An Application of Generative Adversarial Networks for Super Resolution Medical Imaging
作者： Rewa Sood , Binit Topiwala , Karthik Choutagunta , Rohit Sood , Mirabela Rusu
关键词:
摘要: Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires the patient to remain still for long periods of time, which causes discomfort and increases probability motion induced image artifacts. A possible solution is acquire low resolution (LR) process them with Super Generative Adversarial Network (SRGAN) create an HR version. LR a lower scan time than acquiring images, allows higher comfort scanner throughput. This work applies SRGAN MR prostate improve in-plane by factors 4 8. The term 'super resolution' in context this paper defines post processing enhancement medical as opposed 'high native acquired during acquisition phase. We also compare three other models: SRCNN, SRResNet, Sparse Representation. While results do not have best Peak Signal Noise Ratio (PSNR) or Structural Similarity (SSIM) metrics, they are visually most similar original portrayed Mean Opinion Score (MOS) results.
arxiv.org
harvard.edu
arxiv-vanity.com参考文章(13)
Nong Sang, Fan Ma, Shuhang Gu, Fast image super resolution via local regression international conference on pattern recognition. pp. 3128- 3131 ,(2012)
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification international conference on computer vision. pp. 1026- 1034 ,(2015) , 10.1109/ICCV.2015.123
Roman Zeyde, Michael Elad, Matan Protter, On Single Image Scale-Up Using Sparse-Representations Curves and Surfaces. pp. 711- 730 ,(2012) , 10.1007/978-3-642-27413-8_47
Samuel Schulter, Christian Leistner, Horst Bischof, Fast and accurate image upscaling with super-resolution forests computer vision and pattern recognition. pp. 3791- 3799 ,(2015) , 10.1109/CVPR.2015.7299003
Xiaolin Wu, Weisheng Dong, Guangming Shi, Lei Zhang, Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization IEEE Transactions on Image Processing. ,vol. 20, pp. 1838- 1857 ,(2011) , 10.1109/TIP.2011.2108306
Hong Chang, Dit-Yan Yeung, Yimin Xiong, Super-resolution through neighbor embedding computer vision and pattern recognition. ,vol. 1, pp. 275- 282 ,(2004) , 10.1109/CVPR.2004.1315043
Jianchao Yang, John Wright, Thomas S Huang, Yi Ma, Image Super-Resolution Via Sparse Representation IEEE Transactions on Image Processing. ,vol. 19, pp. 2861- 2873 ,(2010) , 10.1109/TIP.2010.2050625
Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error visibility to structural similarity IEEE Transactions on Image Processing. ,vol. 13, pp. 600- 612 ,(2004) , 10.1109/TIP.2003.819861
Radu Timofte, Vincent De, Luc Van Gool, Anchored Neighborhood Regression for Fast Example-Based Super-Resolution international conference on computer vision. pp. 1920- 1927 ,(2013) , 10.1109/ICCV.2013.241
Justin Johnson, Alexandre Alahi, Li Fei-Fei, Perceptual Losses for Real-Time Style Transfer and Super-Resolution Computer Vision – ECCV 2016. pp. 694- 711 ,(2016) , 10.1007/978-3-319-46475-6_43