Related Experiment Video
Updated: Aug 19, 2026
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
Published on: September 2, 2025
Augmented Reality-based Guidance with Deformable Registration in Head and Neck Tumor Resection
Qingyun Yang1, Fangjie Li1, Jiayi Xu1
1Vanderbilt University, Nashville TN 37235, USA.
Abstract:
Head and neck squamous cell carcinoma has one of the highest rates of recurrence. Recurrence rates can be reduced by accurate localization of positive margins. While frozen section analysis of resected specimens provides accurate intraoperative margin assessment, complex 3D anatomy and significant shrinkage of resected specimens complicate margin relocation from the specimen back to the post-resection cavity. We propose a novel deformable registration framework that uses both the pre-resection external surface and the post-resection cavity of the specimen to incorporate thickness information. In tongue specimens, the proposed framework improved the target registration error (TRE) by up to 33% as compared to using the post-resection cavity alone. We found distinct deformation behaviors in skin, buccal, and tongue specimens, highlighting the need for tailored deformation strategies. Notably, tongue specimens hold the highest clinical need for improvement among head and neck specimens. To further aid intraoperative visualization, we also integrated this framework into an augmented reality-based guidance system. This system can automatically overlay the deformed 3D specimen mesh with positive margin annotation onto the post-resection cavity. The integrated system improved a surgeon and a trainee's average relocation error from 9.8 mm to 4.8 mm in a pilot study. Our implementation code for AR guidance and generating the target point cloud is available at https://github.com/vu-maple-lab/Head-and-Neck-Tumor-Resection-Guidance.
Insights
Accurate localization of positive margins in head and neck cancer surgery is crucial for reducing recurrence. A new registration framework and augmented reality system improve margin relocation accuracy, aiding surgeons in tumor resection.
Area of Science:
- Medical imaging
- Surgical oncology
- Computer-aided surgery
Background:
- Head and neck squamous cell carcinoma has high recurrence rates, often due to positive margins.
- Accurate intraoperative margin assessment is vital, but specimen shrinkage complicates relocation.
- Current methods struggle with complex 3D anatomy and tissue deformation.
Purpose of the Study:
- To develop a novel deformable registration framework for accurate margin localization in head and neck cancer resection.
- To improve the relocation of positive margins from resected specimens to the post-resection cavity.
- To integrate the framework into an augmented reality (AR) system for intraoperative guidance.
Main Methods:
- A deformable registration framework utilizing pre-resection external surface and post-resection cavity data.
- Incorporation of specimen thickness information into the registration process.
- Development of an AR-based guidance system overlaying 3D specimen meshes onto the surgical site.
Main Results:
- The framework improved target registration error (TRE) by up to 33% in tongue specimens compared to using cavity data alone.
- Distinct deformation behaviors were observed in skin, buccal, and tongue tissues, necessitating tailored strategies.
- The integrated AR system reduced average margin relocation error from 9.8 mm to 4.8 mm in a pilot study.
Conclusions:
- The proposed registration framework enhances margin localization accuracy in head and neck cancer surgery.
- Tailored deformation strategies are crucial for different tissue types, with tongue specimens showing the greatest need for improvement.
- The AR-integrated system offers a promising tool for improving intraoperative visualization and surgical precision in tumor resection.
