Ultralow dose coronary calcium scoring CT at reduced tube voltage and current by using deep learning image reconstruction

IF 3.2 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Pub Date : 2024-09-19 DOI:10.1016/j.ejrad.2024.111742

Liyong Zhuo , Shijie Xu , Guozhi Zhang , Lihong Xing , Yu Zhang , Zepeng Ma , Jianing Wang , Xiaoping Yin

{"title":"Ultralow dose coronary calcium scoring CT at reduced tube voltage and current by using deep learning image reconstruction","authors":"Liyong Zhuo , Shijie Xu , Guozhi Zhang , Lihong Xing , Yu Zhang , Zepeng Ma , Jianing Wang , Xiaoping Yin","doi":"10.1016/j.ejrad.2024.111742","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>To explore the potential of the deep learning reconstruction (DLR) for ultralow dose calcium scoring CT (CSCT) with simultaneously reduced tube voltage and current.</div></div><div><h3>Methods</h3><div>In this prospective study, seventy-five patients (group A) undergoing routine dose CSCT (120kVp/30mAs) were followed by a low dose (120kVp/20mAs) scan and another 81 (group B) were followed by an ultralow dose (80kVp/20mAs) scan. The hybrid iterative reconstruction was used for the routine dose data while the DLR for data of reduced dose. The calcium score and risk categorization were compared, where the correlation was evaluated using the intraclass correlation coefficient (ICC). The noise suppression performance of DLR was characterized by the contrast-to-noise ratio (CNR) between coronary arteries and pericoronary fat.</div></div><div><h3>Results</h3><div>The effective dose was 0.32 ± 0.03 vs. 0.48 ± 0.05 mSv for the two scans in group A and 0.09 ± 0.01 vs. 0.49 ± 0.05 mSv in group B. No significant difference was found on CACSs within either group (A: <em>p</em> = 0.10, ICC=0.99; B: <em>p</em> = 0.14, ICC=0.99), nor was it different on risk categorization (A: <em>p</em> = 0.32, ICC=0.99; B: <em>p</em> = 0.16, ICC=0.99). The DLR images exhibited higher CNR in both groups (A: <em>p</em> < 0.001; B: <em>p</em> = 0.001).</div></div><div><h3>Conclusions</h3><div>The DLR allowed reliable calcium scoring in not only low dose CSCT with reduced tube current but ultralow dose CSCT with simultaneously reduced tube voltage and current, showing feasibility to be adopted in routine applications.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"181 ","pages":"Article 111742"},"PeriodicalIF":3.2000,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0720048X24004583","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

To explore the potential of the deep learning reconstruction (DLR) for ultralow dose calcium scoring CT (CSCT) with simultaneously reduced tube voltage and current.

Methods

In this prospective study, seventy-five patients (group A) undergoing routine dose CSCT (120kVp/30mAs) were followed by a low dose (120kVp/20mAs) scan and another 81 (group B) were followed by an ultralow dose (80kVp/20mAs) scan. The hybrid iterative reconstruction was used for the routine dose data while the DLR for data of reduced dose. The calcium score and risk categorization were compared, where the correlation was evaluated using the intraclass correlation coefficient (ICC). The noise suppression performance of DLR was characterized by the contrast-to-noise ratio (CNR) between coronary arteries and pericoronary fat.

Results

The effective dose was 0.32 ± 0.03 vs. 0.48 ± 0.05 mSv for the two scans in group A and 0.09 ± 0.01 vs. 0.49 ± 0.05 mSv in group B. No significant difference was found on CACSs within either group (A: p = 0.10, ICC=0.99; B: p = 0.14, ICC=0.99), nor was it different on risk categorization (A: p = 0.32, ICC=0.99; B: p = 0.16, ICC=0.99). The DLR images exhibited higher CNR in both groups (A: p < 0.001; B: p = 0.001).

Conclusions

The DLR allowed reliable calcium scoring in not only low dose CSCT with reduced tube current but ultralow dose CSCT with simultaneously reduced tube voltage and current, showing feasibility to be adopted in routine applications.

查看原文本刊更多论文

利用深度学习图像重建技术，在降低管电压和电流的情况下实现超低剂量冠状动脉钙成像 CT

方法在这项前瞻性研究中，75 名接受常规剂量 CSCT（120kVp/30mAs）扫描的患者（A 组）接受了低剂量（120kVp/20mAs）扫描，另有 81 名患者（B 组）接受了超低剂量（80kVp/20mAs）扫描。混合迭代重建用于常规剂量数据，而 DLR 用于降低剂量数据。比较了钙化评分和风险分类，并使用类内相关系数（ICC）评估了相关性。DLR 的噪声抑制性能通过冠状动脉和冠状动脉周围脂肪之间的对比噪声比 (CNR) 来表征。结果 A 组两次扫描的有效剂量分别为 0.32 ± 0.03 对 0.48 ± 0.05 mSv，0.32 ± 0.03 对 0.48 ± 0.05 mSv，0.32 ± 0.03 对 0.48 ± 0.05 mSv。两组的 CACS 均无显著差异（A 组：p = 0.10，ICC=0.99；B 组：p = 0.14，ICC=0.99），风险分类也无差异（A 组：p = 0.32，ICC=0.99；B 组：p = 0.16，ICC=0.99）。结论DLR不仅能在管电流降低的低剂量CSCT中进行可靠的钙化评分，还能在同时降低管电压和电流的超低剂量CSCT中进行可靠的钙化评分，显示了在常规应用中采用DLR的可行性。

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

European Journal of Radiology 医学-核医学

CiteScore

6.70

自引率

3.00%

发文量

398

审稿时长

42 days

期刊介绍： European Journal of Radiology is an international journal which aims to communicate to its readers, state-of-the-art information on imaging developments in the form of high quality original research articles and timely reviews on current developments in the field. Its audience includes clinicians at all levels of training including radiology trainees, newly qualified imaging specialists and the experienced radiologist. Its aim is to inform efficient, appropriate and evidence-based imaging practice to the benefit of patients worldwide.