基于瓶颈检测和分水岭算法的重叠宫颈细胞图像分割方法

段鹏; 程文播; 钱庆; 章强; 杨任兵; 潘宇骏

doi:10.3969/j.issn.1671-7104.2020.01.002

基于瓶颈检测和分水岭算法的重叠宫颈细胞图像分割方法

段鹏^1,2,
程文播^2, ,,
钱庆²,
章强²,
杨任兵²,
潘宇骏²

1 中国科学技术大学, 合肥市, 230026;
2 中国科学院苏州生物医学工程技术研究所, 苏州市, 215163

基金项目:

中国科学院科研仪器设备研制项目（YJKYYQ20170067，YJKYYQ20170068）；吉林省与中国科学院科技合作产业化专项资金（2018SYHZ0007）；中国科学院科技服务网络计划（KFJ-STS-SCYD-007）

详细信息

作者简介:
段鹏,E-mail:duanpeng@mail.ustc.edu.cn

通讯作者:
程文播,E-mail:chengwenbo@sibet.ac.cn

中图分类号: TP391.4
计量
- 文章访问数: 24
- HTML全文浏览量: 0
- PDF下载量: 4
出版历程
- 收稿日期: 2019-05-04
- 网络出版日期: 2024-02-19
- 刊出日期: 2020-01-29

Overlapping Cervical Cell Image Segmentation Based on Bottleneck Detection and Watershed Algorithm

1 University of Science and Technology of China, Hefei, 230026;
2 Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, 215163

摘要

摘要: 针对宫颈细胞图像存在大面积重叠的问题，该研究提出一种基于瓶颈检测和分水岭算法的图像分割方法。首先使用多边形近似得到细胞轮廓上的所有特征点，再通过瓶颈检测和椭圆拟合得到正确的分裂点对，从而确定重合区域的大致范围，对该区域的梯度图像使用分水岭算法得到内部的边界信息，最后与外轮廓进行叠加，得到重叠细胞的分割结果。实验结果表明：该算法能够从重叠的宫颈细胞图像中分割出单个细胞轮廓，具有很好的准确度和完整度。与医生手工标记的分割结果接近，与现有其它算法相比，分割效果更好。
- 宫颈细胞分割 /
- 瓶颈检测 /
- 重叠细胞 /
- 分水岭算法
Abstract: This study proposes an image segmentation method based on bottleneck detection and watershed algorithm to solve the problem of overlapping cervical cell image. First, we use polygon approximation to get all feature points on the cell contour and then use bottleneck detection and ellipse fitting to obtain the correct split point pairs. Therefore, the approximate range of the overlapping region was determined. The watershed algorithm was used to obtain the internal boundary information for the gradient image of the region. Finally, the segmentation results of the overlapped cells were obtained by superimposing with the outer contour. The experimental results show that this algorithm can segment the contour of a single cell from the overlapping cervical cell images with good accuracy and integrity. The segmentation result is close to that of doctors' manual marking, and the segmentation result is better than other existing algorithms.
- cervical cell division /
- bottleneck detection /
- adhesion cells /
- watershed algorithm

HTML全文

参考文献(13)

[1]	HUH W K, AULT K A, CHELMOW D, et al. Use of primary high-risk human papillomavirus testing for cervical cancer screening:Interim clinical guidance[J]. Gynecol Oncol, 2015, 136(2):178-182.
[2]	CRAMER D W. The role of cervical cytology in the declining morbidity and mortality of cervical cancer[J]. Cancer, 2015, 34(6):2018-2027.
[3]	TOTA J E, BENTLEY J, BLAKE J, et al. Introduction of molecular HPV testing as the primary technology in cervical cancer screening:Acting on evidence to change the current paradigm[J]. Prev Med, 2017, 98:5-14.
[4]	ZHOU Y, HAO Y, LI Y, et al. Amplification and up-regulation of MIR30D was associated with disease progression of cervical squamous cell carcinomas[J]. Bmc Cancer, 2017, 17(1):230.
[5]	TAREEF A, YANG S, CAI W, et al. Automatic segmentation of overlapping cervical smear cells based on local distinctive features and guided shape deformation[J]. Neurocomputing, 2017, 221:94-107.
[6]	SANYAL P, GANGULI P, BARUI S, et al. Pilot study of an open-source image analysis software for automated screening of conventional cervical smears[J]. J Cytol, 2018, 35(2):71-74.
[7]	张珊珊.宫颈LCT图像分割算法的研究与实现[D].广州:华南理工大学,2013.
[8]	RANNOU F, GREGOR J. Equilateral polygon approximation of closed contours[J]. Pattern Recogn, 2015, 29(7):1105-1115.
[9]	张丙奎.基于瓶颈检测和Dijkstra算法的重叠细胞分割方法[J].技术与市场, 2016, 23(12):174-175.
[10]	LIAO M, ZHAO Y Q, LI X H, et al. Automatic segmentation for cell images based on bottleneck detection and ellipse fitting[J]. Neurocomputing, 2016, 173(P3):615-622.
[11]	张竣凯.基于瓶颈点探测与椭圆拟合的细胞图像分割方法探究[J].电子测试, 2013(10):112-114.
[12]	ZHAO M, WU A, SONG J, et al. Automatic screening of cervical cells using block image processing[J]. Biomed Eng Online, 2016, 15(1):14.
[13]	TAREEF A, SONG Y, HUANG H, et al. Multi-pass fast watershed for accurate segmentation of overlapping cervical cells[J]. IEEE T Med Imaging, 2018, 37(9):2044-2059.

施引文献(13)

期刊类型引用(3)

1.	毛永文，韩俊英，刘成忠. 基于机器视觉的胡麻种子自动化考种方法. 智慧农业(中英文). 2024(01): 135-146 . 百度学术
2.	黎丹雨. 乳腺癌病理细胞图像的识别研究. 现代计算机. 2021(18): 96-102 . 百度学术
3.	张灿，陈玮，尹钟. 基于弱监督宫颈细胞图像的语义分割方法. 电子科技. 2021(12): 68-74 . 百度学术