https://github.com/akshaysharma096/classify-human-diseases-using-deeplearning
Automated methods to detect and classify human diseases from medical images, using Deep Neural Networks
https://github.com/akshaysharma096/classify-human-diseases-using-deeplearning
convolutional-neural-networks data-science deep-learning keras keras-neural-networks machine-learning python3
Last synced: 10 months ago
JSON representation
Automated methods to detect and classify human diseases from medical images, using Deep Neural Networks
- Host: GitHub
- URL: https://github.com/akshaysharma096/classify-human-diseases-using-deeplearning
- Owner: akshaysharma096
- License: mit
- Created: 2018-06-17T17:03:43.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-06-18T23:06:21.000Z (about 8 years ago)
- Last Synced: 2025-06-25T08:08:45.918Z (about 1 year ago)
- Topics: convolutional-neural-networks, data-science, deep-learning, keras, keras-neural-networks, machine-learning, python3
- Language: HTML
- Homepage:
- Size: 373 KB
- Stars: 10
- Watchers: 3
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Classify-human-diseases-using-DeepLearning
## Automated methods to detect and classify human diseases from medical images, using Deep Neural Networks
### What is this project for? ###
The project is about diagnosing Pneumonia from X-ray images of lungs of a person using self laid convolutional neural network. The images were of size greater than 1000 pixels per dimension and the total dataset.
- The dataset contained 5000+ X-ray images, labelled as showing symptoms of Pnuemonia or not.
- The work includes
- Pre-processing of data.
- Laying down a Deep Convolutional Neural Network architecture from scratch.
- The model showed a recall of 95% and a precision of 80%.
- In context of the problem statement, recall of the model plays a more crucial role for the successfull classifcation of images.
- The final model architecture, loss functions and regularization steps have been chosen after continous hyper parameter searches.
### Insipiration
Automated methods to detect and classify human diseases from medical images.
### Reading
- [Batch Normalization](https://arxiv.org/abs/1502.03167)
- [Xavier Initialization](http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf)
- [Dropout Regularization](https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf)
- [Effective Backprop](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf)
- [How Does Batch Normalization Help Optimization?
(No, It Is Not About Internal Covariate Shift)](https://arxiv.org/pdf/1805.11604.pdf)