Shannen Latisha, Albert Christopher Halim, Regan Ricardo, Derwin Suhartono
{"title":"COVID-19 Detection Model on Chest CT Scan and X-ray Images Using VGG16 Convolutional Neural Network","authors":"Shannen Latisha, Albert Christopher Halim, Regan Ricardo, Derwin Suhartono","doi":"10.1109/ISRITI54043.2021.9702839","DOIUrl":null,"url":null,"abstract":"In this pandemic of COVID-19, many people's lives are highly affected in various kinds of aspects. Tests are conducted due to the rising number of infected people, with the PCR test as the current gold standard for many. However, many experts consider the PCR test inaccurate due to the resulting false negative and false positive test results. In order to solve the problem, through this paper, the use of a deep learning model is proposed based on a customized VGG16 CNN as a way to identify the presence COVID-19 virus. The biomarkers used in this paper are X-ray and CT scan images of the lungs. At the end of the research, it can be concluded that both CT scan and X-ray images can be used to detect COVID-19 by using VGG16. However, by comparing the performance of the proposed X-ray and CT scan biomarker-based models, it can be inferred that the X-ray biomarker-based model obtained a higher accuracy score of 97% compared to the CT scan-based model with 93% accuracy. This research proved that the X-ray model got a better score and is a better alternative than CT scan, although both have potential and can be considered accurate alternatives to the PCR tests.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISRITI54043.2021.9702839","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In this pandemic of COVID-19, many people's lives are highly affected in various kinds of aspects. Tests are conducted due to the rising number of infected people, with the PCR test as the current gold standard for many. However, many experts consider the PCR test inaccurate due to the resulting false negative and false positive test results. In order to solve the problem, through this paper, the use of a deep learning model is proposed based on a customized VGG16 CNN as a way to identify the presence COVID-19 virus. The biomarkers used in this paper are X-ray and CT scan images of the lungs. At the end of the research, it can be concluded that both CT scan and X-ray images can be used to detect COVID-19 by using VGG16. However, by comparing the performance of the proposed X-ray and CT scan biomarker-based models, it can be inferred that the X-ray biomarker-based model obtained a higher accuracy score of 97% compared to the CT scan-based model with 93% accuracy. This research proved that the X-ray model got a better score and is a better alternative than CT scan, although both have potential and can be considered accurate alternatives to the PCR tests.