Breast Cancer AI
Breast Cancer AI is an open source research project into using Artificial Intelligence (Deep Learning) to detect various forms of breast cancer by applying different methods and techniques of Artificial Intelligence.
Through the use of convolutional neural networks we can detect cancerous and non cancerous samples with fairly high accuracy. For a technical guide to the core of the project, check out the project article on Intel AI Academy Documentation: Machine Learning and Mammography
The Problem: Breast Cancer
"Breast cancer is an ongoing concern and one of the most common forms of cancer in women. In 2018 there is expected to be an estimated 266,120 new diagnoses in the United States alone."
The Solution: Artificial Intelligence
"The use of Artificial Intelligence can drastically reduce the need for medical staff to examine mammography slides manually, saving not only time, but money, and ultimately lives."
Intel AI DevJam & ICML Sweden
The IDC Classifier project was demonstrated/introduced at Intel AI DevJam & the Intel booth @ ICML (International Conference on Machine Learning) in Sweden in July 2018. Below you will find some photos from the event. You can find more info / photos and videos on the event page on the iotJumpWay social network.
Open Source Projects
Below you will find a number of open source projects using Artificial Intelligence (Computer Vision) to detect breast cancer.
The IDC Classifier is an open source computer vision program created to classify Invasive Ductal Carcinoma (IDC) positive and negative samples. The project includes a number of sub projects using different frameworks and models such as Tensorflow & Inception V3, and Caffe & CaffeNet.» View Project
The Thermography Classifier is an open source computer vision program created to classify breast cancer in thermography images. In collaboration with Gisek this project focuses on Convolutional Neural Networks trained with cancerous and non cancerous thermography images.» View Project