Literature DB >> 31582263

Super-resolution reconstruction of knee magnetic resonance imaging based on deep learning.

Defu Qiu1, Shengxiang Zhang2, Ying Liu3, Jianqing Zhu4, Lixin Zheng5.   

Abstract

BACKGROUND AND
OBJECTIVE: With the rapid development of medical imaging and intelligent diagnosis, artificial intelligence methods have become a research hotspot of radiography processing technology in recent years. The low definition of knee magnetic resonance image texture seriously affects the diagnosis of knee osteoarthritis. This paper presents a super-resolution reconstruction method to address this problem.
METHODS: In this paper, we propose an efficient medical image super-resolution (EMISR) method, in which we mainly adopted three hidden layers of super-resolution convolution neural network (SRCNN) and a sub-pixel convolution layer of efficient sub-pixel convolution neural network (ESPCN). The addition of the efficient sub-pixel convolutional layer in the hidden layer and the small network replacement consisting of concatenated convolutions to address low-resolution images but not high-resolution images are important. The EMISR method also uses cascaded small convolution kernels to improve reconstruction speed and deepen the convolution neural network to improve reconstruction quality.
RESULTS: The proposed method is tested in the public dataset IDI, and the reconstruction quality of the algorithm is higher than that of the sparse coding-based network (SCN) method, the SRCNN method, and the ESPCN method (+ 2.306 dB, + 2.540 dB, + 1.089 dB improved); moreover, the reconstruction speed is faster than its counterparts (+ 4.272 s, + 1.967 s, and + 0.073 s improved).
CONCLUSION: The experimental results show that our EMISR framework has improved performance and greatly reduces the number of parameters and training time. Furthermore, the reconstructed image presents more details, and the edges are more complete. Therefore, the EMISR technique provides a more powerful medical analysis in knee osteoarthritis examinations.
Copyright © 2019 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Convolutional neural network; Deep learning; Low-resolution image; Medical imaging; Super resolution

Mesh:

Year:  2019        PMID: 31582263     DOI: 10.1016/j.cmpb.2019.105059

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  6 in total

1.  Mechanical Analysis of Posterior Pedicle Screw System Placement and Internal Fixation in the Treatment of Lumbar Fractures.

Authors:  Shengkai Mu; Jingxu Wang; Shuyi Gong
Journal:  Comput Math Methods Med       Date:  2022-04-11       Impact factor: 2.809

2.  Unsupervised super-resolution reconstruction of hyperspectral histology images for whole-slide imaging.

Authors:  Ling Ma; Armand Rathgeb; Hasan Mubarak; Minh Tran; Baowei Fei
Journal:  J Biomed Opt       Date:  2022-05       Impact factor: 3.758

Review 3.  Light on osteoarthritic joint: from bench to bed.

Authors:  Yingying Zhou; Junguo Ni; Chunyi Wen; Puxiang Lai
Journal:  Theranostics       Date:  2022-01-01       Impact factor: 11.600

4.  Autoencoder-Inspired Convolutional Network-Based Super-Resolution Method in MRI.

Authors:  Seonyeong Park; H Michael Gach; Siyong Kim; Suk Jin Lee; Yuichi Motai
Journal:  IEEE J Transl Eng Health Med       Date:  2021-04-28

5.  Rapid whole-heart CMR with single volume super-resolution.

Authors:  Jennifer A Steeden; Michael Quail; Alexander Gotschy; Kristian H Mortensen; Andreas Hauptmann; Simon Arridge; Rodney Jones; Vivek Muthurangu
Journal:  J Cardiovasc Magn Reson       Date:  2020-08-03       Impact factor: 5.364

6.  Do Radiographic Assessments of Periodontal Bone Loss Improve with Deep Learning Methods for Enhanced Image Resolution?

Authors:  Maira Moran; Marcelo Faria; Gilson Giraldi; Luciana Bastos; Aura Conci
Journal:  Sensors (Basel)       Date:  2021-03-12       Impact factor: 3.576

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.