Ammonia-Net: A Multi-task Joint Learning Model for Multi-class Segmentation and Classification in Tooth-marked Tongue Diagnosis

TL;DR

Ammonia-Net is a novel multi-task deep learning model that simultaneously segments and classifies tooth-marked tongue images, improving diagnostic accuracy in Traditional Chinese Medicine through automated analysis.

Contribution

This is the first model to utilize semantic segmentation of tooth marks for classifying tooth-marked tongues, integrating multi-class segmentation and classification in a unified framework.

Findings

Achieves 99.06% accuracy in tongue classification

Attains 71.65% mIoU in segmentation tasks

Demonstrates effective multi-task learning for tongue diagnosis

Abstract

In Traditional Chinese Medicine, the tooth marks on the tongue, stemming from prolonged dental pressure, serve as a crucial indicator for assessing qi (yang) deficiency, which is intrinsically linked to visceral health. Manual diagnosis of tooth-marked tongue solely relies on experience. Nonetheless, the diversity in shape, color, and type of tooth marks poses a challenge to diagnostic accuracy and consistency. To address these problems, herein we propose a multi-task joint learning model named Ammonia-Net. This model employs a convolutional neural network-based architecture, specifically designed for multi-class segmentation and classification of tongue images. Ammonia-Net performs semantic segmentation of tongue images to identify tongue and tooth marks. With the assistance of segmentation output, it classifies the images into the desired number of classes: healthy tongue, light tongue, moderate tongue, and severe tongue. As far as we know, this is the first attempt to apply the semantic segmentation results of tooth marks for tooth-marked tongue classification. To train Ammonia-Net, we collect 856 tongue images from 856 subjects. After a number of extensive experiments, the experimental results show that the proposed model achieves 99.06% accuracy in the two-class classification task of tooth-marked tongue identification and 80.02%. As for the segmentation task, mIoU for tongue and tooth marks amounts to 71.65%.