Abstract
This study examined whether using an artificial neural network (ANN) helps beginners in diagnostic cardiac imaging to achieve similar results to experts when interpreting stress myocardial perfusion imaging (MPI). One hundred and thirty-eight patients underwent stress MPI with Tc-labeled agents. An expert and a beginner interpreted stress/rest MPI with or without the ANN and the results were compared. The myocardium was divided into 5 regions (the apex; septum; anterior; lateral, and inferior regions), and the defect score of myocardial blood flow was evaluated from 0 to 4, and SSS, SRS, and SDS were calculated. The ANN effect, defined as the difference in each of these scores between with and without the ANN, was calculated to investigate the influence of ANN on the interpreters' performance. We classified 2 groups (insignificant perfusion group and significant perfusion group) and compared them. In the same way, classified 2 groups (insignificant ischemia group and significant ischemia group) and compared them. Besides, we classified 2 groups (normal vessels group and multi-vessels group) and compared them. The ANN effect was smaller for the expert than for the beginner. Besides, the ANN effect for insignificant perfusion group, insignificant ischemia group and multi-vessels group were smaller for the expert than for the beginner. On the other hand, the ANN effect for significant perfusion group, significant ischemia group and normal vessels group were no significant. When interpreting MPI, beginners may achieve similar results to experts by using an ANN. Thus, interpreting MPI with ANN may be useful for beginners. Furthermore, when beginners interpret insignificant perfusion group, insignificant ischemia group and multi-vessel group, beginners may achieve similar results to experts by using an ANN.
Highlights
During the last 20 years, artificial intelligence (AI) and machine learning (ML), including artificial neural networks (ANN), have markedly developed
The ANN effect for all 138 patients was smaller for the expert than for the beginner (SSS: − 0.49 vs. − 1.23, p < 0.0001; summed rest score (SRS): − 0.34 vs. − 0.88, p = 0.0003; summed difference score (SDS): − 0.15 vs. − 0.36, p = 0.0128, respectively)
The ANN effects for all 138 patients on stress score (SSS), SRS, and SDS were negative for both interpreters, which indicates that they had lower scores with than without the ANN; i.e. their diagnostic approach became more conservative when they were using the ANN
Summary
During the last 20 years, artificial intelligence (AI) and machine learning (ML), including artificial neural networks (ANN), have markedly developed. AI and ML may aid medical imaging-based diagnosis, in terms of the detection of disease, and in management, reporting, and prognostication [1]. ANN is a computational model of ML based on the human brain. It has been found that ANN are powerful tools for pattern recognition, signal processing, image or speech data compression, and learning expert systems [2]. There are 6675 radiologists with specialty licenses in Japan, according to the Japan Radiological Society, but only 1317 radiologists have specialty licenses in nuclear medicine. The number of experts in cardiac nuclear medicine is very small. The interpretation of myocardial perfusion images (MPI) requires skilled expert reading, but there are not as many skilled experts in the interpretation of MPI as there are in the interpretation of computed tomography scans in Japan
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
