Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study

Journal of Digital Imaging · 8 authors, 9 centres

AI SUMMARY

FIDELITY 100%

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

The best-performing fine KNN model achieved an accuracy of 0.84 for classifying patients into three outcome classes.

Full summary

549 CHARS

Seven radiomic features, primarily Gabor, first-order, GLCM, and NGTDM types, were selected and used to train seven classifiers to predict three classes of EF outcome. The fine k-nearest neighbors (KNN) classifier performed best with an accuracy of 0.84, sensitivity of 0.75, and specificity of 0.87. Limitations include the small, single-center dataset and class imbalance. The study suggests radiomic features from MPI-SPECT may predict revascularization outcome, but external validation and larger, multi-center studies are needed for robustness.

STUDY TYPE

other

SPECIALTY

cardiology

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10407007

Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study

Journal of Digital Imaging

READ THE FULL PAPER

ABSTRACT

Abstract In this study, the ability of radiomics features extracted from myocardial perfusion imaging with SPECT (MPI-SPECT) was investigated for the prediction of ejection fraction (EF) post-percutaneous coronary intervention (PCI) treatment. A total of 52 patients who had undergone pre-PCI MPI-SPECT were enrolled in this study. After normalization of the images, features were extracted from the left ventricle, initially automatically segmented by k-means and active contour methods, and finally edited and approved by an expert radiologist. More than 1700 2D and 3D radiomics features were extracted from each patient’s scan. A cross-combination of three feature selections and seven classifier methods was implemented. Three classes of no or dis-improvement (class 1), improved EF from 0 to 5% (class 2), and improved EF over 5% (class 3) were predicted by using tenfold cross-validation. Lastly, the models were evaluated based on accuracy, AUC, sensitivity, specificity, precision, and F-score. Neighborhood component analysis (NCA) selected the most predictive feature signatures, including Gabor, first-order, and NGTDM features. Among the classifiers, the best performance was achieved by the fine KNN classifier, which yielded mean accuracy, AUC, sensitivity, specificity, precision, and F-score of 0.84, 0.83, 0.75, 0.87, 0.78, and 0.76, respectively, in 100 iterations of classification, within the 52 patients with 10-fold cross-validation. The MPI-SPECT-based radiomic features are well suited for predicting post-revascularization EF and therefore provide a helpful approach for deciding on the most appropriate treatment. Supplementary Information The online version contains supplementary material available at 10.1007/s10278-023-00820-1. Keywords: Ejection fraction, Machine learning, Myocardial perfusion imaging, PCI, Quantitative features, Radiomics

CITATION EXPORT

Mobin Mohebi, Mehdi Amini, Mohammad Javad Alemzadeh-Ansari et al.. Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study. Journal of Digital Imaging. (2023). https://doi.org/10.1007/s10278-023-00820-1

AUTHORS

8 · 9 CENTRES

Mobin Mohebi, Mehdi Amini, Mohammad Javad Alemzadeh-Ansari, Azin Alizadehasl, Ahmad Bitarafan Rajabi, Isaac Shiri, Habib Zaidi, Mahdi Orooji

1Department of Biomedical Engineering, Tarbiat Modares University, Tehran, Iran
2Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
3Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
4Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
5Cardio-Oncology Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
6Geneva University Neuro Center, Geneva University, Geneva, Switzerland
7Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands
8Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark
9Department of Electrical and Computer Engineering, University of California–Davis, Davis, CA USA