Coronary artery disease stands as a principal cause of mortality worldwide. A prevalent method for diagnosing and tracking heart conditions, myocardial perfusion imaging (MPI) via single photon emission computed tomography (SPECT), utilizes a radioactive tracer alongside a specialized camera to deliver intricate images of blood circulation to the heart. This aids medical professionals in identifying coronary artery disease and various cardiovascular irregularities. Nevertheless, conventional SPECT imaging necessitates an additional CT scan to guarantee precision, thereby subjecting patients to heightened radiation exposure and escalating expenses.

Presently, an innovative deep-learning technique, conceived by investigators at Washington University in St. Louis, in collaboration with the Cleveland Clinic and the University of California, Santa Barbara, may revolutionize the monitoring of heart health, enhancing safety and accessibility. This method, referred to as CTLESS, employs deep learning to eliminate the need for CT without detracting from diagnostic precision. The initiative, steered by Abhinav Jha, an associate professor of biomedical engineering at the McKelvey School of Engineering and of radiology at WashU Medicine Mallinckrodt Institute of Radiology, was made available online on Nov. 25 in IEEE Transactions on Medical Imaging.

The researchers’ forthcoming actions involve validating this approach while also striving to enhance the accessibility of this technology to hospitals in rural communities. Their cost-efficient method holds particular importance for situations where access to such scans is restricted, notably in rural or otherwise constrained communities, according to Jha.

For additional information, visit the McKelvey Engineering website.

The article Deep learning to increase accessibility, ease of heart imaging was first published on The Source.