High-Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network

被引:10
作者
Sun, Kun [2 ,3 ,4 ]
Qu, Liangqiong [3 ,4 ]
Lian, Chunfeng [3 ,4 ]
Pan, Yongsheng [3 ,4 ]
Hu, Dan [3 ,4 ]
Xia, Bingqing [5 ]
Li, Xinyue [6 ]
Chai, Weimin [2 ]
Yan, Fuhua [2 ]
Shen, Dinggang [1 ,7 ]
机构
[1] Shanghai United Imaging Intelligence Co Ltd, Dept Res & Dev, Shanghai, Peoples R China
[2] Shanghai Jiao Tong Univ, Sch Med, Ruijin Hosp, Dept Radiol, Shanghai 200025, Peoples R China
[3] Univ N Carolina, Dept Radiol, Chapel Hill, NC 27515 USA
[4] Univ N Carolina, BRIC, Chapel Hill, NC 27515 USA
[5] Shanghai Jiao Tong Univ, Sch Med, Dept Radiol, Int Peace Matern & Child Hlth Hosp, Shanghai, Peoples R China
[6] Shanghai Jiao Tong Univ, Sch Med, Ruijin Hosp, Dept Radiol,Luwan Branch, Shanghai, Peoples R China
[7] Korea Univ, Dept Brain & Cognit Engn, Seoul 02841, South Korea
基金
中国国家自然科学基金;
关键词
MRI; breast; generative adversarial network; CNN;
D O I
10.1002/jmri.27256
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Background A generative adversarial network could be used for high-resolution (HR) medical image synthesis with reduced scan time. Purpose To evaluate the potential of using a deep convolutional generative adversarial network (DCGAN) for generating HRpre and HRpost images based on their corresponding low-resolution (LR) images (LRpre and LRpost). Study Type This was a retrospective analysis of a prospectively acquired cohort. Population In all, 224 subjects were randomly divided into 200 training subjects and an independent 24 subjects testing set. Field Strength/Sequence Dynamic contrast-enhanced (DCE) MRI with a 1.5T scanner. Assessment Three breast radiologists independently ranked the image datasets, using the DCE images as the ground truth, and reviewed the image quality of both the original LR images and the generated HR images. The BI-RADS category and conspicuity of lesions were also ranked. The inter/intracorrelation coefficients (ICCs) of mean image quality scores, lesion conspicuity scores, and Breast Imaging Reporting and Data System (BI-RADS) categories were calculated between the three readers. Statistical Test Wilcoxon signed-rank tests evaluated differences among the multireader ranking scores. Results The mean overall image quality scores of the generated HRpre and HRpost were significantly higher than those of the original LRpre and LRpost (4.77 +/- 0.41 vs. 3.27 +/- 0.43 and 4.72 +/- 0.44 vs. 3.23 +/- 0.43, P < 0.0001, respectively, in the multireader study). The mean lesion conspicuity scores of the generated HRpre and HRpost were significantly higher than those of the original LRpre and LRpost (4.18 +/- 0.70 vs. 3.49 +/- 0.58 and 4.35 +/- 0.59 vs. 3.48 +/- 0.61, P < 0.001, respectively, in the multireader study). The ICCs of the image quality scores, lesion conspicuity scores, and BI-RADS categories had good agreements among the three readers (all ICCs >0.75). Data Conclusion DCGAN was capable of generating HR of the breast from fast pre- and postcontrast LR and achieved superior quantitative and qualitative performance in a multireader study. Level of Evidence 3 Technical Efficacy Stage 2 J. MAGN. RESON. IMAGING 2020;52:1852-1858.
引用
收藏
页码:1852 / 1858
页数:7
相关论文
共 40 条
[1]   Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms [J].
Akselrod-Ballin, Ayelet ;
Chorev, Michal ;
Shoshan, Yoel ;
Spiro, Adam ;
Hazan, Alon ;
Melamed, Roie ;
Barkan, Ella ;
Herzel, Esma ;
Naor, Shaked ;
Karavani, Ehud ;
Koren, Gideon ;
Goldscbmidt, Yaara ;
Shalev, Varda ;
Rosen-Zvi, Michal ;
Guindy, Michal .
RADIOLOGY, 2019, 292 (02) :331-342
[2]   Brain tumor detection using statistical and machine learning method [J].
Amin, Javaria ;
Sharif, Muhammad ;
Raza, Mudassar ;
Saba, Tanzila ;
Anjum, Muhammad Almas .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2019, 177 :69-79
[3]  
[Anonymous], 2017, IEEE I CONF COMP VIS, DOI DOI 10.1109/ICCV.2017.244
[4]  
Arjovsky M., 2017, ARXIV170107875
[5]   Women's experiences and preferences regarding breast imaging after completing breast cancer treatment [J].
Brandzel, Susan ;
Rosenberg, Dori E. ;
Johnson, Dianne ;
Bush, Mary ;
Kerlikowske, Karla ;
Onega, Tracy ;
Henderson, Louise ;
Nekhlyudov, Larissa ;
DeMartini, Wendy ;
Wernli, Karen J. .
PATIENT PREFERENCE AND ADHERENCE, 2017, 11 :199-204
[6]   Super-resolution musculoskeletal MRI using deep learning [J].
Chaudhari, Akshay S. ;
Fang, Zhongnan ;
Kogan, Feliks ;
Wood, Jeff ;
Stevens, Kathryn J. ;
Gibbons, Eric K. ;
Lee, Jin Hyung ;
Gold, Garry E. ;
Hargreaves, Brian A. .
MAGNETIC RESONANCE IN MEDICINE, 2018, 80 (05) :2139-2154
[7]   Model-Based Convolutional De-Aliasing Network Learning for Parallel MR Imaging [J].
Chen, Yanxia ;
Xiao, Taohui ;
Li, Cheng ;
Liu, Qiegen ;
Wang, Shanshan .
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT III, 2019, 11766 :30-38
[8]   Efficient and Accurate MRI Super-Resolution Using a Generative Adversarial Network and 3D Multi-level Densely Connected Network [J].
Chen, Yuhua ;
Shi, Feng ;
Christodoulou, Anthony G. ;
Xie, Yibin ;
Zhou, Zhengwei ;
Li, Debiao .
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT I, 2018, 11070 :91-99
[9]  
Chuquicusma MJM, 2018, I S BIOMED IMAGING, P240, DOI 10.1109/ISBI.2018.8363564
[10]   Abbreviated MRI Protocols in Breast Cancer Diagnostics [J].
Deike-Hofmann, Katerina ;
Koenig, Franziska ;
Paech, Daniel ;
Dreher, Constantin ;
Delorme, Stefan ;
Schlemmer, Heinz-Peter ;
Bickelhaupt, Sebastian .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2019, 49 (03) :647-658