CT metal artefact reduction for hip and shoulder implants using novel algorithms and machine learning: A systematic review with pairwise and network meta-analyses

IF 2.5 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Radiography Pub Date : 2024-11-06 DOI:10.1016/j.radi.2024.10.009

K. Amadita, F. Gray, E. Gee, E. Ekpo, Y. Jimenez

{"title":"CT metal artefact reduction for hip and shoulder implants using novel algorithms and machine learning: A systematic review with pairwise and network meta-analyses","authors":"K. Amadita, F. Gray, E. Gee, E. Ekpo, Y. Jimenez","doi":"10.1016/j.radi.2024.10.009","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><div>Many tools have been developed to reduce metal artefacts in computed tomography (CT) images resulting from metallic prosthesis; however, their relative effectiveness in preserving image quality is poorly understood. This paper reviews the literature on novel metal artefact reduction (MAR) methods targeting large metal artefacts in fan-beam CT to examine their effectiveness in reducing metal artefacts and effect on image quality.</div></div><div><h3>Methods</h3><div>The PRISMA checklist was used to search for articles in five electronic databases (MEDLINE, Scopus, Web of Science, IEEE, EMBASE). Studies that assessed the effectiveness of recently developed MAR method on fan-beam CT images of hip and shoulder implants were reviewed. Study quality was assessed using the National Institute of Health (NIH) tool. Meta-analyses were conducted in R, and results that could not be meta-analysed were synthesised narratively.</div></div><div><h3>Results</h3><div>Thirty-six studies were reviewed. Of these, 20 studies proposed statistical algorithms and 16 used machine learning (ML), and there were 19 novel comparators. Network meta-analysis of 19 studies showed that Recurrent Neural Network MAR (RNN-MAR) is more effective in reducing noise (LogOR 20.7; 95 % CI 12.6–28.9) without compromising image quality (LogOR 4.4; 95 % CI -13.8-22.5). The network meta-analysis and narrative synthesis showed novel MAR methods reduce noise more effectively than baseline algorithms, with five out of 23 ML methods significantly more effective than Filtered Back Projection (FBP) (<em>p</em> < 0.05). Computation time varied, but ML methods were faster than statistical algorithms.</div></div><div><h3>Conclusion</h3><div>ML tools are more effective in reducing metal artefacts without compromising image quality and are computationally faster than statistical algorithms. Overall, novel MAR methods were also more effective in reducing noise than the baseline reconstructions.</div></div><div><h3>Implications for practice</h3><div>Implementation research is needed to establish the clinical suitability of ML MAR in practice.</div></div>","PeriodicalId":47416,"journal":{"name":"Radiography","volume":"31 1","pages":"Pages 36-52"},"PeriodicalIF":2.5000,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiography","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1078817424003079","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction

Many tools have been developed to reduce metal artefacts in computed tomography (CT) images resulting from metallic prosthesis; however, their relative effectiveness in preserving image quality is poorly understood. This paper reviews the literature on novel metal artefact reduction (MAR) methods targeting large metal artefacts in fan-beam CT to examine their effectiveness in reducing metal artefacts and effect on image quality.

Methods

The PRISMA checklist was used to search for articles in five electronic databases (MEDLINE, Scopus, Web of Science, IEEE, EMBASE). Studies that assessed the effectiveness of recently developed MAR method on fan-beam CT images of hip and shoulder implants were reviewed. Study quality was assessed using the National Institute of Health (NIH) tool. Meta-analyses were conducted in R, and results that could not be meta-analysed were synthesised narratively.

Results

Thirty-six studies were reviewed. Of these, 20 studies proposed statistical algorithms and 16 used machine learning (ML), and there were 19 novel comparators. Network meta-analysis of 19 studies showed that Recurrent Neural Network MAR (RNN-MAR) is more effective in reducing noise (LogOR 20.7; 95 % CI 12.6–28.9) without compromising image quality (LogOR 4.4; 95 % CI -13.8-22.5). The network meta-analysis and narrative synthesis showed novel MAR methods reduce noise more effectively than baseline algorithms, with five out of 23 ML methods significantly more effective than Filtered Back Projection (FBP) (p < 0.05). Computation time varied, but ML methods were faster than statistical algorithms.

Conclusion

ML tools are more effective in reducing metal artefacts without compromising image quality and are computationally faster than statistical algorithms. Overall, novel MAR methods were also more effective in reducing noise than the baseline reconstructions.

Implications for practice

Implementation research is needed to establish the clinical suitability of ML MAR in practice.

查看原文本刊更多论文

利用新型算法和机器学习减少髋关节和肩关节植入物的 CT 金属伪影：配对分析和网络荟萃分析系统综述

导言为减少金属假体造成的计算机断层扫描（CT）图像中的金属伪影，人们开发了许多工具；然而，人们对这些工具在保持图像质量方面的相对有效性知之甚少。本文回顾了针对扇形束 CT 中大金属伪影的新型金属伪影减少（MAR）方法的文献，以研究这些方法在减少金属伪影方面的有效性以及对图像质量的影响。方法使用 PRISMA 检查表在五个电子数据库（MEDLINE、Scopus、Web of Science、IEEE、EMBASE）中搜索文章。对评估最近开发的 MAR 方法在髋关节和肩关节植入物扇形束 CT 图像上的有效性的研究进行了综述。研究质量采用美国国立卫生研究院（NIH）工具进行评估。用 R 语言进行了元分析，并对无法进行元分析的结果进行了叙述性综合。其中，20 项研究提出了统计算法，16 项研究使用了机器学习 (ML)，还有 19 项新的比较对象。对 19 项研究进行的网络荟萃分析表明，递归神经网络 MAR（RNN-MAR）能更有效地降低噪声（LogOR 20.7；95 % CI 12.6-28.9），同时不影响图像质量（LogOR 4.4；95 % CI -13.8-22.5）。网络荟萃分析和叙述性综合显示，新型 MAR 方法比基线算法更有效地减少了噪声，23 种 ML 方法中有 5 种明显比过滤背投影 (FBP) 更有效（p < 0.05）。结论ML 工具能更有效地减少金属伪影，同时不影响图像质量，而且计算速度快于统计算法。总体而言，新型 MAR 方法在减少噪声方面也比基线重建更有效。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Radiography RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-

CiteScore

4.70

自引率

34.60%

发文量

169

审稿时长

63 days

期刊介绍： Radiography is an International, English language, peer-reviewed journal of diagnostic imaging and radiation therapy. Radiography is the official professional journal of the College of Radiographers and is published quarterly. Radiography aims to publish the highest quality material, both clinical and scientific, on all aspects of diagnostic imaging and radiation therapy and oncology.