Automatic determination of cardiovascular risk by CT attenuation correction maps in Rb-82 PET/CT

Abstract

Background We investigated fully automatic coronary artery calcium (CAC) scoring and cardiovascular disease (CVD) risk categorization from CT attenuation correction (CTAC) acquired at rest and stress during cardiac PET/CT and compared it with manual annotations in CTAC and with dedicated calcium scoring CT (CSCT). Methods and Results We included 133 consecutive patients undergoing myocardial perfusion 82Rb PET/CT with the acquisition of low-dose CTAC at rest and stress. Additionally, a dedicated CSCT was performed for all patients. Manual CAC annotations in CTAC and CSCT provided the reference standard. In CTAC, CAC was scored automatically using a previously developed machine learning algorithm. Patients were assigned to a CVD risk category based on their Agatston score (0, 1–10, 11–100, 101–400, >400). Agreement in CVD risk categorization between manual and automatic scoring in CTAC at rest and stress resulted in Cohen’s linearly weighted κ of 0.85 and 0.89, respectively. The agreement between CSCT and CTAC at rest resulted in κ of 0.82 and 0.74, using manual and automatic scoring, respectively. For CTAC at stress, these were 0.79 and 0.70, respectively. Conclusion Automatic CAC scoring from CTAC PET/CT may allow routine CVD risk assessment from the CTAC component of PET/CT without any additional radiation dose or scan time.

Best practice for the nuclear medicine technologist in CT-based attenuation correction and calcium score for nuclear cardiology

“…This was the first study to quantify CCS using AC images obtained during PET MPI in a cohort of 91 patients. Išgum et al (2018) moved back the threshold level to 130 HU because they stated that a 50 HU introduces more artifacts from the non-calcium structure for the set of images used in their study. They introduced a fully automatic calcium scoring system applied to AC images in clinical routine.…”

Direct Automatic Coronary Calcium Scoring in Cardiac and Chest CT

“…Furthermore, previously proposed automatic calcium scoring methods are dedicated to either cardiac CT or chest CT. These methods required retraining for application in other types of CT [8], [32]. We present an automatic method that performs real-time direct calcium scoring in different types of non-contrastenhanced CT.…”

Machine Learning and Deep Neural Networks in Thoracic and Cardiovascular Imaging

“…Since this early work, supervised machine learning 26 RV, LV endocardium and epicardium CNN Tan et al 27 LV segmentation ANN Baessler et al 28 Myocardial scar detection Random forests Dawes et al 29 Pulmonary hypertension prognosis PCA ECHO Ortiz et al 30 HF prognosis ANN Narula et al 31 HCM vs athlete's heart SVM, Random forests, ANN Sengupta et al 32 Constrictive pericarditis vs restrictive cardiomyopathy AMC, random forest, k-NN, SVM Sengur 33 Valvular disease SVM Moghaddasi and Nourian 34 MR severity SVM Vidya et al 35 MI detection SVM CT Wolterink et al 36 CAC scoring CNN Isgum et al 37 CAC scoring k-NN, SVM Itu et al 38 FFR estimation deep neural network Motwani et al 39 Prognosis Logistic regression Mannil et al 40 MI detection Decision tree, k-NN, random forest, ANN 32 diagnose valvular heart disease, 33 grade severity of mitral valve regurgitation, 34 automate ejection fraction measurement, 53 and detect the presence of myocardial infarction. 35,54 Several machine learning applications have also been developed to assist in the interpretation of CT. For example, algorithms have been developed for the automation of coronary artery calcium scoring 36,37,55,56 and assessment of the functional significance of coronary lesions. More recently, ML techniques have been leveraged to better assess the hemodynamic significance of coronary stenosis.…”