We are using the ChestXray14 raw chest x-ray dataset at NIH Clinical Center. The code is inspired by the cat vs. dog image classificaton at Machine Learning Crash Course by Google Developers.

Tested in Ubuntu 18.04.1 and MacOS:

1. Download image data from ChestXray14 source and decompress.
2. Download and install Anaconda.
3. Start Anaconda Navigator.
4. Create TensorFlow environment (Tab "Environments").
5. Select TensorFlow environment and install: keras, tensorflow, matplotlib, nomkl, h5py, pillow and keras-metrics (pip install keras-metrics).
6. Install Jupyter Notebook (Tab "Home").

1. Activate TF environment (Tab "Environments").
2. Launch Jupyter Notebook (Tab "Home").
3. Open "CNN.ipynb"-file inside the Jupyter Notebook and run all cells starting at the top.

1. Create Deep CNN (more layers).
2. Add different Dropout layers.
3. Less image-downscaling (variable: target_size).
4. Create Transfer learning CNN from InceptionV3 by cutting at 'mixed7' or last convolution layer (VGG, AlexNet, ResNet, DenseNet).
5. Use data augmentation to balance underrepresented classes.
6. Play with train/validation split.
7. Consideration of unbalanced dataset (class_weight='balanced')