Building a Simple Multilayer Convolutional Network to Detect Cancer in MIAS Mammograms

Previously, we modified the MNIST For ML Beginners Tutorial to process Mini-MIAS imagery [http://jacob.vi/modifying-tensorflows-mnist-for-beginners-tutorial-to-search-for-cancer-in-mammograms/] . The results of this were not great. Let's try this again but with a simple Multilayer Convolutional Network (CNN) in TensorFlow [https://www.tensorflow.org/versions/r0.11/tutorials/mnist/pros/…

Deep Learning Algorithm Diagnoses Skin Cancer As Well As Seasoned Dermatologists

Stanford in the news today with another deep-learning breakthrough in cancer diagnostics: Deep learning algorithm diagnoses skin cancer as well as seasoned dermatologists [http://news.stanford.edu/2017/01/25/artificial-intelligence-used-identify-skin-cancer/] First, the impressive results: > The final product, the subject of a paper in the Jan. 25 issue of…

Publicly Available Mammography Datasets

In order to build a machine learning model to help us with mammography-based diagnosis[1] we will need data to train our models. Thankfully, there are a number of data sets publicly available. University of South Florida Digital Database for Screening Mammography [http://marathon.csee.usf.edu/Mammography/Database.html]…

Is Machine Learning Just Another Fad?

According to Mattermark, No. AI Is The New New Thing (And It's Taking Over) [https://mattermark.com/ai-new-new-thing-taking/] This editorial presents an interesting look at the ecosystem of machine learning startups, across all industries. Some choice quotes: > 2013’s Big Data is 2016’s Machine Learning (ML)…

Machine Learning in Cancer Care

Machine Learning (ML) is a technique to train computers to identify patterns instead of explicitly telling them what those patterns are. If you want to teach a machine-learning system to recognize a cat, you don't tell it to look for whiskers, ears, fur, and eyes. Instead, you show…