Image segmentation technique to support automatic marking of objects in endoscopic images

Informatization and communication Pub Date : 2021-02-16 DOI:10.34219/2078-8320-2021-12-2-146-154

R. Akhmetvaleev, I. Lackman, D. V. Popov, M.V. Krasnoperov

{"title":"Image segmentation technique to support automatic marking of objects in endoscopic images","authors":"R. Akhmetvaleev, I. Lackman, D. V. Popov, M.V. Krasnoperov","doi":"10.34219/2078-8320-2021-12-2-146-154","DOIUrl":null,"url":null,"abstract":"The aim of this study is to develop a method for visual segmentation of various objects of endoscopic images based on a collection of endoscopic images. The method was developed on the basis of a collection of images obtained by ENVD LLC on a contractual basis with medical organizations of the Republic of Bashkortostan, Russia. The collection consists of 70 endoscopic images recording clinical cases diagnosed in accordance with the Paris Tumor Classification of Gastrointestinal Diseases. A number of machine vision operations were carried out, including image preprocessing, image sampling, and subsequent clustering for the purpose of image segmentation. Results: A technique for the analysis of endoscopic images was developed, which makes it possible to obtain the contours of objects of interest to a specialist performing endoscopy. Conclusion. The developed solution allows to speed up and improve the procedure for marking endoscopic images, which in turn prepares a platform for further processing of endoscopic images, for example, nosological classification of neoplasms.","PeriodicalId":299496,"journal":{"name":"Informatization and communication","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informatization and communication","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.34219/2078-8320-2021-12-2-146-154","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

The aim of this study is to develop a method for visual segmentation of various objects of endoscopic images based on a collection of endoscopic images. The method was developed on the basis of a collection of images obtained by ENVD LLC on a contractual basis with medical organizations of the Republic of Bashkortostan, Russia. The collection consists of 70 endoscopic images recording clinical cases diagnosed in accordance with the Paris Tumor Classification of Gastrointestinal Diseases. A number of machine vision operations were carried out, including image preprocessing, image sampling, and subsequent clustering for the purpose of image segmentation. Results: A technique for the analysis of endoscopic images was developed, which makes it possible to obtain the contours of objects of interest to a specialist performing endoscopy. Conclusion. The developed solution allows to speed up and improve the procedure for marking endoscopic images, which in turn prepares a platform for further processing of endoscopic images, for example, nosological classification of neoplasms.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

支持内窥镜图像中物体自动标记的图像分割技术

本研究的目的是开发一种基于内窥镜图像集合的内窥镜图像中各种物体的视觉分割方法。该方法是根据ENVD LLC根据与俄罗斯巴什科尔托斯坦共和国医疗组织签订的合同获得的图像集开发的。该集合包括70个内镜图像，记录了根据胃肠道疾病巴黎肿瘤分类诊断的临床病例。进行了一系列机器视觉操作，包括图像预处理、图像采样和随后的聚类，以实现图像分割。结果:开发了一种内窥镜图像分析技术，可以获得专家执行内窥镜检查感兴趣的物体的轮廓。结论。开发的解决方案可以加快和改进内窥镜图像标记的程序，这反过来又为内窥镜图像的进一步处理(例如肿瘤的分类学分类)准备了平台。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Informatization and communication

自引率

0.00%

发文量