Share Email Print
cover

Proceedings Paper • new

Synthesis and texture manipulation of screening mammograms using conditional generative adversarial network
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Annotated data availability has always been a major limiting f actor for the development of algorithms in the field of computer aided diagnosis. The purpose of this study is to investigate the feasibility of using a conditional generative adversarial network (GAN) to synthesize high resolution mammography images with semantic control. We feed a binary mammographic texture map to the generator to synthesize a full-field digital-mammogram (FFDM). Our results show the generator quickly learned to grow anatomical details around the edges within the texture mask. However, we found the training unstable and the quality of generated images unsatisfactory due to the inherent limitation of latent space and sample space mapping by the pix2pix framework. In order to synthesize high resolution mammography images with semantic control, we identified the critical challenge is to build the efficient mappings of binary textures with a great variety of pattern realizations with the image domain.

Paper Details

Date Published: 13 March 2019
PDF: 6 pages
Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 109502M (13 March 2019); doi: 10.1117/12.2513125
Show Author Affiliations
Dehan Kong, Duke Univ. School of Medicine (United States)
Beijing Institute of Technology (China)
Yinhao Ren, Duke Univ. School of Medicine (United States)
Duke Univ. (United States)
Rui Hou, Duke Univ. School of Medicine (United States)
Duke Univ. (United States)
Lars J. Grimm, Duke Univ. School of Medicine (United States)
Jeffrey R. Marks, Duke Univ. School of Medicine (United States)
Joseph Y. Lo, Duke Univ. School of Medicine (United States)
Duke Univ. (United States)


Published in SPIE Proceedings Vol. 10950:
Medical Imaging 2019: Computer-Aided Diagnosis
Kensaku Mori; Horst K. Hahn, Editor(s)

© SPIE. Terms of Use
Back to Top