The Traditional Chinese Medicine (TCM) Tongue Diagnosis Indices of Upper Gastrointestinal (UGI) Disorders

Upper gastrointestinal disorders are common in clinical practice. Currently, the diagnosis of peptic ulcer only depends on laboratory exams such as clinical symptoms, blood test, urine test and feces test. But the result can be only auxiliary exams which don't gain correct diagnosis on helping assess ulcer severity. As the most suitable diagnosis method, panendoscopy can directly observe lesions, judge disease severity, carry out a biopsy, test lesion is benignant or malignant, Helicobacter Pylorus infection or not, the degree of inflammation, etc. But panendoscopy belongs to invasive test. If we can observe tongue characteristics of patients with upper gastrointestinal diseases through scientific tongue diagnosis, physical discomfort caused by the test will be significantly reduced.

Based on clinical observational study, this project will employ the Automatic Tongue Diagnosis System (ATDS) developed. The ATDS was developed to capture tongue images and extract features reliably to assist the diagnosis of TCM practitioners demonstrates the steps in the three major functions, i.e., image capturing and color calibration, tongues area segmentation, and tongue feature extraction, included in the ATDS.

Variations in background lighting may change the color and brightness of the acquired images, greatly affecting consistency and stability of the extracted tongue features. The ATDS developed can automatically correct lighting and color deviation caused by the change of background lighting with a color bar attached in the ATDS. The color bar placed beside the patient is used for color calibration to make sure the image quality is consistent even taken at different circumstances. Tongue images are analyzed by first isolating the tongue region within an image to eliminate irrelevant lower facial portions and background surrounding the tongue, thereby facilitating feature identification and extraction; and then extracting the tongue features by employing criteria such as the aspect ratio, color composition, location, shape, and color distribution of the tongue, as well as the quantity of neighboring pixels. Features including tongue color, tongue fissure, fur color, fur thickness, ecchymosis, tooth mark, red dot, saliva, and tongue shape are extracted to further generate detailed information regarding length, area, moisture, and number of fissures, marks, and dots to be employed in tongue diagnosis. Nine primary tongue features, including tongue color (slightly white, slightly red, red, dark red, dark purple), fur color (white, yellow, dye), fur thickness (none, thin, thick), saliva (none, little, normal, excessive), tongue shape (thin and small, moderate, fat and large), tongue fissure, red dot, ecchymosis, and tooth marks (the last four features are divided into categories of none, mild, moderate, and severe), are selected for tongue diagnosis.

This project will employ the ATDS verified to extract the tongue features of patients with upper gastrointestinal disorders. Through statistically analysis of the data collected and cross-referencing the existing indices of western medicine, we aim to derive meaningful TCM indices from tongue diagnosis of upper gastrointestinal diseases, such as peptic ulcer, etc. A TCM indices derived through the non-intrusive tongue diagnosis procedure can provide valuable information for clinical doctors to analyze the current status of a patient and dynamically schedule a treatment plan, facilitating early detection and diagnosis of upper gastrointestinal disorders.