Pneumonia Detection
A computer-aided diagnosis system for automatic pneumonia detection using chest X-ray images has been developed in this project. Deep transfer learning has been employed to handle the scarcity of available data. With 90% precision, the model is trained in such a way that it detects pneumonia with the help of chest X-ray images wherein, the dataset used is this from Kaggle. Hence, to address this problem and aid the detection of this severe disease, our team has created a pneumonia detection model using deep learning (CNN)
- Image data gen basically used for rescaling, sizing, turning into images fit for neural networks.
- The model has used VGG19 which is an object-recognition model that supports up to 19 layers of cnn for image classification.
- Then we used Residual Network (ResNet) which is a Convolutional Neural Network (CNN) architecture that overcame the “vanishing gradient” problem, It has predefined weights which helps us in image classification
- Resnet is the best model over this dataset with proper hypertuning of parameters
- Speech API is used for voice-over output.
- PyQt file is imported for graphic widgets and interface to connect our backend model
● Early detection of pneumonia disease can increase
the survival rate of lung patients.
● Chest X-ray (CXR) images are the primarily means
of detecting and diagnosing pneumonia.
● Detecting pneumonia from CXR images by a trained
radiologist is a challenging task.
● Pneumonia has caused significant deaths worldwide.
● It is a challenging task to detect many lung diseases
such as like atelectasis, cardiomegaly, lung cancer,
etc., often due to limited professional radiologists in
hospital settings.
● With this model, we can track pneumonia in its’ initial
stages and may lead to an increase in the survival rate
of lung patients.
- Dhruv Bajaj (RA1911032010054)
- Shubham Patil (RA1911032010045)
- Harshal Gupta (RA1911032010035)