Automatic COVID-19 Lung Infection Segmentation from CT Images

Automatic COVID-19 Lung Infection Segmentation from CT Images

1Nikhil Lohar

2Kedar Talegave

3Pradnya Thombare

4Sumeet Makhijani

5Prof. Manjusha F. Gaikwad

MET’s Institute of Engineering, Adgaon, Nashik-422003

Abstract - COVID-19, the disease caused by the new corona virus, can cause lung com- plications such as pneumonia and, in the most severe cases, acute respiratory distress syndrome, or ARDS. Sepsis, another possible complication of COVID-19, can also cause lasting harm to the lungs and other organs. The virus that causes COVID-19 is mainly transmitted through droplets generated when an infected person coughs, sneezes, or ex- hales. These droplets are too heavy to hang in the air, and quickly fall on floors or surfaces. As everyone is aware corona virus disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. So in order to auto- mate detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. How- ever, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. Our propose solution will analyze the CT image of lung and detect the infected part of lung along with the percentage of affected part. System will Identify the Inflection severity and will help patients to take essential measures.

Keywords: Automatic COVID-19 Lung Infection Segmentation CT Images system