Abstract
We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku PET Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from 15O–H2O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used. The CNN was evaluated against the clinical interpretation. The classification accuracy was evaluated with: accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE) and precision (PRE). The CNN had a median ACC of 0.8261, AUC of 0.8058, F1S of 0.7647, SEN of 0.6500, SPE of 0.9615 and PRE of 0.9286. In comparison, clinical interpretation had ACC of 0.8696, AUC of 0.8558, F1S of 0.8333, SEN of 0.7500, SPE of 0.9615 and PRE of 0.9375. The CNN classified only 2 cases differently than the clinical interpretation. The clinical interpretation and CNN had similar accuracy in classifying false positives and true negatives. Classification of ischemia is feasible in 15O–H2O stress perfusion imaging using JPEG polar maps alone with a custom CNN and may be useful for the detection of obstructive CAD.
Highlights
We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku positron emission tomography (PET) Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from 15O–H2O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used
The aim of this study was to implement an automatic classifier based on a custom two-dimensional (2D) convolutional neural network (CNN) architecture to classify polar maps of stress myocardial blood flow (MBF) created with Carimas 2.9 software as ischemic or non-ischemic in 15O–H2O myocardial perfusion imaging
We report the values for ACC, F1 score (F1S), SEN, SPE and PRE in addition to true positives (TP), true negatives (TN), false positives (FP) and false negatives (FN) as median with the interquartile range over the 100 runs for the data with the CNN
Summary
We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku PET Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from 15O–H2O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used. Classification of ischemia is feasible in 15O–H2O stress perfusion imaging using JPEG polar maps alone with a custom CNN and may be useful for the detection of obstructive CAD. The earliest study investigating the use of machine learning algorithms for myocardial perfusion imaging (MPI) was performed by Fujita et al.[3], who used a three-layer feed-forward neural network to classify polar plots from 74 polar maps with Thallium-201 SPECT. The study showed that deep learning improved automatic prediction of obstructive coronary artery disease (CAD) compared with the current standard clinical method. In another SPECT study, Spier et al.[9] compared several network architectures to classify 946 labeled polar maps with relatively good agreement with a human observer
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
