| 选择性集成学习方法提取超声心动图的心内膜 |
| |
| 引用本文： | 郭翌, 汪源源, 孔德红, 舒先红. 选择性集成学习方法提取超声心动图的心内膜[J]. 声学学报, 2012, 37(3): 244-251. DOI: 10.15949/j.cnki.0371-0025.2012.03.001 |
| |
| 作者姓名： | 郭翌 汪源源 孔德红 舒先红 |
| |
| 作者单位： | 1 复旦大学电子工程系 上海 200433; |
| |
| 基金项目： | 国家自然科学基金(10974035)和上海市优秀学科带头人项目(10XD1400600)。 |
| |
| 摘 要： | 针对超声心动图特点,提出了一种选择性集成学习方法心内膜提取算法。先在超声心动图中根据形状先验知识确定感兴趣区域(ROI);然后对ROI中的每个候选像素点,提取多个不同性质的特征参数;将其输入选择性集成学习算法,得到模糊分类结果;最后将分类结果作为活动轮廓算法的外能,进一步获得光滑完整的心内膜边缘。对超声心动图分别采用本文方法和其他边缘提取方法进行比较实验。结果表明,相对于传统活动轮廓模型,本文方法分割图像的最小距离绝对差减少了2.56个像素点,面积重叠百分比提高了17.80%。可见,本文方法对噪声和初始轮廓不敏感,提取的心内膜边缘与医生手工勾画边缘最接近,性能优于现有算法。
|
| 收稿时间： | 2011-03-23 |
| 修稿时间： | 2011-07-07 |
Endocardium extraction using selective ensemble learning method in echocardiogram |
| |
| GUO Yi, WANG Yuanyuan, KONG Dehong, SHU Xianhong. Endocardium extraction using selective ensemble learning method in echocardiogram[J]. ACTA ACUSTICA, 2012, 37(3): 244-251. DOI: 10.15949/j.cnki.0371-0025.2012.03.001 |
| |
| Authors: | GUO Yi WANG Yuanyuan KONG Dehong SHU Xianhong |
| |
| Affiliation: | 1 Department of Electronic Engineering, Fudan University Shanghai 200433;2 Department of Echocardiography, Zhongshan Hospital of Fudan University Shanghai 200032 |
| |
| Abstract: | A novel endocardium extraction method was proposed for echocardiogram based on the selective ensemble learning algorithm.Firstly,the region of interest(ROI) was initialized by incorporating the shape-based global prior. Secondly,various features were extracted for each candidate pixel in the ROI.The local features were learned and tested through the selective ensemble learning algorithm to obtain the fuzzy results.Lastly,these pixels' values were conveniently used in the snake model as the outer energy to eliminate the ambiguity and obtain final contours.This method was evaluated and compared with other contour extraction methods for real echocardiograms.The results demonstrated that the mean absolute difference and percentage of area overlap have decreased by 2.56 pixels and increased by 17.80% respectively.The proposed method was insensitive to speckle and initial contour.Our segmented boundaries were very close to the manually-segmented ones.It was indicated that our method had a better overall performance than existed ones. |
| |
| Keywords: | |
|
| 点击此处可从《声学学报》浏览原始摘要信息 |
|
点击此处可从《声学学报》下载免费的PDF全文 |
|
