AI and OCT Combo Shows Promise for Detecting High-Risk Coronary Plaques

New method uses AI to analyze spectral data from OCT images to identify lipid-rich plaques linked to heart attack risk.

Published on Feb. 20, 2026

Got story updates? Submit your updates here. ›

Researchers have developed a new artificial intelligence-based approach for detecting fatty deposits inside coronary arteries using optical coherence tomography (OCT) images. The method analyzes wavelength-dependent information in the OCT signal and uses deep learning to automatically identify the presence and distribution of lipid within the vessel wall. This could help doctors spot dangerous plaques before they rupture and cause damage.

Why it matters

Plaques with more lipid and certain patterns of lipid distribution are strongly associated with the risk of major cardiac events like heart attacks. This new AI-powered OCT analysis method has the potential to improve risk assessment, procedural planning, and long-term management of patients with coronary artery disease.

The details

The researchers developed a deep learning approach that enables quantitative, automatic assessment of lipids directly from intravascular OCT images. The method doesn't require any hardware changes and works with OCT systems already used in the clinic. It feeds wavelength-dependent information from OCT images into an AI model, which learns to recognize signal patterns more likely to originate from lipid-rich tissue and can then highlight suspicious regions throughout the image.

  • The study results were published in February 2026 in the journal Biomedical Optics Express.

The players

Hyeong Soo Nam

Research team leader from the Korea Advanced Institute of Science and Technology in South Korea.

Jin Won Kim

Researcher at Korea University Guro Hospital, who previously collaborated with Nam's team on spectroscopic OCT research.

Optica Publishing Group

The publisher of the Biomedical Optics Express journal where the study was published.

Got photos? Submit your photos here. ›

What they’re saying

“Plaques with more lipid and certain patterns of lipid distribution are strongly associated with the risk of major cardiac events.”

— Hyeong Soo Nam, Research team leader (Biomedical Optics Express)

“Our group previously demonstrated that spectroscopic OCT can detect lipid-related optical signatures within atherosclerotic plaques. This new study builds on that by extending it with modern deep learning techniques to significantly improve detection accuracy and robustness.”

— Hyeong Soo Nam, Research team leader (Biomedical Optics Express)

“Importantly, unlike many conventional AI systems that require experts to painstakingly label lipid regions at the pixel level — an extremely time-consuming and subjective process — our approach learns from much simpler frame-level annotations that indicate only whether lipid is present or absent. This substantially lowers the annotation burden and makes the method far more practical for real-world clinical use.”

— Hyeong Soo Nam, Research team leader (Biomedical Optics Express)

What’s next

The researchers are now working to improve the processing speed and robustness of the approach to make it more practical for real-time clinical use. They also plan to perform additional validation studies using human coronary artery data and figure out the best way to integrate the method into existing clinical workflows.

The takeaway

This new AI-powered OCT analysis method has the potential to significantly improve the detection of high-risk, lipid-rich coronary plaques, which could lead to better risk assessment, treatment planning, and long-term management of patients with coronary artery disease.