View in EDS

Comparing various AI approaches to traditional quantitative assessment of the myocardial perfusion in [82Rb] PET for MACE prediction

Saved in:
Bibliographic Details
Title: Comparing various AI approaches to traditional quantitative assessment of the myocardial perfusion in [82Rb] PET for MACE prediction
Authors: Bors, S., Abler, D., Dietz, M., Andrearczyk, V., Fageot, J., Nicod-Lalonde, M., Schaefer, N., DeKemp, R., Kamani, C.H., Prior, J.O., Depeursinge, A.
Source: Sci Rep
Scientific Reports, Vol 14, Iss 1, Pp 1-13 (2024)
Scientific reports, vol. 14, no. 1, pp. 9644
Publisher Information: Springer Science and Business Media LLC, 2024.
Publication Year: 2024
Subject Terms: Male, Science, Myocardial Perfusion Imaging, Middle Aged, Prognosis, Article, 3. Good health, Artificial Intelligence, Cardiovascular Diseases, Positron-Emission Tomography, Coronary Circulation, Medicine, Humans, Female, Myocardial Perfusion Imaging/methods, Positron-Emission Tomography/methods, Aged, Rubidium Radioisotopes, Neural Networks, Computer, Cardiovascular Diseases/diagnostic imaging, Cardiovascular Diseases/diagnosis
Description: Assessing the individual risk of Major Adverse Cardiac Events (MACE) is of major importance as cardiovascular diseases remain the leading cause of death worldwide. Quantitative Myocardial Perfusion Imaging (MPI) parameters such as stress Myocardial Blood Flow (sMBF) or Myocardial Flow Reserve (MFR) constitutes the gold standard for prognosis assessment. We propose a systematic investigation of the value of Artificial Intelligence (AI) to leverage [$$^{82}$$ 82 Rb] Silicon PhotoMultiplier (SiPM) PET MPI for MACE prediction. We establish a general pipeline for AI model validation to assess and compare the performance of global (i.e. average of the entire MPI signal), regional (17 segments), radiomics and Convolutional Neural Network (CNN) models leveraging various MPI signals on a dataset of 234 patients. Results showed that all regional AI models significantly outperformed the global model ($$p p < 0.001 ), where the best AUC of 73.9% (CI 72.5–75.3) was obtained with a CNN model. A regional AI model based on MBF averages from 17 segments fed to a Logistic Regression (LR) constituted an excellent trade-off between model simplicity and performance, achieving an AUC of 73.4% (CI 72.3–74.7). A radiomics model based on intensity features revealed that the global average was the least important feature when compared to other aggregations of the MPI signal over the myocardium. We conclude that AI models can allow better personalized prognosis assessment for MACE.
Document Type: Article
Other literature type
File Description: application/pdf
Language: English
ISSN: 2045-2322
DOI: 10.1038/s41598-024-60095-6
Access URL: https://pubmed.ncbi.nlm.nih.gov/38671059
https://doaj.org/article/04d8552567144e6b9f4b562be9a2f82f
http://nbn-resolving.org/urn/resolver.pl?urn=urn:nbn:ch:serval-BIB_6229F1E6792C6
https://serval.unil.ch/resource/serval:BIB_6229F1E6792C.P001/REF.pdf
https://serval.unil.ch/notice/serval:BIB_6229F1E6792C
Rights: CC BY
Accession Number: edsair.doi.dedup.....c54bde44cf00fd5bc0e6320f62cd4a7e
Database: OpenAIRE
Description
Abstract:Assessing the individual risk of Major Adverse Cardiac Events (MACE) is of major importance as cardiovascular diseases remain the leading cause of death worldwide. Quantitative Myocardial Perfusion Imaging (MPI) parameters such as stress Myocardial Blood Flow (sMBF) or Myocardial Flow Reserve (MFR) constitutes the gold standard for prognosis assessment. We propose a systematic investigation of the value of Artificial Intelligence (AI) to leverage [$$^{82}$$ 82 Rb] Silicon PhotoMultiplier (SiPM) PET MPI for MACE prediction. We establish a general pipeline for AI model validation to assess and compare the performance of global (i.e. average of the entire MPI signal), regional (17 segments), radiomics and Convolutional Neural Network (CNN) models leveraging various MPI signals on a dataset of 234 patients. Results showed that all regional AI models significantly outperformed the global model ($$p p < 0.001 ), where the best AUC of 73.9% (CI 72.5–75.3) was obtained with a CNN model. A regional AI model based on MBF averages from 17 segments fed to a Logistic Regression (LR) constituted an excellent trade-off between model simplicity and performance, achieving an AUC of 73.4% (CI 72.3–74.7). A radiomics model based on intensity features revealed that the global average was the least important feature when compared to other aggregations of the MPI signal over the myocardium. We conclude that AI models can allow better personalized prognosis assessment for MACE.
ISSN:20452322
DOI:10.1038/s41598-024-60095-6