Literature DB >> 35399301

SR-CycleGAN: super-resolution of clinical CT to micro-CT level with multi-modality super-resolution loss.

Tong Zheng1, Hirohisa Oda1, Yuichiro Hayashi1, Takayasu Moriya1, Shota Nakamura2, Masaki Mori3, Hirotsugu Takabatake4, Hiroshi Natori5, Masahiro Oda1,6, Kensaku Mori1,7,8.   

Abstract

Purpose: We propose a super-resolution (SR) method, named SR-CycleGAN, for SR of clinical computed tomography (CT) images to the micro-focus x-ray CT CT ( μ CT ) level. Due to the resolution limitations of clinical CT (about 500 × 500 × 500    μ m 3 / voxel ), it is challenging to obtain enough pathological information. On the other hand, μ CT scanning allows the imaging of lung specimens with significantly higher resolution (about 50 × 50 × 50    μ m 3 / voxel or higher), which allows us to obtain and analyze detailed anatomical information. As a way to obtain detailed information such as cancer invasion and bronchioles from preoperative clinical CT images of lung cancer patients, the SR of clinical CT images to the μ CT level is desired. Approach: Typical SR methods require aligned pairs of low-resolution (LR) and high-resolution images for training, but it is infeasible to obtain precisely aligned paired clinical CT and μ CT images. To solve this problem, we propose an unpaired SR approach that can perform SR on clinical CT to the μ CT level. We modify a conventional image-to-image translation network named CycleGAN to an inter-modality translation network named SR-CycleGAN. The modifications consist of three parts: (1) an innovative loss function named multi-modality super-resolution loss, (2) optimized SR network structures for enlarging the input LR image to 2 k -times by width and height to obtain the SR output, and (3) sub-pixel shuffling layers for reducing computing time.
Results: Experimental results demonstrated that our method successfully performed SR of lung clinical CT images. SSIM and PSNR scores of our method were 0.54 and 17.71, higher than the conventional CycleGAN's scores of 0.05 and 13.64, respectively. Conclusions: The proposed SR-CycleGAN is usable for the SR of a lung clinical CT into μ CT scale, while conventional CycleGAN output images with low qualitative and quantitative values. More lung micro-anatomy information could be observed to aid diagnosis, such as the shape of bronchioles walls.
© 2022 The Authors.

Entities:  

Keywords:  detailed anatomical information; inter-modality translation; lung micro-anatomy; unpaired super-resolution

Year:  2022        PMID: 35399301      PMCID: PMC8983071          DOI: 10.1117/1.JMI.9.2.024003

Source DB:  PubMed          Journal:  J Med Imaging (Bellingham)        ISSN: 2329-4302


  23 in total

Review 1.  Screening for lung cancer.

Authors:  E F Patz; P C Goodman; G Bepler
Journal:  N Engl J Med       Date:  2000-11-30       Impact factor: 91.245

2.  Image quality assessment: from error visibility to structural similarity.

Authors:  Zhou Wang; Alan Conrad Bovik; Hamid Rahim Sheikh; Eero P Simoncelli
Journal:  IEEE Trans Image Process       Date:  2004-04       Impact factor: 10.856

3.  CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE).

Authors:  Chenyu You; Wenxiang Cong; Michael W Vannier; Punam K Saha; Eric A Hoffman; Ge Wang; Guang Li; Yi Zhang; Xiaoliu Zhang; Hongming Shan; Mengzhou Li; Shenghong Ju; Zhen Zhao; Zhuiyang Zhang
Journal:  IEEE Trans Med Imaging       Date:  2019-06-14       Impact factor: 10.048

4.  Fully Convolutional Networks for Semantic Segmentation.

Authors:  Evan Shelhamer; Jonathan Long; Trevor Darrell
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2016-05-24       Impact factor: 6.226

5.  Image Super-Resolution Using Deep Convolutional Networks.

Authors:  Chao Dong; Chen Change Loy; Kaiming He; Xiaoou Tang
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2016-02       Impact factor: 6.226

6.  Deep Learning for Image Super-resolution: A Survey.

Authors:  Zhihao Wang; Jian Chen; Steven C H Hoi
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2020-03-23       Impact factor: 6.226

7.  Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising.

Authors:  Chenyu You; Qingsong Yang; Hongming Shan; Lars Gjesteby; Guang Li; Shenghong Ju; Zhuiyang Zhang; Zhen Zhao; Yi Zhang; Cong Wenxiang; Ge Wang
Journal:  IEEE Access       Date:  2018-07-20       Impact factor: 3.367

8.  Deep Learning Based High-Resolution Reconstruction of Trabecular Bone Microstructures from Low-Resolution CT Scans using GAN-CIRCLE.

Authors:  Indranil Guha; Syed Ahmed Nadeem; Chenyu You; Xiaoliu Zhang; Steven M Levy; Ge Wang; James C Torner; Punam K Saha
Journal:  Proc SPIE Int Soc Opt Eng       Date:  2020-02-28

9.  Potential and limitations of X-Ray micro-computed tomography in arthropod neuroanatomy: a methodological and comparative survey.

Authors:  Andy Sombke; Elisabeth Lipke; Peter Michalik; Gabriele Uhl; Steffen Harzsch
Journal:  J Comp Neurol       Date:  2015-03-02       Impact factor: 3.215

10.  A step towards valid detection and quantification of lung cancer volume in experimental mice with contrast agent-based X-ray microtomography.

Authors:  Pidassa Bidola; Juliana Martins de Souza E Silva; Klaus Achterhold; Enkhtsetseg Munkhbaatar; Philipp J Jost; Anna-Lena Meinhardt; Kirsten Taphorn; Marie-Christine Zdora; Franz Pfeiffer; Julia Herzen
Journal:  Sci Rep       Date:  2019-02-04       Impact factor: 4.379

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.