Generative Machine Learning for Synthetic Histopathology Slides
Anonymising medical data for use in machine learning is important to preserve patient privacy and, in many circumstances, is a requirement before data can be made available. One approach to anonymising image data is to train a generative model to produce data that is statistically similar to the input data and use the synthetic data in place of the real. In this work, we present a study of the effects of such a process on an exemplar downstream task, histology image classification.
Keywords
computer vision, generative models, pathology, Health Informatics
Staff
David Morrison, [David Harris-Birtill]{dcchb}