We developed a fully automated deep learning system to grade prostate biopsies using 5759 biopsies from 1243 patients, and showed that this system achieved pathologist-level performance.
The tf.data API of Tensorflow is a great way to build a pipeline for sending data to the GPU. In this post I give a few examples of augmentations and how to implement them using this API.
Prostate cancer is graded based on distinctive patterns in the tissue. At MIDL2018 I presented an unsupervised deep learning method, based on clustering adversarial autoencoders, to train a system to detect prostate cancer without using labeled data.
Building systems to detect tumor, in this case prostate cancer, is often hard due to a lack of data. Tumor annotations made by pathologists are often coarse due to time constraints. With this project we want to automatically refine these annotations by building a system that can automatically filter out irrelevant parts of the data.
In this post we build upon part 1 of 'Getting started with generative adversarial networks' and work with RGB data instead of monochrome. We apply a simple technique to map MNIST images to RGB.