Artificial intelligence for vascular minimally invasive surgery: techniques, clinical integration, and challenges
8 affiliations
- 1Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School
- 2Chinese Medicine Guangdong Laboratory
- 3Department of General Surgery, Hebei Key Laboratory of Colorectal Cancer Precision Diagnosis and Treatment, The First Hospital of Hebei Medical University
- 4Institute of Biomedical Engineering, Boğaziçi University
- 5Medical Artificial Intelligence Lab, The First Hospital of Hebei Medical University
- 6Department of Oncology, The First Hospital of Hebei Medical University
- 7School of Mechanical, Electrical and Information Engineering, Shandong University
- 8Translational Medicine Research Center, Chongqing University Three Gorges Hospital, Chongqing University
Abstract
Introduction: Minimally invasive surgery (MIS), including endovascular and robot-assisted procedures, is widely used for vascular pathologies but remains limited by technical complexity, cognitive workload, and postoperative complications. Artificial Intelligence (AI) may help address these challenges through predictive analysis, decision support, image analysis, and automation.
Methods: A structured Google Scholar search was conducted from February 21, 2025, to January 1, 2026, and updated through September 2026. Peer-reviewed studies applying AI to vascular MIS were included, with additional targeted searches addressing clinical translation, deployment, regulation, and ethical considerations.
Results: Thirty primary studies were analyzed, including eight on machine learning, nine on deep learning, four on natural language processing, and nine on robotics or reinforcement learning. Machine learning supported risk stratification and outcome prediction, deep learning enabled imaging and segmentation applications, natural language processing facilitated clinical information extraction, and robotic systems supported navigation and procedural assistance.
Discussion: AI demonstrates substantial potential across the vascular MIS pathway, but broader clinical adoption requires stronger validation, prospective multicenter studies, standardized reporting, health-economic evaluation, and careful consideration of regulatory, liability, and accessibility challenges.
Related
- Low-Dose CT in the Age of Artificial Intelligence: Techniques, Evidence, and Clinical Impact
- Artificial Intelligence in Oncologic Imaging: Deep Learning, Radiomics, and Clinical Integration for Precision Cancer Diagnosis
- Clinical Translation of Artificial Intelligence in Oncology: Real-World Validation, Workflow Integration, and Precision Medicine Applications
- Artificial Intelligence, Multi-Omics, and Multimodal Integration in Precision Radiotherapy for Head and Neck Cancer: From Biological Insights to Treatment Decisions
- Artificial intelligence and radiomics in small cell lung cancer: a narrative review of imaging and multisource data integration
BibTeX
@article{jiang2026artificial,
title = {{Artificial intelligence for vascular minimally invasive surgery: techniques, clinical integration, and challenges}},
author = {Cenk Jiang and Bogdan Bortnovskii and Ijaz Gul and Mehmed Özkan and Lian Zhang and Dongmei Yu and Vijay Pandey and Runming Wang and Jian Wu and Peiwu Qin},
journal = {Frontiers in Cardiovascular Medicine},
year = {2026},
month = oct,
doi = {10.3389/fcvm.2026.1966224},
url = {https://www.frontiersin.org/articles/10.3389/fcvm.2026.1966224/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial intelligence for vascular minimally invasive surgery: techniques, clinical integration, and challenges
AU - Cenk Jiang
AU - Bogdan Bortnovskii
AU - Ijaz Gul
AU - Mehmed Özkan
AU - Lian Zhang
AU - Dongmei Yu
AU - Vijay Pandey
AU - Runming Wang
AU - Jian Wu
AU - Peiwu Qin
PY - 2026
DA - 2026/10/22
JO - Frontiers in Cardiovascular Medicine
DO - 10.3389/fcvm.2026.1966224
UR - https://www.frontiersin.org/articles/10.3389/fcvm.2026.1966224/full
AB - Introduction: Minimally invasive surgery (MIS), including endovascular and robot-assisted procedures, is widely used for vascular pathologies but remains limited by technical complexity, cognitive workload, and postoperative complications. Artificial Intelligence (AI) may help address these challenges through predictive analysis, decision support, image analysis, and automation. Methods: A structured Google Scholar search was conducted from February 21, 2025, to January 1, 2026, and updated through September 2026. Peer-reviewed studies applying AI to vascular MIS were included, with additional targeted searches addressing clinical translation, deployment, regulation, and ethical considerations. Results: Thirty primary studies were analyzed, including eight on machine learning, nine on deep learning, four on natural language processing, and nine on robotics or reinforcement learning. Machine learning supported risk stratification and outcome prediction, deep learning enabled imaging and segmentation applications, natural language processing facilitated clinical information extraction, and robotic systems supported navigation and procedural assistance. Discussion: AI demonstrates substantial potential across the vascular MIS pathway, but broader clinical adoption requires stronger validation, prospective multicenter studies, standardized reporting, health-economic evaluation, and careful consideration of regulatory, liability, and accessibility challenges.
SN - 2297-055X
ER -