The use of deep learning towards dose optimization in low-dose computed tomography: A scoping review

E Immonen,J Wong,M Nieminen,L Kekkonen,S Roine,S Törnroos,L Lanca,F Guan,E Metsälä

doi:10.1016/j.radi.2021.07.010

Abstract

IntroductionLow-dose computed tomography tends to produce lower image quality than normal dose computed tomography (CT) although it can help to reduce radiation hazards of CT scanning. Research has shown that Artificial Intelligence (AI) technologies, especially deep learning can help enhance the image quality of low-dose CT by denoising images. This scoping review aims to create an overview on how AI technologies, especially deep learning, can be used in dose optimisation for low-dose CT. MethodsLiterature searches of ProQuest, PubMed, Cinahl, ScienceDirect, EbscoHost Ebook Collection and Ovid were carried out to find research articles published between the years 2015 and 2020. In addition, manual search was conducted in SweMed+, SwePub, NORA, Taylor & Francis Online and Medic. ResultsFollowing a systematic search process, the review comprised of 16 articles. Articles were organised according to the effects of the deep learning networks, e.g. image noise reduction, image restoration. Deep learning can be used in multiple ways to facilitate dose optimisation in low-dose CT. Most articles discuss image noise reduction in low-dose CT. ConclusionDeep learning can be used in the optimisation of patients’ radiation dose. Nevertheless, the image quality is normally lower in low-dose CT (LDCT) than in regular-dose CT scans because of smaller radiation doses. With the help of deep learning, the image quality can be improved to equate the regular-dose computed tomography image quality. Implications to practiceLower dose may decrease patients’ radiation risk but may affect the image quality of CT scans. Artificial intelligence technologies can be used to improve image quality in low-dose CT scans. Radiologists and radiographers should have proper education and knowledge about the techniques used.

Highlights

Low-dose computed tomography tends to produce lower image quality than normal dose computed tomography (CT) it can help to reduce radiation hazards of CT scanning
This scoping review aims to provide an overview on how Artificial Intelligence (AI) technologies, especially deep learning, can be used in dose optimisation in low-dose CT
The researchers found that a number of research studies had been developed and published on how AI technologies can help with dose optimisation in low-dose CT in different ways, including reducing noises in low-dose CT images, restoring low-dose images as normal-dose images by recovering structures and preserving details

Summary

Introduction

Computed tomography (CT) has a critical role in medical imaging clinical practice. CT can produce two- or three-dimensional images of patients.[1]. It is important to note that all AI-based techniques should be tested in an ethical way and from the ethical point of view This scoping review aims to provide an overview on how AI technologies, especially deep learning, can be used in dose optimisation in low-dose CT. Categorising and analysing the results The articles were organised according to the effects of the deep learning networks, e.g. image noise reduction and image restoration. They were tabulated according to subcategories as follows: authors’ names and the year of publication, the type of the network, the dataset used and the human anatomical part where the test imaging was performed. Short summaries of each article were drafted to facilitate the comparison of their results

Methods

Conflict of interest statement

Limitations