Improving lesion detection in mammograms by leveraging a Cycle-GAN-based lesion remover

Author:

Lee Juhun,Nishikawa Robert M.

Abstract

Abstract Background The wide heterogeneity in the appearance of breast lesions and normal breast structures can confuse computerized detection algorithms. Our purpose was therefore to develop a Lesion Highlighter (LH) that can improve the performance of computer-aided detection algorithms for detecting breast cancer on screening mammograms. Methods We hypothesized that a Cycle-GAN based Lesion Remover (LR) could act as an LH, which can improve the performance of lesion detection algorithms. We used 10,310 screening mammograms from 4,832 women that included 4,942 recalled lesions (BI-RADS 0) and 5,368 normal results (BI-RADS 1). We divided the dataset into Train:Validate:Test folds with the ratios of 0.64:0.16:0.2. We segmented image patches (400 × 400 pixels) from either lesions marked by MQSA radiologists or normal tissue in mammograms. We trained a Cycle-GAN to develop two GANs, where each GAN transferred the style of one image to another. We refer to the GAN transferring the style of a lesion to normal breast tissue as the LR. We then highlighted the lesion by color-fusing the mammogram after applying the LR to its original. Using ResNet18, DenseNet201, EfficientNetV2, and Vision Transformer as backbone architectures, we trained three deep networks for each architecture, one trained on lesion highlighted mammograms (Highlighted), another trained on the original mammograms (Baseline), and Highlighted and Baseline combined (Combined). We conducted ROC analysis for the three versions of each deep network on the test set. Results The Combined version of all networks achieved AUCs ranging from 0.963 to 0.974 for identifying the image with a recalled lesion from a normal breast tissue image, which was statistically improved (p-value < 0.001) over their Baseline versions with AUCs that ranged from 0.914 to 0.967. Conclusions Our results showed that a Cycle-GAN based LR is effective for enhancing lesion conspicuity and this can improve the performance of a detection algorithm.

Funder

National Institutes of Health

Publisher

Springer Science and Business Media LLC

Reference26 articles.

1. Zhu JY, Park T, Isola P, Efros AA. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. In: 2017 IEEE international conference on computer vision (ICCV), 2017.

2. Isola P, Zhu J, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). 2017. p. 5967–76.

3. Karacan L, Akata Z, Erdem A, Erdem E. Learning to generate images of outdoor scenes from attributes and semantic layouts [Internet]. arXiv; 2016 [cited 2022 Jun 27]. http://arxiv.org/abs/1612.00215

4. Sangkloy P, Lu J, Fang C, Yu F, Hays J. Scribbler: Controlling deep image synthesis with sketch and color [Internet]. arXiv; 2016 [cited 2022 Jun 27]. http://arxiv.org/abs/1612.00835

5. Smith L, Dhawan N, Zhang M, Abbeel P, Levine S. AVID: learning multi-stage tasks via pixel-level translation of human videos [Internet]. arXiv; 2020 [cited 2022 Jun 27]. http://arxiv.org/abs/1912.04443

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. 3D Knee Structure Reconstruction from 2D X-rays Based on Generative Deep Learning Models;2024 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC);2024-07-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3