in June 2024Surgical team led by Professor Richard Y. Hsu said the doctor. Jane J. Pugh From the Faculty of Dentistry University of Hong Konghas collaborated with United Imaging Intelligence (UII) to deliver groundbreaking AI-assisted oral and maxillofacial reconstructive surgery using the uAI MERITS platform, which stands for Metaverse Ecosystem for Robotic Interventions, Therapies, and Surgeries, leveraging large-scale multi-modal models for healthcare.
Benefits of intraoperative use of uAI
Overcoming Challenges in Oral and Maxillofacial Reconstruction
This surgery allowed a patient who had lost part of his lower jaw due to cancer to have his lower jaw reconstructed and regain normal aesthetics and function. During the surgery, a free fibula flap, including bone and soft tissue from the patient’s lower leg, was transferred to reconstruct the lost lower jaw and oral mucosa. At the same time, dental implants were placed in the newly transferred bone, restoring the patient’s chewing function, anatomical structure, and facial aesthetics.
Maxillofacial reconstructive surgery has been constrained by the complexity of anatomical structures, high demands for esthetics and functionality, and the need for surgical precision. In this case, accurate identification and localization of the perforator vessels in the soft tissue was crucial for successful mandibular reconstruction using a free fibula flap.
In traditional approaches, it is essential that surgeons have a high level of expertise and extensive surgical experience to minimize errors in locating perforator veins. Historically, physicians have relied on auxiliary tools such as ultrasound to estimate the location of these perforator veins, but this method often lacks accuracy and achieves suboptimal surgical outcomes. In addition, the surgical process requires surgeons to manually compare and distinguish between conventional cross-sectional CT images and the surgical site, which requires significant time and effort from the surgeon. This process poses considerable challenges to surgical efficiency and accuracy.
AI-assisted oral and maxillofacial reconstructive surgery achieves superior outcomes
Professor Su’s team performed the first successful oral and maxillofacial reconstructive surgery with the assistance of a medical large-scale multimodal model. The innovation of this technology lies in addressing the clinical challenge of surgeons who rely on empirical knowledge and best estimates to find perforator vessels during free flap harvesting surgery. The solution is enabled by a robust large-scale transformer model trained on a variety of medical images for accurate preoperative segmentation, and a large-scale multimodal model for intraoperative 3D image and video registration, predictive projection, and dynamic visual tracking. This integrated approach significantly improves surgical efficiency and accuracy.
The AI-assisted mandibular reconstruction surgery used the UII Discover – Runoff CTA system, an advanced intelligent system for evaluating the arteries of the lower limbs. The system quickly and automatically reconstructs comprehensive 3D models of the arteries, bones, and skin of the lower limbs, providing multi-modal 360-degree rotating views. It intelligently identified and contoured the perforator vessels of the legs and displayed them in different colors, streamlining the preoperative planning process and increasing surgical efficiency.
During the surgery, the uAI MERITS system, which integrates advanced AI technologies such as large-scale multimodal models and digital twins, played a key role in improving accuracy and efficiency. The system provided real-time projection of anatomical structures that intelligently and dynamically aligned the 3D reconstruction from the CTA system to the patient’s surgical site, seamlessly adapting to patient movements without compromising the accuracy of the procedure. This goggle-free approach allowed for fast and accurate delineation of the surgical field, significantly improving the accuracy and success rate of the surgery.
The success of this oral and maxillofacial reconstructive surgery is a testament to the integration of cutting-edge technologies such as AI and large-scale multimodal models with real medical use cases, and it is also the world’s first oral and maxillofacial reconstructive surgery driven by a medical-grade large-scale multimodal model.
To date, the team has successfully completed three oral and maxillofacial reconstruction surgeries using the uAI MERITS platform, with the third surgery being a notable breakthrough as it was the first to introduce the innovative technique of harvesting an anterolateral thigh flap, as opposed to the first two free fibula flap surgeries.
International Society of Oral and Maxillofacial Rehabilitation Hong Kong In June, Professor Su presented a successful case of using uAI MERITS in oral and maxillofacial reconstructive surgery, which attracted great attention from the experts and clinicians in attendance. James J. SheaUnited Imaging Intelligence’s Chief Medical Officer, Dr. David G. Schneider, MD, spoke about the latest advancements in AI technology in healthcare, and said the company will continue to collaborate with medical experts to discover clinical use cases and develop clinical applications leveraging large-scale modeling technology to unlock new possibilities for doctors and patients around the world.
Disclaimer: Products and features described herein may not be available in all countries and there is no guarantee of their future availability.
