AUTHOR=Zhou Yuanpin , Wei Jun , Wu Dongmei , Zhang Yaqin 

TITLE=Generating Full-Field Digital Mammogram From Digitized Screen-Film Mammogram for Breast Cancer Screening With High-Resolution Generative Adversarial Network

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.868257

DOI=10.3389/fonc.2022.868257

ISSN=2234-943X

ABSTRACT=Purpose
Developing deep learning algorithms for breast cancer screening is limited due to the lack of labeled full-field digital mammograms (FFDMs). Since FFDM is a new technique that rose in recent decades and replaced digitized screen-film mammograms (DFM) as the main technique for breast cancer screening, most mammograms datasets were still stored in the form of DFM. A solution for developing deep learning algorithms based on FFDM while leveraging existing labeled DFM datasets is a generative algorithm that generates FFDM from DFM. Generating high-resolution FFDM from DFM remains a challenge due to the limitations of network capacity and lacking GPU memory.
Method
In this study, we developed a deep-learning-based generative algorithm, HRGAN, to generate synthesized FFDM (SFFDM) from DFM. Firstly, a sliding window was used to crop DFMs and FFDMs into patches. Secondly, the patches were divided into three categories by breast masks. Patches from the DFM and FFDM datasets were paired as inputs for training our model where these paired patches should be sampled from the same category of the two different image sets. U-Net liked generators and modified discriminators with two-channels output were used in our algorithm. Lastly, a study was designed to evaluate the usefulness of HRGAN. A mass segmentation task and a calcification detection task were included in the study.
Results
Two public mammography datasets, the CBIS-DDSM dataset, and the INbreast dataset were included in our experiment. The CBIS-DDSM dataset contains a total of 3568 DFMs. The INbreast dataset contains a total of 410 FFDMs. 1784 DFMs and 205 FFDM were randomly selected as Dataset A. The remaining DFMs from the CBIS-DDSM dataset were selected as Dataset B. The remaining FFDMs from the INbreast dataset were selected as Dataset C. A study with a mass segmentation task and a calcification detection task was performed to evaluate the usefulness of HRGAN. 
Conclusions
The proposed HRGAN can generate high-resolution SFFDMs from DFMs. Extensive experiments showed the SFFDMs were able to help improve the performance of deep-learning-based algorithms for breast cancer screening on DFM when the size of the training dataset is small.