Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study
Abstract This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspici...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-42142-w |
| _version_ | 1797453215198871552 |
|---|---|
| author | Mehdi Amini Mohamad Pursamimi Ghasem Hajianfar Yazdan Salimi Abdollah Saberi Ghazal Mehri-Kakavand Mostafa Nazari Mahdi Ghorbani Ahmad Shalbaf Isaac Shiri Habib Zaidi |
| author_facet | Mehdi Amini Mohamad Pursamimi Ghasem Hajianfar Yazdan Salimi Abdollah Saberi Ghazal Mehri-Kakavand Mostafa Nazari Mahdi Ghorbani Ahmad Shalbaf Isaac Shiri Habib Zaidi |
| author_sort | Mehdi Amini |
| collection | DOAJ |
| description | Abstract This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models’ evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process. |
| first_indexed | 2024-03-09T15:19:34Z |
| format | Article |
| id | doaj.art-77111609a7294341a89939a297e27c5c |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:19:34Z |
| publishDate | 2023-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-77111609a7294341a89939a297e27c5c2023-11-26T12:53:35ZengNature PortfolioScientific Reports2045-23222023-09-0113111210.1038/s41598-023-42142-wMachine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics studyMehdi Amini0Mohamad Pursamimi1Ghasem Hajianfar2Yazdan Salimi3Abdollah Saberi4Ghazal Mehri-Kakavand5Mostafa Nazari6Mahdi Ghorbani7Ahmad Shalbaf8Isaac Shiri9Habib Zaidi10Division of Nuclear Medicine and Molecular Imaging, Geneva University HospitalDepartment of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical SciencesDivision of Nuclear Medicine and Molecular Imaging, Geneva University HospitalDivision of Nuclear Medicine and Molecular Imaging, Geneva University HospitalDivision of Nuclear Medicine and Molecular Imaging, Geneva University HospitalDepartment of Medical Physics, School of Medicine, Semnan University of Medical SciencesDepartment of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical SciencesDepartment of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical SciencesDepartment of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical SciencesDivision of Nuclear Medicine and Molecular Imaging, Geneva University HospitalDivision of Nuclear Medicine and Molecular Imaging, Geneva University HospitalAbstract This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models’ evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process.https://doi.org/10.1038/s41598-023-42142-w |
| spellingShingle | Mehdi Amini Mohamad Pursamimi Ghasem Hajianfar Yazdan Salimi Abdollah Saberi Ghazal Mehri-Kakavand Mostafa Nazari Mahdi Ghorbani Ahmad Shalbaf Isaac Shiri Habib Zaidi Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study Scientific Reports |
| title | Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study |
| title_full | Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study |
| title_fullStr | Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study |
| title_full_unstemmed | Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study |
| title_short | Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study |
| title_sort | machine learning based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging spect a radiomics study |
| url | https://doi.org/10.1038/s41598-023-42142-w |
| work_keys_str_mv | AT mehdiamini machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT mohamadpursamimi machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT ghasemhajianfar machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT yazdansalimi machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT abdollahsaberi machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT ghazalmehrikakavand machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT mostafanazari machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT mahdighorbani machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT ahmadshalbaf machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT isaacshiri machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy AT habibzaidi machinelearningbaseddiagnosisandriskclassificationofcoronaryarterydiseaseusingmyocardialperfusionimagingspectaradiomicsstudy |