文献检索文档翻译深度研究
Suppr Zotero 插件Zotero 插件
邀请有礼套餐&价格历史记录

新学期，新优惠

限时优惠:9月1日-9月22日

30天高级会员仅需29元

1天体验卡首发特惠仅需5.99元

了解详情
不再提醒
插件&应用
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
高级版
套餐订阅购买积分包
AI 工具
文献检索文档翻译深度研究
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2025

基于深度学习的心脏 CT 重建与迭代和滤波反投影重建相比，可产生明显的放射组学特征。

Deep learning-based reconstruction on cardiac CT yields distinct radiomic features compared to iterative and filtered back projection reconstructions.

机构信息

Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea.

Department of Biostatistics and Computing, Yonsei University Graduate School, Seoul, Korea.

出版信息

Sci Rep. 2022 Sep 7;12(1):15171. doi: 10.1038/s41598-022-19546-1.

DOI:10.1038/s41598-022-19546-1
PMID:36071138
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9452656/
Abstract

We aimed to determine the effects of deep learning-based reconstruction (DLR) on radiomic features obtained from cardiac computed tomography (CT) by comparing with iterative reconstruction (IR), and filtered back projection (FBP). A total of 284 consecutive patients with 285 cardiac CT scans that were reconstructed with DLR, IR, and FBP, were retrospectively enrolled. Radiomic features were extracted from the left ventricular (LV) myocardium, and from the periprosthetic mass if patients had cardiac valve replacement. Radiomic features of LV myocardium from each reconstruction were compared using a fitting linear mixed model. Radiomics models were developed to diagnose periprosthetic abnormality, and the performance was evaluated using the area under the receiver characteristics curve (AUC). Most radiomic features of LV myocardium (73 of 88) were significantly different in pairwise comparisons between all three reconstruction methods (P < 0.05). The radiomics model on IR exhibited the best diagnostic performance (AUC 0.948, 95% CI 0.880-1), relative to DLR (AUC 0.873, 95% CI 0.735-1) and FBP (AUC 0.875, 95% CI 0.731-1), but these differences did not reach significance (P > 0.05). In conclusion, applying DLR to cardiac CT scans yields radiomic features distinct from those obtained with IR and FBP, implying that feature robustness is not guaranteed when applying DLR.

摘要

我们旨在通过比较深度学习重建（DLR）与迭代重建（IR）和滤波反投影（FBP），确定基于深度学习的重建（DLR）对心脏 CT 获得的放射组学特征的影响。共回顾性纳入 284 例连续 285 例心脏 CT 扫描患者，这些患者分别采用 DLR、IR 和 FBP 重建。从左心室（LV）心肌和心脏瓣膜置换术患者的假体周围肿块中提取放射组学特征。使用拟合线性混合模型比较每种重建的 LV 心肌的放射组学特征。开发了用于诊断假体周围异常的放射组学模型，并使用接收特征曲线下面积（AUC）评估性能。三种重建方法之间的两两比较，LV 心肌的大多数放射组学特征（88 个中的 73 个）均有显著差异（P < 0.05）。IR 上的放射组学模型表现出最佳的诊断性能（AUC 0.948，95%CI 0.880-1），优于 DLR（AUC 0.873，95%CI 0.735-1）和 FBP（AUC 0.875，95%CI 0.731-1），但这些差异无统计学意义（P > 0.05）。总之，在心脏 CT 扫描中应用 DLR 会产生与 IR 和 FBP 获得的放射组学特征不同的特征，这表明应用 DLR 时特征稳健性无法保证。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/d22c4e70cb1e/41598_2022_19546_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/913faeab704b/41598_2022_19546_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/81832137ce13/41598_2022_19546_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/dcd1afbbc46e/41598_2022_19546_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/070a8d31e6e2/41598_2022_19546_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/d22c4e70cb1e/41598_2022_19546_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/913faeab704b/41598_2022_19546_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/81832137ce13/41598_2022_19546_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/dcd1afbbc46e/41598_2022_19546_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/070a8d31e6e2/41598_2022_19546_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/62d8/9452656/d22c4e70cb1e/41598_2022_19546_Fig5_HTML.jpg

相似文献

[1]
Deep learning-based reconstruction on cardiac CT yields distinct radiomic features compared to iterative and filtered back projection reconstructions.

Sci Rep. 2022-9-7

[2]
Low-contrast lesion detection in neck CT: a multireader study comparing deep learning, iterative, and filtered back projection reconstructions using realistic phantoms.

Eur Radiol Exp. 2024-7-24

[3]
The effect of deep learning reconstruction on abdominal CT densitometry and image quality: a systematic review and meta-analysis.

Eur Radiol. 2022-5

[4]
Superior objective and subjective image quality of deep learning reconstruction for low-dose abdominal CT imaging in comparison with model-based iterative reconstruction and filtered back projection.

Br J Radiol. 2021-7-1

[5]
The impact of deep learning reconstruction on image quality and coronary CT angiography-derived fractional flow reserve values.

Eur Radiol. 2022-11

[6]
Comparison of a Deep Learning-Based Reconstruction Algorithm with Filtered Back Projection and Iterative Reconstruction Algorithms for Pediatric Abdominopelvic CT.

Korean J Radiol. 2022-7

[7]
Image Quality and Lesion Detection on Deep Learning Reconstruction and Iterative Reconstruction of Submillisievert Chest and Abdominal CT.

AJR Am J Roentgenol. 2020-1-22

[8]
Improving Image Quality and Reducing Radiation Dose for Pediatric CT by Using Deep Learning Reconstruction.

Radiology. 2021-1

[9]
[Effect of Deep Learning-based Contrast-enhanced CT Image Reconstruction on the Image Quality of the Biliary System].

Zhongguo Yi Xue Ke Xue Yuan Xue Bao. 2022-8

[10]
Improving radiomics reproducibility using deep learning-based image conversion of CT reconstruction algorithms in hepatocellular carcinoma patients.

Eur Radiol. 2024-3

引用本文的文献

[1]
Impact of Emerging Deep Learning-Based MR Image Reconstruction Algorithms on Abdominal MRI Radiomic Features.

J Comput Assist Tomogr. 2024

[2]
Impact of deep learning image reconstruction algorithms on CT radiomic features in patients with liver tumors.

Front Oncol. 2023-4-5

本文引用的文献

[1]
Deep learning reconstruction improves radiomics feature stability and discriminative power in abdominal CT imaging: a phantom study.

Eur Radiol. 2022-7

[2]
Deep Learning-Based Image Conversion Improves the Reproducibility of Computed Tomography Radiomics Features: A Phantom Study.

Invest Radiol. 2022-5-1

[3]
Deep learning image reconstruction for improvement of image quality of abdominal computed tomography: comparison with hybrid iterative reconstruction.

Jpn J Radiol. 2021-6

[4]
Preserving image texture while reducing radiation dose with a deep learning image reconstruction algorithm in chest CT: A phantom study.

Phys Med. 2021-1

[5]
Deep learning reconstruction versus iterative reconstruction for cardiac CT angiography in a stroke imaging protocol: reduced radiation dose and improved image quality.

Quant Imaging Med Surg. 2021-1

[6]
CT iterative vs deep learning reconstruction: comparison of noise and sharpness.

Eur Radiol. 2021-5

[7]
Differentiation of left atrial appendage thrombus from circulatory stasis using cardiac CT radiomics in patients with valvular heart disease.

Eur Radiol. 2021-2

[8]
Validation of Deep-Learning Image Reconstruction for Low-Dose Chest Computed Tomography Scan: Emphasis on Image Quality and Noise.

Korean J Radiol. 2021-1

[9]
Image Quality Assessment of Abdominal CT by Use of New Deep Learning Image Reconstruction: Initial Experience.

AJR Am J Roentgenol. 2020-4-14

[10]
Validation of deep-learning image reconstruction for coronary computed tomography angiography: Impact on noise, image quality and diagnostic accuracy.

J Cardiovasc Comput Tomogr. 2020-1-13

文献AI研究员

20分钟写一篇综述，助力文献阅读效率提升50倍

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

推荐工具

医学文档翻译智能文献检索