Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Prediction of obstructive coronary artery disease from myocardial perfusion scintigraphy using deep neural networks

Arvidsson, Ida LU orcid ; Overgaard, Niels Christian LU ; Aström, Kalle LU orcid ; Heyden, Anders LU orcid ; Figueroa, Miguel Ochoa ; Rose, Jeronimo Frias and Davidsson, Anette (2020) 25th International Conference on Pattern Recognition, ICPR 2020 In Proceedings - International Conference on Pattern Recognition p.4442-4449
Abstract

For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data... (More)

For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2020 25th International Conference on Pattern Recognition (ICPR)
series title
Proceedings - International Conference on Pattern Recognition
article number
9412674
pages
8 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
25th International Conference on Pattern Recognition, ICPR 2020
conference location
Virtual, Milan, Italy
conference dates
2021-01-10 - 2021-01-15
external identifiers
  • scopus:85103686647
ISSN
1051-4651
ISBN
9781728188089
DOI
10.1109/ICPR48806.2021.9412674
project
Deep learning based evaluation of coronary artery disease and estimation of quantitative coronary angiography using myocardial perfusion imaging
language
English
LU publication?
yes
additional info
Funding Information: ACKNOWLEDGMENT The authors would like to thank AIDA/Medtech4Health for funding. Publisher Copyright: © 2020 IEEE
id
d3b98c37-485d-416c-8acc-4260d432fdb6
date added to LUP
2021-11-29 08:10:45
date last changed
2024-08-11 02:30:06
@inproceedings{d3b98c37-485d-416c-8acc-4260d432fdb6,
  abstract     = {{<p>For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.</p>}},
  author       = {{Arvidsson, Ida and Overgaard, Niels Christian and Aström, Kalle and Heyden, Anders and Figueroa, Miguel Ochoa and Rose, Jeronimo Frias and Davidsson, Anette}},
  booktitle    = {{2020 25th International Conference on Pattern Recognition (ICPR)}},
  isbn         = {{9781728188089}},
  issn         = {{1051-4651}},
  language     = {{eng}},
  pages        = {{4442--4449}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{Proceedings - International Conference on Pattern Recognition}},
  title        = {{Prediction of obstructive coronary artery disease from myocardial perfusion scintigraphy using deep neural networks}},
  url          = {{http://dx.doi.org/10.1109/ICPR48806.2021.9412674}},
  doi          = {{10.1109/ICPR48806.2021.9412674}},
  year         = {{2020}},
}