94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Virtual Real.
Sec. Virtual Reality in Medicine
Volume 6 - 2025 | doi: 10.3389/frvir.2025.1420404
Research on the Combination of Artificial Intelligence Algorithms and Mixed Reality for the Localization of Perforator Vessels in Anterolateral Thigh and Free Fibula Flaps
Provisionally accepted- Cancer Hospital, Chongqing University, Chongqing, China
Purpose: This study develops a system integrating algorithms with mixed reality to precisely locate perforating vessels for anterolateral thigh and free fibular flap harvesting. Its efficacy is compared to color Doppler ultrasonography (CDU) in vessel localization.Methods: Fifty patients requiring lower extremity flaps for maxillofacial reconstruction were randomized into the System Group and CDU Group (n=25 each). In the System Group, the flap outline and positioning markers were applied to the donor area, followed by lower-limb CTA scanning. The resulting 3D model, including vessels and markers, was reconstructed and imported into HoloLens 2. An AI algorithm aligned the 3D models with real markers, achieving vessel registration. In the CDU Group, conventional methods were used for vessel localization. The number of perforator vessels identified preoperatively and intraoperatively, the accuracy of identification, and the margin of error between marked and actual exit points were recorded. Flap harvesting success and complications were also assessed.Results: In the System Group, 51 vessel penetration sites were identified preoperatively, with 53 confirmed intraoperatively (96.2% accuracy). In the CDU Group, 44 sites were identified, with 49 confirmed (89.7% accuracy). The margin of error between identified and actual sites was 1.68±0.22 mm in the System Group versus 3.08±0.60 mm in the CDU Group. All 25 System Group patients had successful flap harvests, while 2 in the CDU Group required repositioning due to failed vessel localization. Postoperatively, one patient in each group experienced ischemic necrosis, requiring additional intervention.Conclusion: The proposed system accurately localizes perforating vessels for lower extremity flap harvesting, demonstrating superior precision and reliability compared to CDU. It holds significant potential for clinical application in reconstructive surgery.
Keywords: Mixed reality, Artificial intelligence algorithm, Anterolateral thigh flap, Free fibular flap, Perforating vessel localization Mixed reality, Perforating vessel localization
Received: 20 Apr 2024; Accepted: 25 Feb 2025.
Copyright: © 2025 Liu, Lian, Tang, Wu and Shuangjiang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Jian Wu, Cancer Hospital, Chongqing University, Chongqing, China
Wu Shuangjiang, Cancer Hospital, Chongqing University, Chongqing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.