Skip to content

Deep Learning Model with CNN to detect whether a person is having pneumonia or tuberculosis based on the chest x-ray images

Notifications You must be signed in to change notification settings

V2dha/Pneumonia-and-Tuberculosis-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pneumonia-and-Tuberculosis-Detection

Pneumonia and Tuberculosis are one of the major causes of deaths among children and the elderly. Furthermore, the fact that despite being curable with proper treatment the numbers of deaths by these diseases are high. In a country with such a large population, the smaller number of doctors is a problem due to which the diagnosis of these diseases is not that accurate and often flawed. In this project, a deep learning model to classify and detect pneumonia and tuberculosis with the help of Convolutional Neural Networks is implemented. The dataset used for Pneumonia consists of chest x-rays of 1 - 5 years of age from Guangzhou women and children’s medical center, Guangzhou, consisting of 5,863 images and for tuberculosis contains 662 chest x-rays. The model detected pneumonia with an accuracy and recall percentage of 91% while the accuracy achieved in detecting tuberculosis is 87% with a recall percentage of 88%.

Results

Classification Report

For Pneumonia

For Tuberculosis

Confusion Matrix

For Pneumonia

For Tuberculosis

ROC Curve

For Pneumonia

For Tuberculosis

About

Deep Learning Model with CNN to detect whether a person is having pneumonia or tuberculosis based on the chest x-ray images

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages