Overview / Usage

Melanoma skin cancer is a fatal disease that kills thousands of people all over the world. It is mainly prevalent in the USA. Melanoma skin cancer is curable if it is detected in the early stages. This project would leverage deep learning techniques for early stage detection of cancerous tissues.

Methodology / Approach

The dataset used for the project is a set of images from the International Skin Imaging Collaboration: Mellanoma Project ISIC https://isic-archive.com. There were two categories of skin lesions: benign and malign.

Deep learning techniques, namely Convolutional neural networks were used to classify the images and provide confidence scores.
The model was trained on Intel Devcloud.

Technologies Used

Tensorflow, Keras, Intel Devcloud