/COVID-19-analysis-through-Chest-X-rays

I have built a Deep learning-based framework using CNN and transfer learning algorithms like DenseNet and MobileNet from Tensorflow library

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

COVID-19-analysis-through-Chest-X-rays

Dataset from here: https://www.kaggle.com/praveengovi/coronahack-chest-xraydataset

CoronaHack -Chest X-Ray-Dataset

Classify the X Ray image which is having Corona

Context

Corona - COVID19 virus affects the respiratory system of healthy individual & Chest X -Ray is one of the important imaging methods to identify the corona virus.

With the Chest X - Ray dataset, Develop a Machine Learning Model to classify the X Rays of Healthy vs Pneumonia (Corona) affected patients & this model powers the AI application to test the Corona Virus in Faster Phase.

Content

Collection Chest X Ray of Healthy vs Pneumonia (Corona) affected patients infected patients along with few other categories such as SARS (Severe Acute Respiratory Syndrome ) ,Streptococcus & ARDS (Acute Respiratory Distress Syndrome)

Images name and labels are available in ChestXrayCorona_Metadata.csv

  1. COVID 19 - https://en.wikipedia.org/wiki/Coronavirus_disease_2019
  2. ARDS - https://en.wikipedia.org/wiki/Acute_respiratory_distress_syndrome
  3. Streptococcus - https://en.wikipedia.org/wiki/Streptococcus
  4. SARS - https://en.wikipedia.org/wiki/Severe_acute_respiratory_syndrome

Acknowledgements

I would like to thank to below team from Joseph Paul Cohen. Postdoctoral Fellow, Mila, University of Montreal for the dataset below for corona dataset & 80% dataset collected from different sources.

Original Source :- https://github.com/ieee8023/covid-chestxray-dataset

Inspiration

Automated methods to detect and classify human diseases from medical images.Novel Machine Learning Algorithms and neural networks helps to reduce the Corona Virus detection time and aids the doctor to drive the consultation in better way

Libraries Used here

  1. Tensorflow and Keras
  2. Matplotlib
  3. Pandas
  4. Numpy
  5. PIL
  6. Scikit-Learn

Models Used

  1. Simple Convolutional Neural Networks
  2. DenseNet121
  3. MobileNet_V2

Do visit my implementation for more understanding :)

Hope You Like this work!!