Breast Cancer Detection Using Computer Vision & IoT
- 0 Collaborators
Detecting Invasive Ductal Carcinoma (IDC) in unlabelled histology images using Intel AI DevCloud, UP Squared & Intel Movidius. ...learn more
Project status: Under Development
Internet of Things, Artificial Intelligence
Intel Technologies
AI DevCloud / Xeon,
Movidius NCS
Overview / Usage
Invasive Ductal Carcinoma is one of the most common forms of breast cancer. The cancer starts in the milk duct of the breast and “invades” the surrounding tissue. This form of cancer makes up around 80% of all breast cancer diagnosis, with more than 180,000 women a year in the United States alone being diagnosed with IDC according to the American Cancer Society.
Invasive Ductal Carcinoma (IDC) Classification Using Computer Vision & IoT combines Computer Vision and the Internet of Things to provide researchers, doctors and students with a way to train a neural network with labelled breast cancer histology images to detect Invasive Ductal Carcinoma (IDC) in unseen/unlabelled images.
Methodology / Approach
The project uses the power of the Intel® Movidius and uses a custom trained Inception V3 model to carry out image classification, both locally and via a server / client. IoT communication is powered by the IoT JumpWay and publishes the results after processing local images or images sent through the API.
DISCLAIMER
This is a project I created as an extension to one of my facial recognition projects, I advise that this is to be used by developers interested in learning about the use cases of computer vision, medical researchers and students, or professionals in the medical industry to evaluate if it may help them and to expand upon. This is not meant to be an alternative for use instead of seeking professional help. I am a developer not a doctor or expert on cancer.
For full tutorial and code please visit the Github linked below.
Technologies Used
To create the IDC classifier, I use the Intel AI DevCloud to train the neural network, an Intel Movidius for carrying out inference on the edge, and Intel UP2 to serve the trained model making it accessible via an API, and an IoT connected alarm system built using a Raspberry Pi that will demonstrate the potential of using the Internet of Things via the IoT JumpWay combined with AI to create intelligent, automated medical systems.