Inspiration
On reading the news that CoronaVirus is spreading in fraction of second in China. Most shocking was it takes nearly to 2 days to identify whether the patient is COVID positive or not. Then after some advancements also, it is taking some hours to test. So, I thought there should be the minimum time to test this virus so that actions can be taken as soon as possible. A person who gets tested positive for the disease can taken an immediate initiative to self-quarantine them, avoid the infection spreading to other people.
What it does
This study of research expected to set up an early screening model to detect Novel Coronavirus (2019 – nCov) pneumonia, with aspiratory CT scan utilizing Digital Image Processing procedures. The signs of registered tomography (CT) imaging of 2019 – nCov had their own attributes, which are not the same as different sorts of viral pneumonia. Accordingly, clinical specialists require another early analytic criteria for this new kind of pneumonia at the earliest opportunity. The applicant contamination locales were handled under Digital Image Processing systems: image pre-processing, image enhancement and image segmentation of a 3-dimensional pneumonic CT image set capturing. These isolated images were then sorted into 2019 – nCov, using marker-based watershed segmentation method.
How I built it
It consist of simple steps. Just by uploading a JPG/PNG image format of Lung CT Scan and click Submit on Process! the result obtained is whether the patient have tested positive or negative for COVID-19 along with the prediction area associated with it.
Challenges I ran into
The main challenge was to build an accurate model with the scarcity of data sets. Databases and resources of CT scan samples of COVID-19 patient are not available.
Accomplishments that I'm proud of
The main accomplishments which I am proud of is that the proposed system would useful to detecting COVID-19 infected scans, which can be further improved upon by proper and accurate segmentation of training datasets.
What I learned
Learned the usage of technology to tackle critical global problems which can help save lives. The only thing the researcher need of the motivation of building the concept.
What's next for Detection of Novel Coronavirus using image segmentation
Further enhancement of this system is on accuracy. By proper tunning of the performance of this methodology, can be used to predict COVID-19 Positive cases where the govt and the people can be benefited from this.
Log in or sign up for Devpost to join the conversation.