Cargando…

Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography

BACKGROUND: Automatic coronary angiography (CAG) assessment may help in faster screening and diagnosis of stenosis in patients with atherosclerotic disease. We aimed to provide an end-to-end workflow that separates cases with normal or mild stenoses from those with higher stenosis severities to faci...

Descripción completa

Detalles Bibliográficos
Autores principales: Cong, Chao, Kato, Yoko, Vasconcellos, Henrique Doria De, Ostovaneh, Mohammad R., Lima, Joao A. C., Ambale-Venkatesh, Bharath
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9941145/
https://www.ncbi.nlm.nih.gov/pubmed/36824452
http://dx.doi.org/10.3389/fcvm.2023.944135
_version_ 1784891222616178688
author Cong, Chao
Kato, Yoko
Vasconcellos, Henrique Doria De
Ostovaneh, Mohammad R.
Lima, Joao A. C.
Ambale-Venkatesh, Bharath
author_facet Cong, Chao
Kato, Yoko
Vasconcellos, Henrique Doria De
Ostovaneh, Mohammad R.
Lima, Joao A. C.
Ambale-Venkatesh, Bharath
author_sort Cong, Chao
collection PubMed
description BACKGROUND: Automatic coronary angiography (CAG) assessment may help in faster screening and diagnosis of stenosis in patients with atherosclerotic disease. We aimed to provide an end-to-end workflow that separates cases with normal or mild stenoses from those with higher stenosis severities to facilitate safety screening of a large volume of the CAG images. METHODS: A deep learning-based end-to-end workflow was employed as follows: (1) Candidate frame selection from CAG videograms with Convolutional Neural Network (CNN) + Long Short Term Memory (LSTM) network, (2) Stenosis classification with Inception-v3 using 2 or 3 categories (<25%, >25%, and/or total occlusion) with and without redundancy training, and (3) Stenosis localization with two methods of class activation map (CAM) and anchor-based feature pyramid network (FPN). Overall 13,744 frames from 230 studies were used for the stenosis classification training and fourfold cross-validation for image-, artery-, and per-patient-level. For the stenosis localization training and fourfold cross-validation, 690 images with > 25% stenosis were used. RESULTS: Our model achieved an accuracy of 0.85, sensitivity of 0.96, and AUC of 0.86 in per-patient level stenosis classification. Redundancy training was effective to improve classification performance. Stenosis position localization was adequate with better quantitative results in anchor-based FPN model, achieving global-sensitivity for left coronary artery (LCA) and right coronary artery (RCA) of 0.68 and 0.70. CONCLUSION: We demonstrated a fully automatic end-to-end deep learning-based workflow that eliminates the vessel extraction and segmentation step in coronary artery stenosis classification and localization on CAG images. This tool may be useful to facilitate safety screening in high-volume centers and in clinical trial settings.
format Online
Article
Text
id pubmed-9941145
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-99411452023-02-22 Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography Cong, Chao Kato, Yoko Vasconcellos, Henrique Doria De Ostovaneh, Mohammad R. Lima, Joao A. C. Ambale-Venkatesh, Bharath Front Cardiovasc Med Cardiovascular Medicine BACKGROUND: Automatic coronary angiography (CAG) assessment may help in faster screening and diagnosis of stenosis in patients with atherosclerotic disease. We aimed to provide an end-to-end workflow that separates cases with normal or mild stenoses from those with higher stenosis severities to facilitate safety screening of a large volume of the CAG images. METHODS: A deep learning-based end-to-end workflow was employed as follows: (1) Candidate frame selection from CAG videograms with Convolutional Neural Network (CNN) + Long Short Term Memory (LSTM) network, (2) Stenosis classification with Inception-v3 using 2 or 3 categories (<25%, >25%, and/or total occlusion) with and without redundancy training, and (3) Stenosis localization with two methods of class activation map (CAM) and anchor-based feature pyramid network (FPN). Overall 13,744 frames from 230 studies were used for the stenosis classification training and fourfold cross-validation for image-, artery-, and per-patient-level. For the stenosis localization training and fourfold cross-validation, 690 images with > 25% stenosis were used. RESULTS: Our model achieved an accuracy of 0.85, sensitivity of 0.96, and AUC of 0.86 in per-patient level stenosis classification. Redundancy training was effective to improve classification performance. Stenosis position localization was adequate with better quantitative results in anchor-based FPN model, achieving global-sensitivity for left coronary artery (LCA) and right coronary artery (RCA) of 0.68 and 0.70. CONCLUSION: We demonstrated a fully automatic end-to-end deep learning-based workflow that eliminates the vessel extraction and segmentation step in coronary artery stenosis classification and localization on CAG images. This tool may be useful to facilitate safety screening in high-volume centers and in clinical trial settings. Frontiers Media S.A. 2023-02-07 /pmc/articles/PMC9941145/ /pubmed/36824452 http://dx.doi.org/10.3389/fcvm.2023.944135 Text en Copyright © 2023 Cong, Kato, Vasconcellos, Ostovaneh, Lima and Ambale-Venkatesh. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Cardiovascular Medicine
Cong, Chao
Kato, Yoko
Vasconcellos, Henrique Doria De
Ostovaneh, Mohammad R.
Lima, Joao A. C.
Ambale-Venkatesh, Bharath
Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
title Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
title_full Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
title_fullStr Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
title_full_unstemmed Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
title_short Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
title_sort deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography
topic Cardiovascular Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9941145/
https://www.ncbi.nlm.nih.gov/pubmed/36824452
http://dx.doi.org/10.3389/fcvm.2023.944135
work_keys_str_mv AT congchao deeplearningbasedendtoendautomatedstenosisclassificationandlocalizationoncathetercoronaryangiography
AT katoyoko deeplearningbasedendtoendautomatedstenosisclassificationandlocalizationoncathetercoronaryangiography
AT vasconcelloshenriquedoriade deeplearningbasedendtoendautomatedstenosisclassificationandlocalizationoncathetercoronaryangiography
AT ostovanehmohammadr deeplearningbasedendtoendautomatedstenosisclassificationandlocalizationoncathetercoronaryangiography
AT limajoaoac deeplearningbasedendtoendautomatedstenosisclassificationandlocalizationoncathetercoronaryangiography
AT ambalevenkateshbharath deeplearningbasedendtoendautomatedstenosisclassificationandlocalizationoncathetercoronaryangiography