Article: Deep learning techniques in CT image reconstruction and segmentation: a systematic literature review Journal: International Journal of Nanotechnology (IJNT) 2023 Vol.20 No.5/6/7/8/9/10 pp.790 - 828 Abstract: Deep learning (DL) in computed tomography (CT) is an important research area in computer vision and it provides fast advancement in the field of medical imaging. DL enables automated extraction of features and real-time estimation, whereas the traditional image reconstruction methods approximate the inverse function based on historical parameters to maintain reconstruction efficiency. The main objective of this work is to provide a brief overview of deep learning models in the field of Medical Imaging and how it works. Research papers and conference proceedings from reliable sources are collected and evaluated. Different models were examined in terms of their effectiveness in solving domain-specific issues. This systematic literature review (SLR) study based on the last five-year data with the help of digital libraries (IEEE, ACM, Springer, Wiley, ScienceDirect) found the research articles. We provide a systematic mapping report using selected research articles based on the inclusion-exclusion technique. We describe some research questions that include deep learning methods, framework, parameters, etc. The research work has been evaluated using quantitative reports, charts, and methodology. We also highlight the challenges of DL in the medical imaging domain, particularly in the application of reconstruction and segmentation, and potential future development in the area. Inderscience Publishers - linking academia, business and industry through research

Title: Deep learning techniques in CT image reconstruction and segmentation: a systematic literature review

Authors: Manju Devi; Sukhdip Singh; Shailendra Tiwari

Addresses: Deenbandhu ChhotuRam University of Science and Technology, Haryana, Murthal, 131039, India ' Deenbandhu ChhotuRam University of Science and Technology, Haryana, Murthal, 131039, India ' Thapar Institute of Engineering and Technology (TIET), Punjab, Patiala, 147004, India

Abstract: Deep learning (DL) in computed tomography (CT) is an important research area in computer vision and it provides fast advancement in the field of medical imaging. DL enables automated extraction of features and real-time estimation, whereas the traditional image reconstruction methods approximate the inverse function based on historical parameters to maintain reconstruction efficiency. The main objective of this work is to provide a brief overview of deep learning models in the field of Medical Imaging and how it works. Research papers and conference proceedings from reliable sources are collected and evaluated. Different models were examined in terms of their effectiveness in solving domain-specific issues. This systematic literature review (SLR) study based on the last five-year data with the help of digital libraries (IEEE, ACM, Springer, Wiley, ScienceDirect) found the research articles. We provide a systematic mapping report using selected research articles based on the inclusion-exclusion technique. We describe some research questions that include deep learning methods, framework, parameters, etc. The research work has been evaluated using quantitative reports, charts, and methodology. We also highlight the challenges of DL in the medical imaging domain, particularly in the application of reconstruction and segmentation, and potential future development in the area.

Keywords: medical imaging; image reconstruction; image segmentation; deep learning.

DOI: 10.1504/IJNT.2023.134033

International Journal of Nanotechnology, 2023 Vol.20 No.5/6/7/8/9/10, pp.790 - 828

Received: 13 Oct 2021
Accepted: 07 Mar 2022
Published online: 10 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Deep learning techniques in CT image reconstruction and segmentation: a systematic literature review

Keep up-to-date