TCM-Tongue: A Standardized Tongue Image Dataset with Pathological Annotations for AI-Assisted TCM Diagnosis

TL;DR

This paper introduces a large, standardized dataset of 6,719 tongue images with pathological annotations to facilitate AI development in traditional Chinese medicine diagnosis, addressing previous data scarcity and standardization issues.

Contribution

It provides the first large-scale, annotated tongue image dataset for AI-driven TCM diagnosis, supporting multiple annotation formats and benchmarking with various deep learning models.

Findings

Dataset supports multiple annotation formats (COCO, TXT, XML).

Benchmarking with nine deep learning models demonstrates dataset utility.

All images are annotated with clinically validated pathological labels.

Abstract

Traditional Chinese medicine (TCM) tongue diagnosis, while clinically valuable, faces standardization challenges due to subjective interpretation and inconsistent imaging protocols, compounded by the lack of large-scale, annotated datasets for AI development. To address this gap, we present the first specialized dataset for AI-driven TCM tongue diagnosis, comprising 6,719 high-quality images captured under standardized conditions and annotated with 20 pathological symptom categories (averaging 2.54 clinically validated labels per image, all verified by licensed TCM practitioners). The dataset supports multiple annotation formats (COCO, TXT, XML) for broad usability and has been benchmarked using nine deep learning models (YOLOv5/v7/v8 variants, SSD, and MobileNetV2) to demonstrate its utility for AI development. This resource provides a critical foundation for advancing reliable computational tools in TCM, bridging the data shortage that has hindered progress in the field, and facilitating the integration of AI into both research and clinical practice through standardized, high-quality diagnostic data.