Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
2
2021-180 Smart Assistant to ease the process of COVID-19 and Pneumonia disease detection
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
2021-180
2021-180 Smart Assistant to ease the process of COVID-19 and Pneumonia disease detection
Commits
fc249bb1
Commit
fc249bb1
authored
Apr 17, 2021
by
Akalanka B. A. IT18114836
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Update README.md
parent
13b49c41
Pipeline
#2405
canceled with stages
Changes
1
Pipelines
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
43 additions
and
0 deletions
+43
-0
README.md
README.md
+43
-0
No files found.
README.md
View file @
fc249bb1
...
...
@@ -89,3 +89,46 @@ The aim of this objective is to develop the mobile application. The mobile
application is used for taking photos of a chest CT scan and upload it to the
cloud-based AI model for analyzing.
**IT18115130 Senevirathne K.D.A**
Image diagnosis is a vital problem in medicine. Now a day’s ongoing pandemic of
Covid-19 has become the major infectious diseases among all other diseases.
As we all know, Covid-19 is a fast-spreading viral disease. Researchers found
that patients with Covid-19 have proved that they are mostly affected by lung
diseases. Covid-19 is diagnosed using RT-PCR Testing, CT Scans and Chest X-Ray
(CXR) images. But the problem is RT-PCR test takes at least more than 12 hours
to get a result. Covid-19 patients should be identified and tracked as soon as
possible, and it requires specific material equipment. In developing countries,
there is a lack of resources to do these tests. Even though methods that can
generate faster results exist, these methods are too expensive for third-world
countries like Sri Lanka.
Most people like to get their reports in minimum time. In this kind of a
situation patients must wait for a long time, and it is stressful. If there is
a proper and speed method that gives the result in very accurate way that will
be helpful.
Chest X-ray images become the less cost and time-effective tool for take the
decisions. Compared to other Chest X-ray methods, it is a lower-cost process,
and anyone can easily access this method. In this global pandemic, frequent
patients will need to be assessed in short periods by a few clinicians and very
few resources.
Not only Covid-19 but also Pneumonia is an infectious disease that needs to be
diagnosed at an early stage. With the introduction of imaging, the diagnosis of
diseases using X-ray images of the chest has been accelerated. But it also
requires a specialist and a qualified radiologist to read the chest X-ray image
correctly. To this purpose, we are suggesting a joined method using image
processing and Convolution Neural Network for automated detection of covid-19
and pneumonia by using chest X-ray images.
**Objectives**
*
Understanding correct objects and automatically process the data of that specific object and ready for the disease identification process.
*
Segment the captured chest x-ray image to identify the image.
*
Adding color filtering algorithm to the captured image
*
Organize processed Data for disease identification algorithms.
*
Developing an algorithm to analyze a sample of captured chest x-ray images to predict the disease.
*
Developing a method for classifying lung diseases
.
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment