MammoGAN: High-Resolution Synthesis of Realistic Mammograms

Conference Proceedings: International Conference on Medical Imaging with Deep Learning (MIDL) 2019

Publishing Date: 17th April 2019

Video: Watch this video for more information from Kheiron Medical Technologies

Pre-print here: 9th July 2018

Abstract

We explore whether recent advances in generative adversarial networks (GANs) enable synthesis of realistic medical images that are hard to distinguish from real ones, even by domain experts. High-quality synthetic images can be useful for data augmentation, domain transfer, and out-of-distribution detection. However, generating realistic images is challenging, particularly for Full Field Digital Mammograms (FFDM), due to the high resolution, textural heterogeneity, fine structural details and specific tissue properties. We employ progressive GANs to synthesize mammograms at a resolution of 1280×1024 pixels, the highest reported so far. In order to assess the perceptual realism, we designed a user study where experts are asked to distinguish real and generated images with exciting results.

Latest articles

PR

11th May 2022

Kheiron Forms US Breast Medical Advisory Board; Appoints Three Leaders With Deep Track Record Advocating For Women’s Health

Dr. Wendy DeMartini, Dr. Elizabeth Morris, and Dr. Amy Patel are trailblazers at the forefront of introducing innovative breast imaging technologies into clinical practice (London ...

Read more
Latest articles

PR

4th May 2022

InHealth signs up to AI Award with Kheiron

InHealth, who provide services for North and East Devon NHS Breast Screening, has entered into the research agreement to work with Kheiron Medical Technologies as part of the AI in...

Read more
Latest articles

PR

9th March 2022

Kheiron included in Fast Company’s Most Innovative Companies 2022 list

This AI cancer diagnostics company joins the ranks of Canva, Microsoft, SpaceX, and other winning companies that are changing lives for the better (London –  March 9, 20...

Read more
Latest articles

PR

30th November 2021

Dr Ben Glocker Joins Kheiron

As Head of Machine Learning Research, Glocker will help make sure that Kheiron’s algorithms generalize and can help patients, regardless of their ethnic background or where they ...

Read more
Latest articles

PR

29th November 2021

Kheiron Introduces RSViP to U.S.

AI-Enabled Scheduling Tool That Focuses Attention on Women Who Need Breast Screening the Most Nov. 29, 2021 – As many as 3.9 million women in the U.S. missed their routine ma...

Read more
Latest articles

PR

29th November 2021

Stanford University Partners with Kheiron

Collaboration leverages Stanford’s clinical expertise and Kheiron’s machine learning capabilities to assist radiologists in more effectively staging and monitoring treatment re...

Read more
Latest articles

PR

29th November 2021

Kheiron Introduces Mia IQ to U.S.

Award-Winning AI Solutions Developer Launches Image Quality Assurance Tool to Support Radiographers and Radiologists in Breast Screening Process Nov. 29, 2021 – To aid breast...

Read more
Latest articles

PR

27th October 2021

Royal Free London NHS Foundation Trust signs up to AI Award with Kheiron

“The study will provide evidence to help assess whether the use of AI in this instance could be a viable option,” said Dr William Teh, clinical lead with Royal Free London NHS ...

Read more
Latest articles

PR

27th October 2021

Kheiron, Gateshead Health Foundation NHS Trust Enter Research Agreement

Partnership marks significant step in the journey to build evidence base to demonstrate effectiveness and safety of AI in NHS breast cancer screening LONDON, 26 October 2021–&nbs...

Read more
1 2 3 7