Code Lab 1: Skin Cancer MNIST

These are the materials for the first code lab in Curae.ai's Deep Learning in Healthcare Workshop.

In this lab, we will get comfortable with our environments and explore a basic computer vision model on a simplified medical dataset: HAM10000.

Specifically, we will walk through how to launch these code labs on your platform of choice. Then we will learn how to load data, create a convolutional neural network model, and train our model using Tensorflow's Eager Execution API in anticipation of Tensorflow 2.0's default settings.

References

Dataset

1. Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: “Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)”, 2018; https://arxiv.org/abs/1902.03368
2. Tschandl, P., Rosendahl, C. & Kittler, H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 doi:10.1038/sdata.2018.161 (2018).