基于S变换的喘鸣音数学形态学检测算法  

S-Transform Analysis of Wheeze Based on Mathematical Morphology

作　　者：张柯欣[1,2] 王雪峰[3] 魏巍[3] 龙哲[1] 王春武[4] 赵宏 

机构地区：[1]东北大学中荷生物医学与信息工程学院,辽宁沈阳110819 [2]辽宁中医药大学,辽宁沈阳110847 [3]辽宁中医药大学附属医院,辽宁沈阳110032 [4]吉林师范大学,吉林四平136000

出　　处：《辽宁中医药大学学报》2016年第6期73-76,共4页Journal of Liaoning University of Traditional Chinese Medicine

基　　金：国家自然科学基金资助项目(81273800)

摘　　要：目的:对喘鸣音进行即时识别和分析,是监控呼吸系统病情和不断改进治疗方法的一种必要手段。该文提出了一种从肺音中检测喘鸣音的方法。方法:这一方法是基于提取和分析采集数字肺音数据的S变换光谱信息自动识别喘鸣音。通过分析肺音信号的S变换光谱得到不同的数学形态学特征值。结果:该文提出的方法在喘鸣音的检测中达到了84%的准确率。结论:喘鸣音S变换光谱显示出了不规则直线特征。在肺音分析中,这是一种快速识别喘鸣音的有效特征。Objective：The immediate recognition and analysis of wheeze are very necessary means for monitoring and treatment improvement of respiratory disease. In this study,a method is proposed for the detection of wheeze from normal breath sounds. Methods：This method automatically recognizes wheeze based on the extraction and analysis of S-Transform spectral information from digitally recorded lung sounds. Various mathematical morphology feature sets were extracted through S-Transform Spectrogram analysis on pulmonary signals. Results：The results showed that the proposed method achieved 84% accuracy in the detection of wheeze. Conclusions：The S-Transform spectrograms of the wheeze in the lung exhibit irregular linear image features. For lung sound analysis,this is a useful feature that can be used for the immediate recognition and analysis of wheeze.

关 键 词：喘鸣音 S变换 数学形态学 肺音 

分 类 号：R443.4[医药卫生—诊断学]