AI-based image analysis enhances post-stent monitoring

Following stent implantation, the growth of tissue over the stent must be monitored carefully. Irregular healing — such as excessive tissue growth or plaque accumulation — can lead to complications like restenosis or vessel occlusion. Although intravascular OCT offers a high-resolution imaging technique for assessing these issues, the manual interpretation of images is slow and not feasible for routine use. 

DeepNeo addresses this gap by using artificial intelligence to interpret OCT scans automatically. The algorithm classifies various healing patterns, quantifies tissue thickness, and assesses stent coverage — delivering results within seconds. 

“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,” says Valentin Koch, first author of the study introducing the algorithm. “DeepNeo is as good as a doctor, but much faster.” 

To ensure DeepNeo’s reliability, the team trained the algorithm on 1,148 manually annotated OCT images from 92 patient scans. The system was then validated in both animal models and clinical datasets: 

• In 87 percent of cases, DeepNeo correctly identified abnormal tissue compared to gold-standard laboratory analysis. 

• For human scans, its assessments closely aligned with those of cardiologists and medical imaging experts. 

“DeepNeo demonstrates how machine learning can support clinicians in making quicker, more informed treatment decisions,” says Dr. Carsten Marr, Director of the Institute of AI for Health at Helmholtz Munich. 

DeepNeo’s development was supported by a Helmholtz Innovation Grant, and a patent has already been filed. Ascenion, a life sciences technology transfer partner, is helping identify suitable industry partners for future deployment. 

“This has the potential to not only reduce healthcare costs but pave the way for more effective and personalized cardiovascular treatments,” explain PD Philipp Nicol and Prof. Michael Joner, cardiologists at the TUM University Hospital. 

MEDICA-tradefair.com; Source: Helmholtz Munich