Kunpeng Xie

Oral & Maxillofacial Surgeon & Researcher

University Hospital RWTH Aachen

About Me

I am a doctoral candidate (Dr. med. dent.) at RWTH Aachen University, working in the Research Group OMFS digital (AG MKG digital) under the supervision of Dr. Dr. Behrus Hinrichs-Puladi, jointly affiliated with the Department of Oral and Maxillofacial Surgery and the Institute of Medical Informatics at University Hospital RWTH Aachen.

My research focuses on bridging the gap between clinical oral and maxillofacial surgery and digital innovation. I am particularly interested in AI-driven medical image analysis, computer-aided surgical planning, and augmented reality navigation for head and neck procedures.

Prior to joining RWTH Aachen, I completed my Bachelor’s and Master’s degrees in Stomatology at Jilin University, China, under the mentorship of Prof. Guomin Wu, where I also worked as a resident surgeon specializing in orthognathic surgery, dentoalveolar surgery, and 3D-printed surgical planning.

Interests

AI in Oral & Maxillofacial Surgery
Medical Image Processing
Computer-Aided Surgery
Orthognathic Surgery
Plastic & Reconstructive Surgery
Dentoalveolar Surgery

Education

Dr. med. dent. (in progress), 2022
RWTH Aachen University
Master of Stomatology, 2022
Jilin University
Bachelor of Stomatology, 2019
Jilin University

Research Topics

Mar 23, 2026

AI for Medical Image Analysis

Segmentation, prediction, and clinically grounded imaging workflows.

Mar 22, 2026

Computer-Aided Surgery

Digital planning, simulation, and workflow integration in surgery.

Mar 21, 2026

Augmented Reality Navigation

AR-guided visualization and navigation for head and neck procedures.

Featured Publications

Kunpeng Xie, Lennart Johannes Gruber, Martin Crampen, Yao Li, André Ferreira, Behrus Hinrichs-Puladi

March, 2026 Expert Systems with Applications

Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems

We present a comprehensive multi-center evaluation of 20 state-of-the-art bone segmentation models across 1,000 clinically resampled CT/CBCT scans. Our study reveals that image sharpness, isotropic smaller voxels, and neutral orientation significantly improve segmentation performance, while metallic osteosynthesis and anatomical complexity lead to significant degradation. The findings highlight the gap between benchmark performance and real-world clinical applicability, emphasizing the need for robustness evaluation in socio-technical systems.

Yao Li, Gijs Luijten, Christina Gsaxner, Kim Grunert, Alexis Bader, Frank Hölzle, Rainer Röhrig, Matías de la Fuente, Jan Egger, Kunpeng Xie, Behrus Hinrichs-Puladi

January, 2026 JMIR Serious Games

Usability Study of Augmented Reality Visualization Modalities on Localization Accuracy in the Head and Neck: Randomized Crossover Trial

We systematically evaluated the localization accuracy between two augmented reality visualization modalities: see-through display with markerless inside-out tracking and video for different types of anatomical structures in the head and neck region. This randomized crossover trial provides insights into the usability and accuracy of AR-guided surgical navigation for head and neck procedures.

Ila Motmaen^†, Kunpeng Xie^†, Leon Schönbrunn, Johannes Berens, Kim Grunert, Behrus Puladi

† Equal contribution

June, 2024 Clinical Oral Investigations

Insights into Predicting Tooth Extraction from Panoramic Dental Images: Artificial Intelligence vs. Dentists

Tooth extraction is one of the most frequently performed medical procedures, yet determining whether a tooth should be extracted is not always straightforward. Using 26,956 single teeth images from 1,184 panoramic radiographs, we trained a ResNet50 network to classify teeth as either extraction-worthy or preservable. The best AI model achieved ROC-AUC of 0.901, significantly outperforming dentists’ average of 0.797. AI models could serve as decision support tools to monitor at-risk teeth and reduce errors in extraction indications.