research
Dental radiologic ai
This study was conducted in collaboration with Vuno Inc. to develop an algorithm for automatically detecting, classifying, and segmenting diseases in a dental panorama.
In this study, a deep learning-based method for developing an automated diagnostic support system that detects periodontal bone loss in the panoramic dental radiographs is proposed. The presented method called DeNTNet not only detects lesions but also provides the corresponding teeth numbers of the lesion according to dental federation notation. DeNTNet applies deep convolutional neural networks(CNNs) using transfer learning and clinical prior knowledge to overcome the morphological variation of the lesions and imbalanced training dataset.
Chatbot for Medical Appointment
This project is a national project of the Korea Industrial Complex Corporation under the Ministry of SMEs and Startups, and was started in 2018 to develop and commercialize a web-based medical appointment chatbot program for Korea University Medical Center. We developed a medicine chatbot program through a call center treatment reservation program company and succeeded in commercializing it in 2019.
Platform for personal information utilization
This project is a MyData pilot project hosted by the Ministry of Science and ICT in 2019. It integrates and analyzes consumer card consumption patterns, meal consumption patterns, and medical record data owned by a total of 10 institutions including BC Card, Mango Plate, and Korea University Medical Center. This was done to provide customized wellness services to people.
Development of cervical spine measurement point automation and bone growth prediction program using lateral radiographs
This research is conducted to predict the hand-wrist maturation stages based on the cervical vertebrae (CV) images, and to analyse the accuracy of the proposed algorithms. After the program development is completed, domestic patent registration and US/China patent application are in progress. The research results were also selected in the top 13% proceeding of MICCAI 2022.
Ar/vr/xr based training system
We were selected as the overall lead agency for the 2021 dental AI/XR-based digital twin education and training platform development project and developed a VR and haptic-based dental education and training platform.
The purpose of this study is to develop a surreal dental AI and XR education and training system and contents that medical staff and students can feel and experience in real life, from basic dental examinations that require safety and accuracy to patient response and implant surgery. In other words, we intend to develop a surreal dental treatment education and training system and contents using digital twin, AI, and XR technologies and evaluate safety, effectiveness, and usability.