[1]曾果△,刘彦荣,王力,等.基于图像融合的乳腺肿瘤感兴趣区域边缘识别*[J].生物医学工程研究,2020,04:337-341.
ZENG Guo,LIU Yanrong,WANG Li,et al.Edge recognition of breast tumor region of interest based on image fusion[J].Journal of Biomedical Engineering Research,2020,04:337-341.
点击复制
基于图像融合的乳腺肿瘤感兴趣区域边缘识别*(PDF)
《生物医学工程研究》[ISSN:1006-6977/CN:61-1281/TN]
- 期数:
-
2020年04期
- 页码:
-
337-341
- 栏目:
-
- 出版日期:
-
2020-12-25
文章信息/Info
- Title:
-
Edge recognition of breast tumor region of interest based on image fusion
- 文章编号:
-
1672-6278 (2020)04-0337-05
- 作者:
-
曾果1△; 刘彦荣1; 王力1; 许方彧1; 蒋烈夫2; 靳玉川3
-
1.南阳市第二人民医院医学影像中心,南阳 473000;2.南阳医学高等专科学校,南阳 473000;3.河北医科大学,石家庄 050017
- Author(s):
-
ZENG Guo1; LIU Yanrong1; WANG Li1; XU Fangyu1; JIANG Liefu2; JIN Yuchuan3
-
1.Medical Imaging Center,Nanyang Second General Hospital,Nanyang 473000,China;2.Nanyang Medical College,Nanyang 473000;3.Hebei Medical University,Shijiazhuang 050017,China
-
- 关键词:
-
乳腺肿瘤; 边缘识别; 准确率; 图像融合; 加权平均
- Keywords:
-
Breast tumor; Edge recognition; Accuracy; Image fusion; Weighted average
- 分类号:
-
R318;R814.3
- DOI:
-
10.19529/j.cnki.1672-6278.2020.04.03
- 文献标识码:
-
A
- 摘要:
-
目前,乳腺肿瘤感兴趣区域(region of interest,ROI)边缘的识别方法中,单一的病变检查图像无法全面反映出肿瘤情况,导致识别的准确率不足。针对该问题,本研究提出一种基于图像融合的乳腺肿瘤感兴趣区域边缘识别方法。首先运用加权平均图像融合技术融合不同设备采集的病理图像,然后采用Normalized Cut法提取图像的肿瘤边缘。利用核极限学习算法,建立肿瘤感兴趣区域模型后,输入肿瘤边缘得出肿瘤特征因素,最后使用ROI技术实现乳腺肿瘤感兴趣区域边缘识别。对比验证表明,本研究方法的识别准确率更高,具有可行性。
- Abstract:
-
In the region of interest (ROI) edge recognition method for breast tumors, the single inspection lesion image can not fully reflect the tumor, which causes insufficient recognition accuracy. In view of this problem, we proposed an edge recognition method of breast tumor region of interest based on image fusion. The pathological images collected by different devices were fused by using weighted averange image fusion technology, after the ROI model of tumor was established by using kernel limit learning algorithm, the tumor edge was inputted to get the tumor feature factors. Finally, ROI technique was used to realize the edge recognition of the breast tumor region of interest. Comparative verification shows that this method has higher recognition accuracy,and it is feasible.
备注/Memo
- 备注/Memo:
-
(收稿日期:2020-03-11)河南省中医管理局项目(2018ZY1007)。△通信作者Email:zq217218219@163.com
更新日期/Last Update:
2021-02-05