In this liveProject, you’ll build a VGG16 deep learning model from scratch to analyze medical imagery. A VGG16 is a deep convolutional network model which has shown to achieve high accuracy in image based pattern recognition tasks. You’ll then train your model on X-ray and CT datasets, and plot validation loss, and accuracies vs. epochs. You’ll build an important familiarity with the functional blocks of a DL model, how data must be formatted, and which layers to use to solve your problems.
This liveProject is for intermediate Python programmers. To begin this liveProject, you will need to be familiar with:
- Intermediate Python 3.x and Jupyter notebooks
- Basics of Keras and OpenCV
Basics of deep learning and image classification
you will learn
In this liveProject, you’ll gain familiarity with medical image datasets and build deep neural networks to analyze them.
- Building a VGG16 deep learning architecture with basic functional components in Keras
- Using custom image data generators in Keras
- DICOM data format for training and test images
- Deploying VGG16 model for training on DICOM images
- Training VGG16 model on two different types of medical image datasets (X-ray, CT)
- Tuning VGG16 model hyperparameters to improve performance