Literature DB >> 35284282

Low-dose computed tomography image reconstruction via a multistage convolutional neural network with autoencoder perceptual loss network.

Qing Li1, Saize Li1, Runrui Li1, Wei Wu2, Yunyun Dong1, Juanjuan Zhao1, Yan Qiang1, Rukhma Aftab1.   

Abstract

Background: Computed tomography (CT) is widely used in medical diagnoses due to its ability to non-invasively detect the internal structures of the human body. However, CT scans with normal radiation doses can cause irreversible damage to patients. The radiation exposure is reduced with low-dose CT (LDCT), although considerable speckle noise and streak artifacts in CT images and even structural deformation may result, significantly undermining its diagnostic capability.
Methods: This paper proposes a multistage network framework which gradually divides the entire process into 2-staged sub-networks to complete the task of image reconstruction. Specifically, a dilated residual convolutional neural network (DRCNN) was used to denoise the LDCT image. Then, the learned context information was combined with the channel attention subnet, which retains local information, to preserve the structural details and features of the image and textural information. To obtain recognizable characteristic details, we introduced a novel self-calibration module (SCM) between the 2 stages to reweight the local features, which realizes the complementation of information at different stages while refining feature information. In addition, we also designed an autoencoder neural network, using a self-supervised learning scheme to train a perceptual loss neural network specifically for CT images.
Results: We evaluated the diagnostic quality of the results and performed ablation experiments on the loss function and network structure modules to verify each module's effectiveness in the network. Our proposed network architecture obtained high peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual information fidelity (VIF) values in terms of quantitative evaluation. In the analysis of qualitative results, our network structure maintained a better balance between eliminating image noise and preserving image details. Experimental results showed that our proposed network structure obtained better metrics and visual evaluation. Conclusions: This study proposed a new LDCT image reconstruction method by combining autoencoder perceptual loss networks with multistage convolutional neural networks (MSCNN). Experimental results showed that the newly proposed method has performance than other methods. 2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Low-dose CT (LDCT); autoencoder; multistage convolutional neural network (MSCNN); self-calibrated

Year:  2022        PMID: 35284282      PMCID: PMC8899925          DOI: 10.21037/qims-21-465

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  28 in total

1.  Low-dose CT statistical iterative reconstruction via modified MRF regularization.

Authors:  Hong Shangguan; Quan Zhang; Yi Liu; Xueying Cui; Yunjiao Bai; Zhiguo Gui
Journal:  Comput Methods Programs Biomed       Date:  2015-10-23       Impact factor: 5.428

2.  Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography.

Authors:  Jing Wang; Tianfang Li; Hongbing Lu; Zhengrong Liang
Journal:  IEEE Trans Med Imaging       Date:  2006-10       Impact factor: 10.048

3.  Low-dose CT via convolutional neural network.

Authors:  Hu Chen; Yi Zhang; Weihua Zhang; Peixi Liao; Ke Li; Jiliu Zhou; Ge Wang
Journal:  Biomed Opt Express       Date:  2017-01-09       Impact factor: 3.732

4.  Learned Primal-Dual Reconstruction.

Authors:  Jonas Adler; Ozan Oktem
Journal:  IEEE Trans Med Imaging       Date:  2018-06       Impact factor: 10.048

5.  Ray contribution masks for structure adaptive sinogram filtering.

Authors:  Michael Balda; Joachim Hornegger; Bjoern Heismann
Journal:  IEEE Trans Med Imaging       Date:  2012-02-10       Impact factor: 10.048

6.  Methods for clinical evaluation of noise reduction techniques in abdominopelvic CT.

Authors:  Eric C Ehman; Lifeng Yu; Armando Manduca; Amy K Hara; Maria M Shiung; Dayna Jondal; David S Lake; Robert G Paden; Daniel J Blezek; Michael R Bruesewitz; Cynthia H McCollough; David M Hough; Joel G Fletcher
Journal:  Radiographics       Date:  2014 Jul-Aug       Impact factor: 5.333

7.  Accurate and Fast Image Denoising via Attention Guided Scaling.

Authors:  Yulun Zhang; Kunpeng Li; Kai Li; Gan Sun; Yu Kong; Yun Fu
Journal:  IEEE Trans Image Process       Date:  2021-07-12       Impact factor: 10.856

8.  Denoised and texture enhanced MVCT to improve soft tissue conspicuity.

Authors:  Ke Sheng; Shuiping Gou; Jiaolong Wu; Sharon X Qi
Journal:  Med Phys       Date:  2014-10       Impact factor: 4.071

9.  A review on Deep Learning approaches for low-dose Computed Tomography restoration.

Authors:  K A Saneera Hemantha Kulathilake; Nor Aniza Abdullah; Aznul Qalid Md Sabri; Khin Wee Lai
Journal:  Complex Intell Systems       Date:  2021-05-30
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.