A3
AI-based Method and Tool (DeepNeo) for Intravascular Optical Coherence Tomography Image Analysis of Coronary Artery Neointimal Tissue
Valentin Koch, Helmholtz Munich; Dr Philipp Nicol, German Heart Center
Ascenion GmbH
Challenge
Percutaneous Coronary Interventions (PCIs) are among the most common procedures in cardiovascular medicine. Despite development of long-term risks such as in-stent restenosis, a tool for standardized, automatic analysis of vascular healing is lacking. Commercially available OCT image analysis tools lack the ability to characterize the neointimal tissue and thus miss important features in post-procedure monitoring.
Technology
Researchers of Helmholtz Munich and the German Heart Center have developed an AI-based method that allows the analysis of Intravascular Optical Coherence Tomography (IV-OCT) pullback image series of coronary arteries after PCI. The researchers implemented a corresponding deep learning architecture and trained their model with patient data to come up with an AI-based tool (DeepNeo) for IV-OCT pullback image series analysis to classify the neointimal tissue, which is the newborn tissue covering the stent surface inside treated coronary arteries.
The method implemented by DeepNeo aims to address the aforementioned gap by characterizing neointimal tissue and providing insights into vessel morphology in a rapid and standardized manner. This approach has the potential to automate and standardize current practices for patients undergoing OCT after PCI, and may ultimately contribute to improving and/or standardizing post-PCI decision-making.
DeepNeo relies on two trained deep neural networks that segment features of coronary vessels and that classify neointimal tissue, respectively. DeepNeo can analyze the neointimal tissue composition of an IV-OCT pullback image series (typically consisting of 300 - 400 frames) and visualizes neointima characteristics for each quadrant of each image of the pullback series.
Commercial Opportunity
The technology is available for in-licensing. DeepNeo can be used to monitor the healing process following coronary stent implantation, support therapeutic decisions, and improve risk detection for cardiac events. The approach can also support research and development activities in the field of drug-eluting stents.
Development Status
A proof of principle has been demonstrated. The classification performance for neointimal tissue has been shown to be comparable to that of human experts. DeepNeo has been developed as an academic tool for research purposes and does not fulfil the regulatory requirements of a medical device.
Patent Situation
A priority establishing patent application and an international patent application have been filed (EP4475072A1, WO2024251852A1). Nationalization/regionalization was initiated in EP and US in December 2025.
Further Reading
Koch V, et al., Deep Learning Model DeepNeo predicts neointimal tissue characterization using optical coherence tomography, Communications Medicine 2025, 5:124
