Mobile Application for Oral Disease Detection using Federated Learning

TL;DR

This paper tackles privacy-sensitive oral-disease detection by deploying a Federated Learning (FL) pipeline that trains YOLOv8-based object detection models across edge devices, enabling self-assessment through a Progressive Web App called OralH. The approach uses a client-server FedAvg framework, with the global update defined as $f(w)=\sum_{k=1}^{K} \left(\frac{n_k}{n}\right) F_k(w)$, and compares local versus federated training across five clients using YOLOv5 and YOLOv8. Results show that YOLOv8 provides superior detection performance, and the federated setup improves or matches central training performance under non-IID data conditions, achieving the target mean Average Precision (mAP) of 80% after sufficient communication rounds. The system integrates camera capture, clinic recommendations via geolocation, offline web app functionality, and a privacy-preserving infrastructure, offering a practical tool for widespread, privacy-conscious oral health monitoring and guidance.

Abstract

The mouth, often regarded as a window to the internal state of the body, plays an important role in reflecting one's overall health. Poor oral hygiene has far-reaching consequences, contributing to severe conditions like heart disease, cancer, and diabetes, while inadequate care leads to discomfort, pain, and costly treatments. Federated Learning (FL) for object detection can be utilized for this use case due to the sensitivity of the oral image data of the patients. FL ensures data privacy by storing the images used for object detection on the local device and trains the model on the edge. The updated weights are federated to a central server where all the collected weights are updated via The Federated Averaging algorithm. Finally, we have developed a mobile app named OralH which provides user-friendly solutions, allowing people to conduct self-assessments through mouth scans and providing quick oral health insights. Upon detection of the issues, the application alerts the user about potential oral health concerns or diseases and provides details about dental clinics in the user's locality. Designed as a Progressive Web Application (PWA), the platform ensures ubiquitous access, catering to users across devices for a seamless experience. The application aims to provide state-of-the-art segmentation and detection techniques, leveraging the YOLOv8 object detection model to identify oral hygiene issues and diseases. This study deals with the benefits of leveraging FL in healthcare with promising real-world results.

Figures (4)

• Figure 1: Federated Learning Implementation.
• Figure 2: Oral Disease Detection Pipeline
• Figure 3: mAP vs. Number of Communication Rounds for the YOLOv5 Model
• Figure 4: mAP vs. Number of Communication Rounds for the YOLOv8 Model