SPECT + Deep Learning = Accurate Major Cardiac Event Prediction
Using advanced artificial intelligence can give patients a personalized assessment of their risk for significant events, such as heart attack or death.
Deep learning does a better job in predicting which patients will experience major adverse cardiac events than the current standard imaging protocols used to make these determinations, according to new research.
In a poster presented during the Society of Nuclear Medicine and Molecular Imaging 2021 Annual Meeting, researchers from Cedars-Sinai Medical Center in Los Angeles created a novel deep learning algorithm that can give patients a personalized assessment of their annualized risk for these types of events, such as heart attack of death.
For more SNMMI 2021 Annual Meeting coverage, click here.
“These findings show that artificial intelligence could be incorporated in standard clinical workstations to assist physicians in accurate and fast risk assessment of patients undergoing SPECT MPI scans,” said Ananya Singh, MS, a research software engineer in the Slomka Lab at Cedars-Sinai. “This work signifies the potential advantage of incorporating artificial intelligence techniques in standard imaging protocols to assist readers with risk stratification.”
Prediction performance of DL compared to quantitative measures and Kaplan-Meier curves for quartiles of DL.
Credit: Image created by Singh et al., Cedars-Sinai Medical Center, Los Angeles, CA.
To build their deep learning network, the team pulled data from 20,401 patients included in the largest available multi-center SPECT dataset – REgistry of Fast myocardial perfusion Imaging in NExt generation SPECT (REFINE SPECT). All patients had undergone SPECT MPI. The team used their network to score each patient on their individual likelihood to have a major adverse cardiac event during the average follow-up period of 4.7 years.
According to their analysis, the network was able to pinpoint the areas of the heart that were associated with an elevated risk of these events and return a risk score in less than 1 second. They determined that the patients with the highest deep learning scores had a 9.7-percent annual major cardiac event rate – a 10.2-fold increased risk over patients with the lowest scores.
For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-Newsletter here.
Photon-Counting Computed Tomography: Eleven Takeaways from a New Literature Review
May 27th 2025In a review of 155 studies, researchers examined the capabilities of photon-counting computed tomography (PCCT) for enhanced accuracy, tissue characterization, artifact reduction and reduced radiation dosing across thoracic, abdominal, and cardiothoracic imaging applications.
Can AI Predict Future Lung Cancer Risk from a Single CT Scan?
May 19th 2025In never-smokers, deep learning assessment of single baseline low-dose computed tomography (CT) scans demonstrated a 79 percent AUC for predicting lung cancer up to six years later, according to new research presented today at the American Thoracic Society (ATS) 2025 International Conference.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.
