In a significant breakthrough, biomedical engineer Abhinav Jha and his team have developed an AI-powered tool called DEMIST that can improve the detection of cardiac defects in myocardial perfusion imaging (MPI) single-photon emission computed tomography (SPECT) images. The innovative approach leverages deep learning to selectively clean low-count MPI SPECT images, preserving features that influence detection tasks. In a study published in IEEE Transactions on Radiation and Plasma Medical Sciences, the researchers demonstrated that DEMIST outperformed both low-dose scans and a commonly used task-agnostic denoising method on the task of detecting cardiac defects. The tool’s effectiveness was evaluated on anonymized clinical data from 338 patients, and the results showed that DEMIST significantly enhanced detection of cardiac defects by a model observer. This technology has the potential to reduce radiation dose and acquisition time, making it a game-changer for patient care and treatment outcomes.
AI-Powered Image Denoising Tool Enhances Heart Defect Detection
DEMIST offers possibilities to enhance the accuracy and efficiency of detecting myocardial perfusion defects, ultimately benefiting patient care and treatment outcomes.
1–2 minutes
TOP STORIES
The Pentagon has secured agreements with tech giants to enhance military AI capabilities, raising ethical concerns about its use in …
The legal clash over AI safety and profit motives highlights critical concerns …
Meta’s acquisition of ARI aims to boost its humanoid robotics and AI development …
The trial between Elon Musk and OpenAI reveals deep divisions over AI’s future and ethical commitments …
The U.S. Defense Department expands its AI partnerships to enhance military capabilities …
Apple’s Mac revenue outperformed expectations, driven by strong AI demand and new product launches …
