Self-supervised Learning for CT Image Denoising and Reconstruction: a Review

Overview

Journal Biomed Eng Lett

Specialty Biomedical Engineering

Date 2024 Oct 28

PMID 39465103

Authors

Kihwan Choi

Affiliations

Soon will be listed here.

Abstract

This article reviews the self-supervised learning methods for CT image denoising and reconstruction. Currently, deep learning has become a dominant tool in medical imaging as well as computer vision. In particular, self-supervised learning approaches have attracted great attention as a technique for learning CT images without clean/noisy references. After briefly reviewing the fundamentals of CT image denoising and reconstruction, we examine the progress of deep learning in CT image denoising and reconstruction. Finally, we focus on the theoretical and methodological evolution of self-supervised learning for image denoising and reconstruction.

References

Ren S, He K, Girshick R, Sun J . Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2016; 39(6):1137-1149. DOI: 10.1109/TPAMI.2016.2577031. View

Sidky E, Pan X . Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization. Phys Med Biol. 2008; 53(17):4777-807. PMC: 2630711. DOI: 10.1088/0031-9155/53/17/021. View

Li H, Yang X, Yang S, Wang D, Jeon G . Transformer With Double Enhancement for Low-Dose CT Denoising. IEEE J Biomed Health Inform. 2022; 27(10):4660-4671. DOI: 10.1109/JBHI.2022.3216887. View

Bai T, Wang B, Nguyen D, Jiang S . Probabilistic self-learning framework for low-dose CT denoising. Med Phys. 2021; 48(5):2258-2270. DOI: 10.1002/mp.14796. View

Ramani S, Fessler J . A splitting-based iterative algorithm for accelerated statistical X-ray CT reconstruction. IEEE Trans Med Imaging. 2011; 31(3):677-88. PMC: 3298196. DOI: 10.1109/TMI.2011.2175233. View

Niu C, Li M, Fan F, Wu W, Guo X, Lyu Q . Noise Suppression With Similarity-Based Self-Supervised Deep Learning. IEEE Trans Med Imaging. 2023; 42(6):1590-1602. PMC: 10288330. DOI: 10.1109/TMI.2022.3231428. View

Garayoa J, Castro P . A study on image quality provided by a kilovoltage cone-beam computed tomography. J Appl Clin Med Phys. 2013; 14(1):3888. PMC: 5714052. DOI: 10.1120/jacmp.v14i1.3888. View

Choi K . A Comparative Study between Image- and Projection-Domain Self-Supervised Learning for Ultra Low-Dose CBCT. Annu Int Conf IEEE Eng Med Biol Soc. 2022; 2022:2076-2079. DOI: 10.1109/EMBC48229.2022.9871947. View

Wolterink J, Leiner T, Viergever M, Isgum I . Generative Adversarial Networks for Noise Reduction in Low-Dose CT. IEEE Trans Med Imaging. 2017; 36(12):2536-2545. DOI: 10.1109/TMI.2017.2708987. View

10.

Ritschl L, Bergner F, Fleischmann C, Kachelriess M . Improved total variation-based CT image reconstruction applied to clinical data. Phys Med Biol. 2011; 56(6):1545-61. DOI: 10.1088/0031-9155/56/6/003. View

11.

Zhu L, Han Y, Xi X, Fu H, Tan S, Liu M . STEDNet: Swin transformer-based encoder-decoder network for noise reduction in low-dose CT. Med Phys. 2023; 50(7):4443-4458. DOI: 10.1002/mp.16249. View

12.

Shen C, Nguyen D, Zhou Z, Jiang S, Dong B, Jia X . An introduction to deep learning in medical physics: advantages, potential, and challenges. Phys Med Biol. 2020; 65(5):05TR01. PMC: 7101509. DOI: 10.1088/1361-6560/ab6f51. View

13.

You C, Yang Q, Shan H, Gjesteby L, Li G, Ju S . Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising. IEEE Access. 2019; 6:41839-41855. PMC: 6426337. DOI: 10.1109/ACCESS.2018.2858196. View

14.

Chun I, Huang Z, Lim H, Fessler J . Momentum-Net: Fast and Convergent Iterative Neural Network for Inverse Problems. IEEE Trans Pattern Anal Mach Intell. 2020; 45(4):4915-4931. PMC: 8011286. DOI: 10.1109/TPAMI.2020.3012955. View

15.

Yuan N, Zhou J, Qi J . Half2Half: deep neural network based CT image denoising without independent reference data. Phys Med Biol. 2020; 65(21):215020. DOI: 10.1088/1361-6560/aba939. View

16.

Chen Y, Pock T . Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration. IEEE Trans Pattern Anal Mach Intell. 2016; 39(6):1256-1272. DOI: 10.1109/TPAMI.2016.2596743. View

17.

Bai M, Liu B, Mu H, Liu X, Jiang Y . The comparison of radiation dose between C-arm flat-detector CT (DynaCT) and multi-slice CT (MSCT): a phantom study. Eur J Radiol. 2011; 81(11):3577-80. DOI: 10.1016/j.ejrad.2011.09.006. View

18.

Choi K . Self-supervised Projection Denoising for Low-Dose Cone-Beam CT. Annu Int Conf IEEE Eng Med Biol Soc. 2021; 2021:3459-3462. DOI: 10.1109/EMBC46164.2021.9629859. View

19.

Yang Q, Yan P, Zhang Y, Yu H, Shi Y, Mou X . Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE Trans Med Imaging. 2018; 37(6):1348-1357. PMC: 6021013. DOI: 10.1109/TMI.2018.2827462. View

20.

Chen H, Zhang Y, Chen Y, Zhang J, Zhang W, Sun H . LEARN: Learned Experts' Assessment-Based Reconstruction Network for Sparse-Data CT. IEEE Trans Med Imaging. 2018; 37(6):1333-1347. PMC: 6019143. DOI: 10.1109/TMI.2018.2805692. View