AI-Powered Algorithm Automates Analysis of Coronary Stents After Implantation

Every year, over three million people globally receive stents to open blocked blood vessels caused by heart disease. However, monitoring the healing process after stent implantation remains a significant challenge. If the tissue growing over the stent becomes irregular—either growing too thick or forming deposits—it can lead to complications such as re-narrowing or occlusion of the blood vessel. Currently, analyzing these healing patterns in intravascular optical coherence tomography (OCT) images is time-consuming and impractical for routine clinical use. Now, a new artificial intelligence (AI)-driven algorithm automates the analysis of coronary stents post-implantation, achieving the accuracy of medical experts while dramatically reducing the time required for assessment. With robust validation in both human and animal models, this AI algorithm has the potential to standardize post-stent monitoring, thereby improving cardiovascular treatment outcomes.

DeepNeo, the AI algorithm developed by researchers from Helmholtz Munich (Oberschleißheim, Germany) in collaboration with other experts, can automatically assess stent healing in OCT images. DeepNeo differentiates between various healing patterns with accuracy comparable to clinical experts but at a fraction of the time. The AI tool also provides precise measurements, such as tissue thickness and stent coverage, offering valuable insights for patient management. To train DeepNeo, the researchers used 1,148 OCT images from 92 patient scans, which were manually annotated to classify different types of tissue growth. The algorithm was then tested on an animal model, where it accurately identified unhealthy tissue in 87% of cases, compared to detailed laboratory analysis, which is considered the gold standard. When analyzing human scans, DeepNeo also demonstrated high precision, closely aligning with expert assessments.

“With DeepNeo, we can achieve an automated, standardized, and highly accurate analysis of stent and vascular healing that was previously only possible through extensive manual effort,” said Valentin Koch, first author of the study introducing the algorithm. “DeepNeo is as good as a doctor, but much faster.”

“DeepNeo demonstrates how machine learning can support clinicians in making quicker, more informed treatment decisions. The next step is now to effectively integrate AI algorithms like DeepNeo into clinical practice,” added Dr. Carsten Marr, Director at the Institute of AI for Health at Helmholtz Munich, who envisions DeepNeo as part of an AI-powered healthcare system that could offer unprecedented certainty for clinical decision-making.

Related Links:
Helmholtz Munich