Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification
This study analyzes CZT SPECT myocardial perfusion images that are collected at Chang Gung Memorial Hospital, Kaohsiung Medical Center in Kaohsiung. This study focuses on the classification of myocardial perfusion images for coronary heart diseases by convolutional neural network techniques. In thes...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/2/514 |
id |
doaj-8365d89488b443e3a7b6b7f7bff33110 |
---|---|
record_format |
Article |
spelling |
doaj-8365d89488b443e3a7b6b7f7bff331102021-01-08T00:00:16ZengMDPI AGApplied Sciences2076-34172021-01-011151451410.3390/app11020514Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated QuantificationJui-Jen Chen0Ting-Yi Su1Wei-Shiang Chen2Yen-Hsiang Chang3Henry Horng-Shing Lu4Department of Nuclear Medicine, Chang Gung Memorial Hospital, Kaohsiung Medical Center, Chang Gung University College of Medicine, Kaohsiung 833, TaiwanInstitute of Statistics, National Chiao Tung University, Hsinchu 300, TaiwanInstitute of Statistics, National Chiao Tung University, Hsinchu 300, TaiwanDepartment of Nuclear Medicine, Chang Gung Memorial Hospital, Kaohsiung Medical Center, Chang Gung University College of Medicine, Kaohsiung 833, TaiwanInstitute of Statistics, National Chiao Tung University, Hsinchu 300, TaiwanThis study analyzes CZT SPECT myocardial perfusion images that are collected at Chang Gung Memorial Hospital, Kaohsiung Medical Center in Kaohsiung. This study focuses on the classification of myocardial perfusion images for coronary heart diseases by convolutional neural network techniques. In these gray scale images, heart blood flow distribution contains the most important features. Therefore, data-driven preprocessing is developed to extract the area of interest. After removing the surrounding noise, the three-dimensional convolutional neural network model is utilized to classify whether the patient has coronary heart diseases or not. The prediction accuracy, sensitivity, and specificity are 87.64%, 81.58%, and 92.16%. The prototype system will greatly reduce the time required for physician image interpretation and write reports. It can assist clinical experts in diagnosing coronary heart diseases accurately in practice.https://www.mdpi.com/2076-3417/11/2/514cardiovascular diseasesmyocardial perfusion imagemachine learningconvolutional neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jui-Jen Chen Ting-Yi Su Wei-Shiang Chen Yen-Hsiang Chang Henry Horng-Shing Lu |
spellingShingle |
Jui-Jen Chen Ting-Yi Su Wei-Shiang Chen Yen-Hsiang Chang Henry Horng-Shing Lu Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification Applied Sciences cardiovascular diseases myocardial perfusion image machine learning convolutional neural network |
author_facet |
Jui-Jen Chen Ting-Yi Su Wei-Shiang Chen Yen-Hsiang Chang Henry Horng-Shing Lu |
author_sort |
Jui-Jen Chen |
title |
Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification |
title_short |
Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification |
title_full |
Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification |
title_fullStr |
Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification |
title_full_unstemmed |
Convolutional Neural Network in the Evaluation of Myocardial Ischemia from CZT SPECT Myocardial Perfusion Imaging: Comparison to Automated Quantification |
title_sort |
convolutional neural network in the evaluation of myocardial ischemia from czt spect myocardial perfusion imaging: comparison to automated quantification |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-01-01 |
description |
This study analyzes CZT SPECT myocardial perfusion images that are collected at Chang Gung Memorial Hospital, Kaohsiung Medical Center in Kaohsiung. This study focuses on the classification of myocardial perfusion images for coronary heart diseases by convolutional neural network techniques. In these gray scale images, heart blood flow distribution contains the most important features. Therefore, data-driven preprocessing is developed to extract the area of interest. After removing the surrounding noise, the three-dimensional convolutional neural network model is utilized to classify whether the patient has coronary heart diseases or not. The prediction accuracy, sensitivity, and specificity are 87.64%, 81.58%, and 92.16%. The prototype system will greatly reduce the time required for physician image interpretation and write reports. It can assist clinical experts in diagnosing coronary heart diseases accurately in practice. |
topic |
cardiovascular diseases myocardial perfusion image machine learning convolutional neural network |
url |
https://www.mdpi.com/2076-3417/11/2/514 |
work_keys_str_mv |
AT juijenchen convolutionalneuralnetworkintheevaluationofmyocardialischemiafromcztspectmyocardialperfusionimagingcomparisontoautomatedquantification AT tingyisu convolutionalneuralnetworkintheevaluationofmyocardialischemiafromcztspectmyocardialperfusionimagingcomparisontoautomatedquantification AT weishiangchen convolutionalneuralnetworkintheevaluationofmyocardialischemiafromcztspectmyocardialperfusionimagingcomparisontoautomatedquantification AT yenhsiangchang convolutionalneuralnetworkintheevaluationofmyocardialischemiafromcztspectmyocardialperfusionimagingcomparisontoautomatedquantification AT henryhorngshinglu convolutionalneuralnetworkintheevaluationofmyocardialischemiafromcztspectmyocardialperfusionimagingcomparisontoautomatedquantification |
_version_ |
1724345958251102208 |