We are glad to share with you that our recent conference paper “GumAgent: Towards an Accessible Gum Disease Detection Tool Leveraging Vision Language Model” has been accepted in 2025 International Conference on Information Communication and Signal Processing (ICICSP):
- C. Cheng, H. S.-H. Tsang, R. T.-C. Hsung, Y.-L. Chan, W.-L. Lo, and W. Lam, ” GumAgent: Towards an Accessible Gum Disease Detection Tool Leveraging Vision Language Model,” 2025 8th International Conference on Information Communication and Signal Processing (ICICSP 2025), Xi’an, China, September, 2025.
Paper Abstract
Gum disease affects more than half of people worldwide and is a big health and economic concern. To help tackle this, our team has developed GumAgent—a smart and easy-to-use tool that can detect gum disease from photos.
GumAgent uses advanced artificial intelligence techniques including vision language model (VLM) Gemma, to first make sure the photo is actually of a person’s mouth and gums. It can filter out irrelevant images, like pictures of dentures or unrelated objects, so only useful photos are analyzed. Then, the tool checks if there’s enough gum area in the photo to look at, and if so, it uses a deep learning model to check for signs of gum disease.
This new technology aims to make it simpler for people to keep an eye on their gum health at home, without needing a visit to the dentist every time. Our approach hopes to improve dental care access and help catch gum problems early.
We will keep advancing our collaboration with leading research institutions to develop cutting-edge technologies!
The research team members
Hong Kong Chu Hai College
- Mr Chi-Chung Cheng, Research Assistant in the Department of Computer Science
- Dr Harris Sik-Ho Tsang, Assistant Professor in the Department of Computer Science
- Dr. Richard Tai-Chiu Hsung, Associate Professor in the Department of Computer Science
- Prof. Wai-Lun Lo, Professor in the Department of Computer Science
The Hong Kong Polytechnic University
- Dr Yui-Lam Chan, Associate Professor in the Department of Electrical and Electronic Engineering
The University of Hong Kong
- Prof. Walter Lam, Professor in the Faculty of Dentistry
Some photos of the authors and papers
User-friendly Assessible Gum Disease Detection Tool Incoporating Proposed GumAgent into the Workflow of Gum Health Self-Monitoring.
Overall Framework: We Incorporate GumAgent into Gum Disease Detection Workflow.
Our proposed approach obtains the highest accuracies by incorporating VLM into our gum health detection software workflow.
