Nuclear medicine

The study find that the A multicenter international study has demonstrate for the first time that diagnosis ; Because of obstructive coronary artery disease is improve by using deep learning analysis ;of upright and supine single photon emission compute tomography (SPECT); myocardial perfusion imaging (MPI). Therefore The research is feature in the May issue of The Journal of Nuclear Medicine. Therefore According to the Centers for Disease Control and Prevention; coronary artery disease is the most common type of heart disease; killing more than 370,000 people in the United States annually.

Coronary artery disease

SPECT MPI, which is widely use for its diagnosis, shows how well the heart muscle ;is pumping and examines blood flow through the heart during exercise and at rest. On new cameras with a patient imaged in sitting position; two positions (semi-upright and supine); are routinely use to mitigate attenuation artifacts.

The current quantitative standard for analyzing MPI data is to calculate the combined total perfusion deficit (TPD) from these 2 positions. Visually; physicians need to reconcile information available from 2 views. Coronary artery disease (CAD)(or atherosclerotic heart disease) is the end result of the accumulation of atheromatous plaques within the walls of the coronary arteries that supply the myocardium (the muscle of the heart); with oxygen and nutrients.

Combined total perfusion

It is sometimes also called coronary heart disease(CHD), but although CAD is the most common cause of CHD, it is not the only cause. CAD is the leading cause of death worldwide. While the symptoms and signs of coronary artery disease are noted in the advanced state of disease, most individuals with coronary artery disease show no evidence of disease for decades as the disease progresses before the first onset of symptoms; often a “sudden” heart attack, finally arises.

Deep convolutional neural networks, often referred to as deep learning (DL); go beyond machine learning using algorithms. They directly analyze visual data, learn from them, and make intelligent findings base on the image information. For this study, DL analysis of data from the two-position stress MPI is compare with the standard TPD analysis of 1,160 patients without known coronary artery disease.

Directly analyze visual data

Patients underwent stress MPI with the nuclear medicine radiotracer technetium (99mTc) sestamibi. Therefore New-generation solid-state SPECT scanners in four different centers are use, and images are quantify at the Cedars-Sinai Medical Center in Los Angeles, California. All patients had on-site clinical reads and invasive coronary angiography correlations within six months of MPI.

Obstructive disease is define as at least 70% narrowing of the three major coronary arteries and at least 50% for the left main coronary artery. During the validation procedure, four different DL models were trained (each using data from three centers) and then are evaluate on the one center left aside.