基于融合的子宫颈癌组织学图像分类方法。
A fusion-based approach for uterine cervical cancer histology image classification.
机构信息
Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409-0040, USA.
出版信息
Comput Med Imaging Graph. 2013 Oct-Dec;37(7-8):475-87. doi: 10.1016/j.compmedimag.2013.08.001. Epub 2013 Sep 1.
Abstract
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.
摘要
专家病理学家通常对宫颈组织异常进行组织学切片的目视判读。我们研究了一种自动化、局部化、基于融合的方法，用于宫颈组织学图像分析，以将鳞状上皮分类为正常、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确定、垂直段分割作为中轴正交切割、单个垂直段特征提取和分类，以及使用融合垂直段 CIN 级别的投票方案进行基于图像的分类。使用 61 张图像的结果表明，与全局图像特征相比，使用局部化的垂直段融合可至少提高 15.5%的 CIN 确切分级分类。
相似文献
1
A fusion-based approach for uterine cervical cancer histology image classification.基于融合的子宫颈癌组织学图像分类方法。
Comput Med Imaging Graph. 2013 Oct-Dec;37(7-8):475-87. doi: 10.1016/j.compmedimag.2013.08.001. Epub 2013 Sep 1.
2
Nuclei-Based Features for Uterine Cervical Cancer Histology Image Analysis With Fusion-Based Classification.基于细胞核特征的子宫颈癌组织学图像分析及融合分类法
IEEE J Biomed Health Inform. 2016 Nov;20(6):1595-1607. doi: 10.1109/JBHI.2015.2483318. Epub 2015 Oct 26.
3
Enhancements in localized classification for uterine cervical cancer digital histology image assessment.子宫颈癌数字组织学图像评估中局部分类的改进。
J Pathol Inform. 2016 Dec 30;7:51. doi: 10.4103/2153-3539.197193. eCollection 2016.
4
Hyperspectral wide gap second derivative analysis for in vivo detection of cervical intraepithelial neoplasia.用于宫颈上皮内瘤变体内检测的高光谱宽间隙二阶导数分析
J Biomed Opt. 2015 Dec;20(12):121303. doi: 10.1117/1.JBO.20.12.121303.
5
DeepCIN: Attention-Based Cervical histology Image Classification with Sequential Feature Modeling for Pathologist-Level Accuracy.深度宫颈影像网络（DeepCIN）：基于注意力机制的宫颈组织学图像分类，采用序列特征建模以实现病理学家级别的准确率。
J Pathol Inform. 2020 Dec 24;11:40. doi: 10.4103/jpi.jpi_50_20. eCollection 2020.
6
An automated machine vision system for the histological grading of cervical intraepithelial neoplasia (CIN).一种用于宫颈上皮内瘤变（CIN）组织学分级的自动化机器视觉系统。
J Pathol. 2000 Nov;192(3):351-62. doi: 10.1002/1096-9896(2000)9999:9999<::AID-PATH708>3.0.CO;2-I.
7
[Diagnosis and grading of cervical intraepithelial neoplasias].[宫颈上皮内瘤变的诊断与分级]
Pathologe. 2012 Mar;33(2):118-23. doi: 10.1007/s00292-011-1549-5.
8
Clinical study of quantitative diagnosis of early cervical cancer based on the classification of acetowhitening kinetics.基于醋酸白动力学分类的早期宫颈癌定量诊断的临床研究。
J Biomed Opt. 2010 Mar-Apr;15(2):026001. doi: 10.1117/1.3365940.
9
An Integrated Approach to Automated Diagnosis of Cervical Intraepithelial Neoplasia in Digital Histology Images.一种数字组织病理学图像中宫颈上皮内瘤变自动诊断的综合方法。
Stud Health Technol Inform. 2023 May 18;302:615-616. doi: 10.3233/SHTI230220.
10
Sources of scattering in cervical tissue: determination of the scattering coefficient by confocal microscopy.宫颈组织中的散射源：通过共聚焦显微镜测定散射系数
Appl Opt. 2005 Apr 10;44(11):2072-81. doi: 10.1364/ao.44.002072.
引用本文的文献
1
Exploratory Analysis of Radiomics and Pathomics in Uterine Corpus Endometrial Carcinoma.子宫体子宫内膜癌的放射组学和病理组学探索性分析
Sci Rep. 2024 Dec 28;14(1):30727. doi: 10.1038/s41598-024-78987-y.
2
Deep multiple-instance learning for abnormal cell detection in cervical histopathology images.基于深度多重实例学习的宫颈组织病理图像中异常细胞检测
Comput Biol Med. 2021 Nov;138:104890. doi: 10.1016/j.compbiomed.2021.104890. Epub 2021 Sep 28.
3
EpithNet: Deep Regression for Epithelium Segmentation in Cervical Histology Images.EpithNet：用于宫颈组织学图像上皮细胞分割的深度回归
J Pathol Inform. 2020 Mar 30;11:10. doi: 10.4103/jpi.jpi_53_19. eCollection 2020.
4
Skin Disease Recognition Method Based on Image Color and Texture Features.基于图像颜色和纹理特征的皮肤病识别方法
Comput Math Methods Med. 2018 Aug 26;2018:8145713. doi: 10.1155/2018/8145713. eCollection 2018.
5
Multifeature Quantification of Nuclear Properties from Images of H&E-Stained Biopsy Material for Investigating Changes in Nuclear Structure with Advancing CIN Grade.从 H&E 染色的活检材料图像中对核性质进行多特征定量，以研究核结构随 CIN 分级进展的变化。
J Healthc Eng. 2018 Jul 5;2018:6358189. doi: 10.1155/2018/6358189. eCollection 2018.
6
Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels.通过超像素进行数字化组织学图像中的深度学习细胞核检测
J Pathol Inform. 2018 Mar 5;9:5. doi: 10.4103/jpi.jpi_74_17. eCollection 2018.
7
Overexpression of ezrin and galectin-3 as predictors of poor prognosis of cervical cancer.埃兹蛋白和半乳糖凝集素-3的过表达作为宫颈癌预后不良的预测指标。
Braz J Med Biol Res. 2017 Mar 23;50(4):e5356. doi: 10.1590/1414-431X20165356.
8
Enhancements in localized classification for uterine cervical cancer digital histology image assessment.子宫颈癌数字组织学图像评估中局部分类的改进。
J Pathol Inform. 2016 Dec 30;7:51. doi: 10.4103/2153-3539.197193. eCollection 2016.
9
Nuclei-Based Features for Uterine Cervical Cancer Histology Image Analysis With Fusion-Based Classification.基于细胞核特征的子宫颈癌组织学图像分析及融合分类法
IEEE J Biomed Health Inform. 2016 Nov;20(6):1595-1607. doi: 10.1109/JBHI.2015.2483318. Epub 2015 Oct 26.
本文引用的文献
1
Molecular mapping of high-grade cervical intraepithelial neoplasia shows etiological dominance of HPV16.高级别宫颈上皮内瘤变的分子图谱显示 HPV16 的病因优势。
Int J Cancer. 2012 Sep 15;131(6):E946-53. doi: 10.1002/ijc.27532. Epub 2012 Apr 16.
2
An image feature-based approach to automatically find images for application to clinical decision support.基于图像特征的方法，用于自动查找图像以应用于临床决策支持。
Comput Med Imaging Graph. 2011 Jul;35(5):365-72. doi: 10.1016/j.compmedimag.2010.11.008. Epub 2010 Dec 8.
3
A unified set of analysis tools for uterine cervix image segmentation.用于子宫颈图像分割的统一分析工具集。
Comput Med Imaging Graph. 2010 Dec;34(8):593-604. doi: 10.1016/j.compmedimag.2010.04.002. Epub 2010 May 26.
4
Digital pathology at the crossroads of major health care trends: corporate innovation as an engine for change.数字病理学处于主要医疗保健趋势的十字路口：企业创新作为变革的引擎。
Arch Pathol Lab Med. 2009 Apr;133(4):555-9. doi: 10.5858/133.4.555.
5
A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images.一种基于基函数特征的方法用于皮肤科皮肤镜图像中的皮肤病变鉴别。
Skin Res Technol. 2008 Nov;14(4):425-35. doi: 10.1111/j.1600-0846.2008.00307.x.
6
A color-based approach for automated segmentation in tumor tissue classification.一种基于颜色的方法用于肿瘤组织分类中的自动分割。
Annu Int Conf IEEE Eng Med Biol Soc. 2007;2007:6577-80. doi: 10.1109/IEMBS.2007.4353866.
7
Segmentation of squamous epithelium from ultra-large cervical histological virtual slides.从超大宫颈组织学虚拟切片中分割鳞状上皮。
Annu Int Conf IEEE Eng Med Biol Soc. 2007;2007:775-8. doi: 10.1109/IEMBS.2007.4352405.
8
Evaluation of colposcopically directed cervical biopsies yielding a histologic diagnosis of CIN 1,2.对经阴道镜引导下宫颈活检组织进行评估，这些活检组织的组织学诊断为CIN 1、2级。
J Low Genit Tract Dis. 2002 Apr;6(2):80-3. doi: 10.1097/00128360-200204000-00003.
9
Subvisual chromatin changes in cervical epithelium measured by texture image analysis and correlated with HPV.通过纹理图像分析测量宫颈上皮中视觉下的染色质变化，并与HPV相关联。
Gynecol Oncol. 2005 Dec;99(3 Suppl 1):S16-23. doi: 10.1016/j.ygyno.2005.07.037. Epub 2005 Sep 26.
10
Quantitative histopathological analysis of cervical intra-epithelial neoplasia sections: methodological issues.宫颈上皮内瘤变切片的定量组织病理学分析：方法学问题
Cell Oncol. 2004;26(1-2):31-43. doi: 10.1155/2004/238769.
Zotero 插件