O. E. Gorokhov, M. A. Kazachuk, I. S. Lazukhin, I. V. Mashechkin, L. L. Pankrat’eva, I. S. Popov
{"title":"Intelligent Technologies for the Segmentation and Classification of Microbiological Photographic Images","authors":"O. E. Gorokhov, M. A. Kazachuk, I. S. Lazukhin, I. V. Mashechkin, L. L. Pankrat’eva, I. S. Popov","doi":"10.3103/s0278641923040131","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The need to detect pathogenic microorganisms in the human body as quickly as possible is an important problem in medicine. One of today’s most common approaches of solving it is based on sowing biological material on nutrient media and then observing the growth of colonies. This technique has certain disadvantages associated mainly with the human factor, which can lead to errors in the final diagnosis. The aim of this work was to develop technologies for the intelligent processing of data from microbiological analyses based on photographic images of Petri dishes. This would reduce dependence on the human factor and improve key indicators of data processing. Results show that the developed heuristic and neural network approaches of detecting and classifying colonies of microorganisms are superior to those of existing ptocedures. They allow the automation of key stages of microbiological examination and thus can be applied in practice.</p>","PeriodicalId":501582,"journal":{"name":"Moscow University Computational Mathematics and Cybernetics","volume":"22 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Moscow University Computational Mathematics and Cybernetics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3103/s0278641923040131","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 need to detect pathogenic microorganisms in the human body as quickly as possible is an important problem in medicine. One of today’s most common approaches of solving it is based on sowing biological material on nutrient media and then observing the growth of colonies. This technique has certain disadvantages associated mainly with the human factor, which can lead to errors in the final diagnosis. The aim of this work was to develop technologies for the intelligent processing of data from microbiological analyses based on photographic images of Petri dishes. This would reduce dependence on the human factor and improve key indicators of data processing. Results show that the developed heuristic and neural network approaches of detecting and classifying colonies of microorganisms are superior to those of existing ptocedures. They allow the automation of key stages of microbiological examination and thus can be applied in practice.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
