English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

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

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