中医舌象多模态数据集

本数据集源自安徽中医药大学第二附属医院、社区医院及相关企业。每例样本均包含中医临床四诊信息、高分辨率RGB舌象图、舌象高光谱数据及部分舌象热成像数据。其中，高光谱数据覆盖可见光至近红外波段（400–1000 nm），能够捕捉舌体表面及浅层组织的精细光谱信息。数据集信息维度丰富，配套数据涵盖受试者人口学信息、中医舌象要素（如舌色、苔色、舌形、苔质等）、全波段光谱数据、四诊症状记录及中医辨证分型，构建了“图像–光谱–临床”三位一体的综合数据库。所有数据均在统一光照环境、固定成像参数和标准操作流程下采集，保证了舌象数据的一致性与可比性。样本构成科学，覆盖高血压、高血糖、高血脂等慢病患者及健康对照人群，能够有效反映舌象多维度信息与疾病证候特征。This dataset is collected from the Second Affiliated Hospital of Anhui University of Chinese Medicine, community hospitals and related enterprises. Each sample contains four diagnostic information of Traditional Chinese Medicine (TCM), high-resolution RGB tongue images, hyperspectral data of tongue manifestations and partial tongue thermography data. The hyperspectral data covers the visible to near-infrared wavelength range (400–1000 nm), which can capture fine spectral information of the tongue surface and superficial tissues. This dataset boasts rich information dimensions. Its accompanying data covers the demographic information of subjects, TCM tongue manifestation features (e.g., tongue color, coating color, tongue shape, coating texture, etc.), full-band spectral data, four diagnostic symptom records and TCM syndrome differentiation patterns, and constructs a three-in-one comprehensive database integrating "image-spectroscopy-clinic". All data are collected under uniform lighting conditions, fixed imaging parameters and standard operating procedures, ensuring the consistency and comparability of tongue manifestation data. The sample composition is scientifically sound, covering patients with chronic diseases such as hypertension, hyperglycemia and hyperlipidemia, as well as healthy control groups, which can effectively reflect the multi-dimensional tongue manifestation information and disease syndrome characteristics.