Automatic Quantitative Coronary Analysis Based on Deep Learning
As a core technique to quantitatively assess the stenosis severity of coronary arteries, quantitative coronary analysis (QCA) is urgently supposed to become more automated and intelligent, especially for regions lacking expertise and technology. The existing QCA methods highly depend on manual opera...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/5/2975 |
_version_ | 1797615770729971712 |
---|---|
author | Xuqing Liu Xiaofei Wang Donghao Chen Honggang Zhang |
author_facet | Xuqing Liu Xiaofei Wang Donghao Chen Honggang Zhang |
author_sort | Xuqing Liu |
collection | DOAJ |
description | As a core technique to quantitatively assess the stenosis severity of coronary arteries, quantitative coronary analysis (QCA) is urgently supposed to become more automated and intelligent, especially for regions lacking expertise and technology. The existing QCA methods highly depend on manual operation, which is time-consuming and subject to personal experience. This study innovatively proposes a fully automatic QCA workflow based on artificial intelligence (AI-QCA), which can quickly and accurately make a quantitative assessment of stenosis severity. The whole AI-QCA workflow mainly consists of three parts: the boundary-aware segmentation on the coronary angiogram (CAG) images, the AI-enabled coronary artery tree construction, and the diameter fitting and stenosis detection. Experiments show that the precision, recall, and F1 score of the segmentation, evaluated on 1322 CAGs, are 0.866, 0.897, and 0.879, respectively. Furthermore, the RMSE between diameter stenosis assessed by AI-QCA and manual QCA served by senior experts, evaluated on 249 CAGs, is 0.064, and the Pearson coefficient is 0.765. Meanwhile, the operation time can be reduced from tens of minutes to several seconds by AI-QCA. As a conclusion, the proposed AI-QCA is able to quickly quantify stenosis parameters as accurately as senior experts, which is significant for the intelligent diagnosis and treatment of coronary artery disease. |
first_indexed | 2024-03-11T07:30:26Z |
format | Article |
id | doaj.art-219090ab12f9449da0e4d05a24ef5915 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T07:30:26Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-219090ab12f9449da0e4d05a24ef59152023-11-17T07:17:36ZengMDPI AGApplied Sciences2076-34172023-02-01135297510.3390/app13052975Automatic Quantitative Coronary Analysis Based on Deep LearningXuqing Liu0Xiaofei Wang1Donghao Chen2Honggang Zhang3School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaAs a core technique to quantitatively assess the stenosis severity of coronary arteries, quantitative coronary analysis (QCA) is urgently supposed to become more automated and intelligent, especially for regions lacking expertise and technology. The existing QCA methods highly depend on manual operation, which is time-consuming and subject to personal experience. This study innovatively proposes a fully automatic QCA workflow based on artificial intelligence (AI-QCA), which can quickly and accurately make a quantitative assessment of stenosis severity. The whole AI-QCA workflow mainly consists of three parts: the boundary-aware segmentation on the coronary angiogram (CAG) images, the AI-enabled coronary artery tree construction, and the diameter fitting and stenosis detection. Experiments show that the precision, recall, and F1 score of the segmentation, evaluated on 1322 CAGs, are 0.866, 0.897, and 0.879, respectively. Furthermore, the RMSE between diameter stenosis assessed by AI-QCA and manual QCA served by senior experts, evaluated on 249 CAGs, is 0.064, and the Pearson coefficient is 0.765. Meanwhile, the operation time can be reduced from tens of minutes to several seconds by AI-QCA. As a conclusion, the proposed AI-QCA is able to quickly quantify stenosis parameters as accurately as senior experts, which is significant for the intelligent diagnosis and treatment of coronary artery disease.https://www.mdpi.com/2076-3417/13/5/2975qantitative coronary analysisdeep learningvessel segmentationcoronary angiogramartificial intelligencevessel tree |
spellingShingle | Xuqing Liu Xiaofei Wang Donghao Chen Honggang Zhang Automatic Quantitative Coronary Analysis Based on Deep Learning Applied Sciences qantitative coronary analysis deep learning vessel segmentation coronary angiogram artificial intelligence vessel tree |
title | Automatic Quantitative Coronary Analysis Based on Deep Learning |
title_full | Automatic Quantitative Coronary Analysis Based on Deep Learning |
title_fullStr | Automatic Quantitative Coronary Analysis Based on Deep Learning |
title_full_unstemmed | Automatic Quantitative Coronary Analysis Based on Deep Learning |
title_short | Automatic Quantitative Coronary Analysis Based on Deep Learning |
title_sort | automatic quantitative coronary analysis based on deep learning |
topic | qantitative coronary analysis deep learning vessel segmentation coronary angiogram artificial intelligence vessel tree |
url | https://www.mdpi.com/2076-3417/13/5/2975 |
work_keys_str_mv | AT xuqingliu automaticquantitativecoronaryanalysisbasedondeeplearning AT xiaofeiwang automaticquantitativecoronaryanalysisbasedondeeplearning AT donghaochen automaticquantitativecoronaryanalysisbasedondeeplearning AT honggangzhang automaticquantitativecoronaryanalysisbasedondeeplearning |