生物医学工程研究2024，Vol.43Issue(2)：123-128,6.DOI:10.19529/j.cnki.1672-6278.2024.02.06
基于双编码特征提取路径的舌体分割方法
Tongue segmentation method based on dual encoding feature extraction path
摘要
Abstract
Aiming at the problems such as blurred tongue edge segmentation and small domain segmentation errors in tongue ima-ges,a segmentation method with dual encoding feature extraction paths was designed to obtain rich information features and assist tongue segmentation accurately.Firstly,a dual encoding feature extraction pathway was designed,in which the spatial information path preserved spatial information and generated high-resolution feature maps,and contextual information pathway enhanced the network's a-bility to extract multi-scale features.Then,a feature fusion module was adopted to merge the output features from spatial information paths and contextual information paths.Finally,a lightweight decoder module was adopted to reduce the number of network model pa-rameters and improve the computational efficiency of the model.The results showed that the precision,recall,F1 score,and mean in-tersection over union(MIoU)of the algorithm reached 98.82%,98.53%,98.60%,and 97.67%,respectively.The total parameter counts and floating-point operations per second(FLOPs)of the model were 7.54 M and 67.09 G.The results demonstrate that this algo-rithm effectively enhances the accuracy of tongue body segmentation,significantly improves the segmentation errors and edge fuzziness in small areas of the tongue body.This method can provide essential support for intelligent auxiliary analysis of traditional Chinese medi-cine tongue images.关键词
舌体分割/舌诊客观化/深度学习/Transformer/多尺度特征提取Key words
Tongue segmentation/Objectification of tongue diagnosis/Deep learning/Transformer/Multi-scale feature extraction分类
医药卫生引用本文复制引用
封晓燕,田琪,徐云峰,丛金玉,刘坤孟,王苹苹,魏本征..基于双编码特征提取路径的舌体分割方法[J].生物医学工程研究,2024,43(2):123-128,6.基金项目
山东省自然科学基金(ZR2022QG051,ZR2023QF094) （ZR2022QG051,ZR2023QF094）
山东省中医药科技项目(Q-2023045,Q-2023070) （Q-2023045,Q-2023070）
青岛市科技惠民示范专项项目(23-2-8-smjk-2-nsh). （23-2-8-smjk-2-nsh）
