通讯作者: 垢德双, 294107865@qq.com

DOI：10.12201/bmr.202404.00020

The Research of Tongue Features Base on Deep Learning

• 摘要：目的/意义 本研究将深度学习技术应用于舌象分析中，以达到舌象分析自动化的目的，并为中医舌象标准化、客观性提供参考依据，进一步推进中医诊疗技术现代化进程。方法/过程 首先构建了一个新的以区域关联性为基础引入标签松弛技术的语义分割损失函数，显式约束舌象分割模型学习局部区域各像素关联性的同时，对错误标签一定的冗余能力，其次从舌象特征中内含的是否颜色相关的潜在先验出发，在模型构建阶段将舌象特征仅解耦为两类下游多标签分类任务，在加速模型拟合的同时有效降低了模型的复杂度。结果/结论 最后，在自建数据集上，验证了本文所提算法的有效性，舌象分割MIoU指标为96.57%，舌象分析宏F1值、平均准确率分别为88.58%、82.59%。

  关键词： 迁移学习；舌象特征；深度学习；舌体分割；中医舌诊; ; ; ; 

   

  Abstract: Purpose/Significance The present research utilizes deep learning methodologies within the context of tongue manifestation analysis, with the objective of automating the process and contributing to the establishment of standardized and objective benchmarks for tongue diagnosis in Traditional Chinese Medicine (TCM). This work endeavors to significantly propel the progression towards the modernization of TCM diagnostic procedures. Method/Process Firstly, a new semantic segmentation loss function has been devised that fundamentally integrates regional association and label relaxation techniques. This advanced function imposes a constraint on the segmentation model such that it learns to account for the inter-pixel relationships within specific regions of the tongue images, while simultaneously endowing the model with a degree of resilience against inaccurately annotated labels. Secondly, leveraging the latent color-related priors inherently present within the characteristics of tongue images, a strategic decision was made to decompose these features exclusively into two separate streams for subsequent multi-label classification tasks during the models architectural design stage. This strategic maneuver serves to expedite the models convergence process while significantly diminishing its overall complexity. Result/Conclusion Lastly, the effectiveness of the algorithm proposed in this paper was validated through experimentation on our custom-built dataset. The results showed an impressive 96.57% Mean Intersection over Union (MIoU) score for tongue image segmentation, along with macro F1-score and average accuracy values of 88.58% and 82.59%, respectively.

  Key words: Transfer Learning; Tongue Image Features; Deep Learning; Tongue Segmentation; Tongue Diagnosis of Traditional Chinese Medicine

  提交时间：2024-04-11

  版权声明：作者本人独立拥有该论文的版权，预印本系统仅拥有论文的永久保存权利。任何人未经允许不得重复使用。
• html

• 图表

• 唐智贤, 李萍, 曾雅楠, 张一乐, 郑宇翔, 李恒峰, 魏千翔, 肖正光. 计算机辅助舌象分析诊断的研究进展. 2021. doi: 10.12201/bmr.202106.00006

  刘庆金, 王锐, 苗元青. 基于深度学习的无症状心肌缺血动态心电图智能检测研究. 2021. doi: 10.12201/bmr.202111.00009

  顾耀文, 李姣. 基于无监督深度学习的电子健康档案数据挖掘技术研究进展. 2021. doi: 10.12201/bmr.202104.00013

  吴胜男, 吴佳辉, 董继宗, 蒋环宇, 王璐琦, 王欣瑶. 基于二分网络表示学习的医学实体关系预测研究. 2024. doi: 10.12201/bmr.202407.00041

  金丽珠, 葛辉, 郭青, 李少琼, 杜雪杰. 基于气象因素和机器学习的流感疫情预警研究. 2021. doi: 10.12201/bmr.202012.00008

  冯利, 岳小飞. 9种结合式机器学习算法在基于高维数据的肿瘤早期诊断准确性的比较研究. 2021. doi: 10.12201/bmr.202108.00016

  兰雨姗, 郑思, 李姣. 机器学习方法在因果推断中混杂因素控制的应用. 2022. doi: 10.12201/bmr.202203.00015

  朱志文, 齐国强, 杨恺熠, 赵永根, 余卓, 俞刚. 基于多中心横向联邦学习的以咳嗽为第一主诉的儿童疾病医疗数据共享模型. 2022. doi: 10.12201/bmr.202207.00004

  郭哲韬, 石文丽, 杨涛. 基于语音识别的中医临床诊疗智能语音助理的设计与实现. 2021. doi: 10.12201/bmr.202110.00013

  刘彬, 肖晓霞, 邹北骥, 周展, 郑立瑞, 谭建聪. 融合汉字部首的BERT-BiLSTM-CRF中医医案命名实体识别模型. 2023. doi: 10.12201/bmr.202303.00004

• 序号	提交日期	编号	操作
  1	2024-02-19	bmr.202404.00020V1	下载

• 公开评论  匿名评论  仅发给作者 提交评论