Siddharth Gupta, A. Panwar, Akanksha Kapruwan, Nisha Chaube, Manav Chauhan
{"title":"Real Time Analysis of Diabetic Retinopathy Lesions by Employing Deep Learning and Machine Learning Algorithms using Color Fundus Data","authors":"Siddharth Gupta, A. Panwar, Akanksha Kapruwan, Nisha Chaube, Manav Chauhan","doi":"10.1109/ICITIIT54346.2022.9744228","DOIUrl":null,"url":null,"abstract":"Diabetes is a rapidly spreading illness that has devastating consequences on human organs such as kidney, lungs, heart, eyes, etc. Diabetic Retinopathy (DR) is a condition caused by abiding diabetes that damages small vessels carrying blood and tissues in the eyes. The condition is characterized by the creation of inflated formations in the retinal region known as Micro-aneurysms, which if ignored can result in irreversible damage to the eye's blood vessels, eventually leading to blindness. In the early stages of the disease, such clinical manifestations do not appear. As a result, regular and timely checkups are foremost important. However, manual identification of diabetic retinopathy is time intensive and prone to human mistake. In the stated research, the color fundus dataset scans after processing are passed to multiple Deep Learning (DL) models employed to learn characteristics. These models trained on millions of different images from thousands of classes. Finally, several machine learning classifiers were used to classify lesions using the collected characteristics. The extracted result shows very eye catching performance. This enables experts to create architecture that fully address the problem of classifying unidentified scans into the right class or category.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICITIIT54346.2022.9744228","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
Diabetes is a rapidly spreading illness that has devastating consequences on human organs such as kidney, lungs, heart, eyes, etc. Diabetic Retinopathy (DR) is a condition caused by abiding diabetes that damages small vessels carrying blood and tissues in the eyes. The condition is characterized by the creation of inflated formations in the retinal region known as Micro-aneurysms, which if ignored can result in irreversible damage to the eye's blood vessels, eventually leading to blindness. In the early stages of the disease, such clinical manifestations do not appear. As a result, regular and timely checkups are foremost important. However, manual identification of diabetic retinopathy is time intensive and prone to human mistake. In the stated research, the color fundus dataset scans after processing are passed to multiple Deep Learning (DL) models employed to learn characteristics. These models trained on millions of different images from thousands of classes. Finally, several machine learning classifiers were used to classify lesions using the collected characteristics. The extracted result shows very eye catching performance. This enables experts to create architecture that fully address the problem of classifying unidentified scans into the right class or category.