A fusion-based approach for uterine cervical cancer histology image classification.

A fusion-based approach for uterine cervical cancer histology image classification.
复制标题

DOI:
10.1016/j.compmedimag.2013.08.001
复制
发表时间:
2013-10
期刊:
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
影响因子:
--
通讯作者:
Zuna R
Zuna R
中科院分区:
其他
文献类型:
--
作者:
De S;Stanley RJ;Lu C;Long R;Antani S;Thoma G;Zuna R

文献摘要

参考文献

被引文献

相似文献

专家病理学家通常对组织学切片进行目测解释,以诊断宫颈组织异常。我们研究了一种自动化的、局部的、基于融合的宫颈组织学图像分析方法,将宫颈鳞状上皮分为正常、CIN1、CIN2和CIN3级宫颈上皮内瘤变(CIN)。上皮图像分析方法包括中轴线确定、垂直段分割为中轴正交线、单个垂直段特征提取和分类、基于图像的分类和融合垂直段CIN等级的投票方案。使用61幅图像的结果显示,与全局图像特征相比,使用局部垂直分段融合的图像的准确分级效果至少提高了15.5%。
Expert pathologists commonly perform visual interpretation of histology slides for cervix tissue abnormality diagnosis. We investigated an automated, localized, fusion-based approach for cervix histology image analysis for squamous epithelium classification into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN). The epithelium image analysis approach includes medial axis determination, vertical segment partitioning as medial axis orthogonal cuts, individual vertical segment feature extraction and classification, and image-based classification using a voting scheme fusing the vertical segment CIN grades. Results using 61 images showed at least 15.5% CIN exact grade classification improvement using the localized vertical segment fusion versus global image features.
DOI: 10.1016/j.patcog.2012.01.021
发表时间: 2012-08-01
影响因子: 8
作者:
Lomenie, Nicolas;Racoceanu, Daniel
通讯作者: Racoceanu, Daniel
DOI: 10.1043/1543-2165-133.4.555
发表时间: 2009-04-01
影响因子: 4.6
作者:
Soenksen, Dirk
通讯作者: Soenksen, Dirk
DOI: 10.1016/j.jag.2011.09.014
发表时间: 2012-02-01
影响因子: 7.5
作者:
Pal, Mahesh
通讯作者: Pal, Mahesh
DOI: 10.1109/36.752194
发表时间: 1999-03-01
影响因子: 8.2
作者:
Soh, LK;Tsatsoulis, C
通讯作者: Tsatsoulis, C
DOI: 10.1111/j.1365-2559.1990.tb01141.x
发表时间: 1990-04-01
期刊: HISTOPATHOLOGY
影响因子: 6.4
作者:
ISMAIL, SM;COLCLOUGH, AB;NEWCOMBE, R
通讯作者: NEWCOMBE, R