https://github.com/Ankuraxz/Covid-Doctor
In the current scenario, there is a widespread of coronavirus in the entire world, but there are limited supplies and services for the patients. But there are a large number of people who want to take Covid test to assure that they are safe, so they went to hospitals and an unnecessary crowd gathers there, which has a high chance of spreading coronavirus. So, to stop this, Team Neurons has developed a contactless Covid 19 Detection Webapp Covid Doctor, which predicts the vital information of humans using a simple camera and a browser. So, people can take the self-assessment test and can run the health test to ensure that they are safe and won’t go to the hospital, which has a high chance of catching the virus.
In these difficult times, everybody has to be cautious for which they need to have a self-assessment tool which they can use for scanning themselves anytime.
With the help of this feature we can get immediate result of our X-Ray instead of going to the hospital and waiting for the outcome, which can lead to the spread of the deadly virus. So, using Deep Learning technology we have built a X-ray Classifier which classifies whether the patient is COVID Positive or Negative. This is will save time and stops from spreading of virus.
COVID-19 (coronavirus disease 2019) is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), previously known as the 2019 novel coronavirus (2019-nCoV), a strain of coronavirus. The first cases were seen in Wuhan, China, in late December 2019 before spreading globally. The current outbreak was officially recognized as a pandemic by the World Health Organization (WHO) on 11 March 2020.Definitive diagnosis of COVID-19 requires a positive RT-PCR test. Current best practice advises that CT chest is not used to diagnose COVID-19, but maybe helpful in assessing for complications. The non-specific imaging findings are most commonly of atypical or organizing pneumonia, often with a bilateral, peripheral, and basal predominant distribution. No effective treatment or vaccine exists currently.
-Open Source Data available on Kaggle and Github (Compiled by organisation like IEEE) has bee used -Data augmentation like Zoom, Rescale, Brightness, Sharpness, ZCA whitening, Shift and Rotation, Dynamic Focus(img- blur_filter(img)) etc were experimented with -CNN model was used to achieve an accuracy >98%
Link for Dataset: https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge https://github.com/ieee8023/covid-chestxray-dataset X-Ray and chest CT maybe helpful in assessing for complications, and hence can be used for initial test