基于深度学习的事后降噪改进了四分之一辐射剂量冠状动脉CT血管造影

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

European Journal of Radiology Pub Date : 2025-06-09 DOI:10.1016/j.ejrad.2025.112232

Tomoro Morikawa , Tatsuya Nishii , Yuki Tanabe , Kazuki Yoshida , Wataru Toshimori , Naoki Fukuyama , Hidetaka Toritani , Hiroshi Suekuni , Tetsuya Fukuda , Teruhito Kido

{"title":"基于深度学习的事后降噪改进了四分之一辐射剂量冠状动脉CT血管造影","authors":"Tomoro Morikawa , Tatsuya Nishii , Yuki Tanabe , Kazuki Yoshida , Wataru Toshimori , Naoki Fukuyama , Hidetaka Toritani , Hiroshi Suekuni , Tetsuya Fukuda , Teruhito Kido","doi":"10.1016/j.ejrad.2025.112232","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the impact of deep learning-based post-hoc noise reduction (DLNR) on image quality, coronary artery disease reporting and data system (CAD-RADS) assessment, and diagnostic performance in quarter-dose versus full-dose coronary CT angiography (CCTA) on external datasets.</div></div><div><h3>Materials and Methods</h3><div>We retrospectively reviewed 221 patients who underwent retrospective electrocardiogram-gated CCTA in 2022–2023. Using dose modulation, either mid-diastole or end-systole was scanned at full dose depending on heart rates, and the other phase at quarter dose. Only patients with motion-free coronaries in both phases were included. Images were acquired using iterative reconstruction, and a residual dense network trained on external datasets denoised the quarter-dose images. Image quality was assessed by comparing noise levels using Tukey’s test. Two radiologists independently assessed CAD-RADS, with agreement to full-dose images evaluated by Cohen’s kappa. Diagnostic performance for significant stenosis referencing full-dose images was compared between quarter-dose and denoised images by the area under the receiver operating characteristic curve (AUC) using the DeLong test.</div></div><div><h3>Results</h3><div>Among 40 cases (age, 71 ± 7 years; 24 males), DLNR reduced noise from 37 to 18 HU (P < 0.001) in quarter-dose CCTA (full-dose images: 22 HU), and improved CAD-RADS agreement from moderate (0.60 [95 % CI: 0.41–0.78]) to excellent (0.82 [95 % CI: 0.66–0.94]). Denoised images demonstrated a superior AUC (0.97 [95 % CI: 0.95–1.00]) for diagnosing significant stenosis compared with original quarter-dose images (0.93 [95 % CI: 0.89–0.98]; P = 0.032).</div></div><div><h3>Conclusion</h3><div>DLNR for quarter-dose CCTA significantly improved image quality, CAD-RADS agreement, and diagnostic performance for detecting significant stenosis referencing full-dose images.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112232"},"PeriodicalIF":3.2000,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning-based post-hoc noise reduction improves quarter-radiation-dose coronary CT angiography\",\"authors\":\"Tomoro Morikawa , Tatsuya Nishii , Yuki Tanabe , Kazuki Yoshida , Wataru Toshimori , Naoki Fukuyama , Hidetaka Toritani , Hiroshi Suekuni , Tetsuya Fukuda , Teruhito Kido\",\"doi\":\"10.1016/j.ejrad.2025.112232\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Purpose</h3><div>To evaluate the impact of deep learning-based post-hoc noise reduction (DLNR) on image quality, coronary artery disease reporting and data system (CAD-RADS) assessment, and diagnostic performance in quarter-dose versus full-dose coronary CT angiography (CCTA) on external datasets.</div></div><div><h3>Materials and Methods</h3><div>We retrospectively reviewed 221 patients who underwent retrospective electrocardiogram-gated CCTA in 2022–2023. Using dose modulation, either mid-diastole or end-systole was scanned at full dose depending on heart rates, and the other phase at quarter dose. Only patients with motion-free coronaries in both phases were included. Images were acquired using iterative reconstruction, and a residual dense network trained on external datasets denoised the quarter-dose images. Image quality was assessed by comparing noise levels using Tukey’s test. Two radiologists independently assessed CAD-RADS, with agreement to full-dose images evaluated by Cohen’s kappa. Diagnostic performance for significant stenosis referencing full-dose images was compared between quarter-dose and denoised images by the area under the receiver operating characteristic curve (AUC) using the DeLong test.</div></div><div><h3>Results</h3><div>Among 40 cases (age, 71 ± 7 years; 24 males), DLNR reduced noise from 37 to 18 HU (P < 0.001) in quarter-dose CCTA (full-dose images: 22 HU), and improved CAD-RADS agreement from moderate (0.60 [95 % CI: 0.41–0.78]) to excellent (0.82 [95 % CI: 0.66–0.94]). Denoised images demonstrated a superior AUC (0.97 [95 % CI: 0.95–1.00]) for diagnosing significant stenosis compared with original quarter-dose images (0.93 [95 % CI: 0.89–0.98]; P = 0.032).</div></div><div><h3>Conclusion</h3><div>DLNR for quarter-dose CCTA significantly improved image quality, CAD-RADS agreement, and diagnostic performance for detecting significant stenosis referencing full-dose images.</div></div>\",\"PeriodicalId\":12063,\"journal\":{\"name\":\"European Journal of Radiology\",\"volume\":\"190 \",\"pages\":\"Article 112232\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-06-09\",\"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/S0720048X25003183\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0720048X25003183","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

摘要

目的评估基于深度学习的事后降噪（DLNR）对图像质量、冠状动脉疾病报告和数据系统（CAD-RADS）评估以及四分之一剂量与全剂量冠状动脉CT血管造影（CCTA）在外部数据集上诊断性能的影响。材料和方法我们回顾性分析了221例在2022-2023年间接受回顾性心电图门控CCTA检查的患者。使用剂量调节，根据心率在全剂量下扫描舒张中期或收缩期末，在四分之一剂量下扫描另一个阶段。仅包括两个阶段的无运动冠状动脉患者。采用迭代重建方法获取图像，利用外部数据集训练的残差密集网络对四分之一剂量图像进行去噪处理。通过使用Tukey测试比较噪声水平来评估图像质量。两名放射科医生独立评估CAD-RADS，与Cohen 's kappa评估的全剂量图像一致。参考四分之一剂量和去噪图像，采用DeLong测试，通过受试者工作特征曲线（AUC）下的面积对显著狭窄的诊断性能进行比较。结果40例患者(年龄71±7岁；DLNR将噪声从37 HU降至18 HU (P <；0.001)， CAD-RADS一致性从中等（0.60 [95% CI: 0.41-0.78]）提高到优秀（0.82 [95% CI: 0.66-0.94]）。与原始四分之一剂量图像（0.93 [95% CI: 0.89-0.98]）相比，去噪图像在诊断明显狭窄方面显示出更高的AUC (0.97 [95% CI: 0.95-1.00])；p = 0.032)。结论dlnr用于四分之一剂量CCTA，可显著提高图像质量、CAD-RADS一致性，以及参考全剂量图像检测明显狭窄的诊断性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Deep learning-based post-hoc noise reduction improves quarter-radiation-dose coronary CT angiography

Purpose

To evaluate the impact of deep learning-based post-hoc noise reduction (DLNR) on image quality, coronary artery disease reporting and data system (CAD-RADS) assessment, and diagnostic performance in quarter-dose versus full-dose coronary CT angiography (CCTA) on external datasets.

Materials and Methods

We retrospectively reviewed 221 patients who underwent retrospective electrocardiogram-gated CCTA in 2022–2023. Using dose modulation, either mid-diastole or end-systole was scanned at full dose depending on heart rates, and the other phase at quarter dose. Only patients with motion-free coronaries in both phases were included. Images were acquired using iterative reconstruction, and a residual dense network trained on external datasets denoised the quarter-dose images. Image quality was assessed by comparing noise levels using Tukey’s test. Two radiologists independently assessed CAD-RADS, with agreement to full-dose images evaluated by Cohen’s kappa. Diagnostic performance for significant stenosis referencing full-dose images was compared between quarter-dose and denoised images by the area under the receiver operating characteristic curve (AUC) using the DeLong test.

Results

Among 40 cases (age, 71 ± 7 years; 24 males), DLNR reduced noise from 37 to 18 HU (P < 0.001) in quarter-dose CCTA (full-dose images: 22 HU), and improved CAD-RADS agreement from moderate (0.60 [95 % CI: 0.41–0.78]) to excellent (0.82 [95 % CI: 0.66–0.94]). Denoised images demonstrated a superior AUC (0.97 [95 % CI: 0.95–1.00]) for diagnosing significant stenosis compared with original quarter-dose images (0.93 [95 % CI: 0.89–0.98]; P = 0.032).

Conclusion

DLNR for quarter-dose CCTA significantly improved image quality, CAD-RADS agreement, and diagnostic performance for detecting significant stenosis referencing full-dose images.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

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.