid-ventricular slices, whereas a 10% addition of real MR-images in the artificial training dataset increased the performance to 97% DICE. The use of artificial MR-images that cover the entire LV yielded 85% (endocardium) and 88% DICE (epicardium) when combined with real MR data with an 80%-20% mix respectively.
CONCLUSIONS CONCLUSIONS
This study suggests a low-cost solution for constructing artificial training datasets for supervised learning techniques in the field of MR by using advanced MR simulations without the use of a real MRI scanner, without scanning patients and without having to use specialized personnel, such as technologists and radiologists.

Identifiants

pubmed: 33160692
pii: S0169-2607(20)31650-3
doi: 10.1016/j.cmpb.2020.105817
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

105817

Informations de copyright

Copyright © 2020. Published by Elsevier B.V.

Déclaration de conflit d'intérêts

Competing interests CGX and AHA are co-founders of Corsmed AB.

Auteurs

Christos G Xanthis (CG)

Laboratory of Computing, Medical Informatics and Biomedical-Imaging Technologies, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece; Department of Clinical Physiology, Clinical Sciences, Lund University and Lund University Hospital, Lund, Sweden. Electronic address: cxanthis@gmail.com.

Dimitrios Filos (D)

Laboratory of Computing, Medical Informatics and Biomedical-Imaging Technologies, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece. Electronic address: dimfilos@auth.gr.

Kostas Haris (K)

Laboratory of Computing, Medical Informatics and Biomedical-Imaging Technologies, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece. Electronic address: konharis@gmail.com.

Anthony H Aletras (AH)

Laboratory of Computing, Medical Informatics and Biomedical-Imaging Technologies, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece; Department of Clinical Physiology, Clinical Sciences, Lund University and Lund University Hospital, Lund, Sweden. Electronic address: aletras@hotmail.com.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH