基于肺音谱图Hough变换的喘鸣音识别方法  

Detection of Wheeze Based on Hough Transform of Spectrogram

作　　者：张柯欣[1,2] 龙哲[1] 王雪峰[3] 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110169 [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

出　　处：《东北大学学报（自然科学版）》2017年第11期1534-1537,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(81273800)

摘　　要：提出了一种基于Hough变换从肺音的STFT光谱图中检测喘鸣音的方法.这一方法先对采集的数字肺音数据的STFT谱图进行ROI区域的截取,再利用Canny算子进行图像边缘检测,最后基于Hough变换数据的分析来自动识别喘鸣音.临床分析的数据包括临床采集的肺音和国际上共享的肺音文件.Hough变换检测方法在60例喘鸣音的检测中达到了87%的准确率,70例正常呼吸音的识别率达到74%.A method based on Hough transform to detect the wheezes from the STFT spectrum of the lung sounds was presented. This method first clips the ROI region of the STFT spectrum of the digital lung sound data,then uses the Canny operator for image edge detection,and finally identifies the wheezes automatically based on the analysis of Hough transform data. The data for clinical analysis includes the clinical acquisition of lung sounds and the international shared lung sound files. Hough transform detection method got the accuracy rate of 87% in the detection of 60 cases of wheezes,and 74% for the 70 cases of normal respiratory sound.

关 键 词：喘鸣音 HOUGH变换 STFT变换 光谱图 肺音识别 

分 类 号：R443.4[医药卫生—诊断学]