用于冠状动脉分割和综合特征描述的全自动深度学习方法。

IF 6.6 3区 医学 Q1 ENGINEERING, BIOMEDICAL
APL Bioengineering Pub Date : 2024-01-23 eCollection Date: 2024-03-01 DOI:10.1063/5.0181281
Guido Nannini, Simone Saitta, Andrea Baggiano, Riccardo Maragna, Saima Mushtaq, Gianluca Pontone, Alberto Redaelli
{"title":"用于冠状动脉分割和综合特征描述的全自动深度学习方法。","authors":"Guido Nannini, Simone Saitta, Andrea Baggiano, Riccardo Maragna, Saima Mushtaq, Gianluca Pontone, Alberto Redaelli","doi":"10.1063/5.0181281","DOIUrl":null,"url":null,"abstract":"<p><p>Coronary computed tomography angiography (CCTA) allows detailed assessment of early markers associated with coronary artery disease (CAD), such as coronary artery calcium (CAC) and tortuosity (CorT). However, their analysis can be time-demanding and biased. We present a fully automated pipeline that performs (i) coronary artery segmentation and (ii) CAC and CorT objective analysis. Our method exploits supervised learning for the segmentation of the lumen, and then, CAC and CorT are automatically quantified. 281 manually annotated CCTA images were used to train a two-stage U-Net-based architecture. The first stage employed a 2.5D U-Net trained on axial, coronal, and sagittal slices for preliminary segmentation, while the second stage utilized a multichannel 3D U-Net for refinement. Then, a geometric post-processing was implemented: vessel centerlines were extracted, and tortuosity score was quantified as the count of branches with three or more bends with change in direction forming an angle >45°. CAC scoring relied on image attenuation. CAC was detected by setting a patient specific threshold, then a region growing algorithm was applied for refinement. The application of the complete pipeline required <5 min per patient. The model trained for coronary segmentation yielded a Dice score of 0.896 and a mean surface distance of 1.027 mm compared to the reference ground truth. Tracts that presented stenosis were correctly segmented. The vessel tortuosity significantly increased locally, moving from proximal, to distal regions (p < 0.001). Calcium volume score exhibited an opposite trend (p < 0.001), with larger plaques in the proximal regions. Volume score was lower in patients with a higher tortuosity score (p < 0.001). Our results suggest a linked negative correlation between tortuosity and calcific plaque formation. We implemented a fast and objective tool, suitable for population studies, that can help clinician in the quantification of CAC and various coronary morphological parameters, which is helpful for CAD risk assessment.</p>","PeriodicalId":46288,"journal":{"name":"APL Bioengineering","volume":"8 1","pages":"016103"},"PeriodicalIF":6.6000,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10807932/pdf/","citationCount":"0","resultStr":"{\"title\":\"A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization.\",\"authors\":\"Guido Nannini, Simone Saitta, Andrea Baggiano, Riccardo Maragna, Saima Mushtaq, Gianluca Pontone, Alberto Redaelli\",\"doi\":\"10.1063/5.0181281\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Coronary computed tomography angiography (CCTA) allows detailed assessment of early markers associated with coronary artery disease (CAD), such as coronary artery calcium (CAC) and tortuosity (CorT). However, their analysis can be time-demanding and biased. We present a fully automated pipeline that performs (i) coronary artery segmentation and (ii) CAC and CorT objective analysis. Our method exploits supervised learning for the segmentation of the lumen, and then, CAC and CorT are automatically quantified. 281 manually annotated CCTA images were used to train a two-stage U-Net-based architecture. The first stage employed a 2.5D U-Net trained on axial, coronal, and sagittal slices for preliminary segmentation, while the second stage utilized a multichannel 3D U-Net for refinement. Then, a geometric post-processing was implemented: vessel centerlines were extracted, and tortuosity score was quantified as the count of branches with three or more bends with change in direction forming an angle >45°. CAC scoring relied on image attenuation. CAC was detected by setting a patient specific threshold, then a region growing algorithm was applied for refinement. The application of the complete pipeline required <5 min per patient. The model trained for coronary segmentation yielded a Dice score of 0.896 and a mean surface distance of 1.027 mm compared to the reference ground truth. Tracts that presented stenosis were correctly segmented. The vessel tortuosity significantly increased locally, moving from proximal, to distal regions (p < 0.001). Calcium volume score exhibited an opposite trend (p < 0.001), with larger plaques in the proximal regions. Volume score was lower in patients with a higher tortuosity score (p < 0.001). Our results suggest a linked negative correlation between tortuosity and calcific plaque formation. We implemented a fast and objective tool, suitable for population studies, that can help clinician in the quantification of CAC and various coronary morphological parameters, which is helpful for CAD risk assessment.</p>\",\"PeriodicalId\":46288,\"journal\":{\"name\":\"APL Bioengineering\",\"volume\":\"8 1\",\"pages\":\"016103\"},\"PeriodicalIF\":6.6000,\"publicationDate\":\"2024-01-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10807932/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"APL Bioengineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1063/5.0181281\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/3/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"APL Bioengineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1063/5.0181281","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/3/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

摘要

冠状动脉计算机断层扫描(CCTA)可详细评估与冠状动脉疾病(CAD)相关的早期标志物,如冠状动脉钙化(CAC)和迂曲(CorT)。然而,对它们的分析可能既耗时又有偏差。我们提出了一种全自动管道,可执行 (i) 冠状动脉分割和 (ii) CAC 和 CorT 客观分析。我们的方法利用监督学习来分割管腔,然后自动量化 CAC 和 CorT。281 张人工标注的 CCTA 图像被用于训练基于 U-Net 的两阶段架构。第一阶段使用在轴向、冠状和矢状切片上训练的 2.5D U-Net 进行初步分割,第二阶段使用多通道 3D U-Net 进行细化。然后,进行几何后处理:提取血管中心线,并将迂曲评分量化为有三个或更多弯曲且方向变化角度大于 45°的分支计数。CAC 评分依赖于图像衰减。通过设置患者特定的阈值来检测 CAC,然后应用区域生长算法进行细化。应用整个流程需要
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization.

Coronary computed tomography angiography (CCTA) allows detailed assessment of early markers associated with coronary artery disease (CAD), such as coronary artery calcium (CAC) and tortuosity (CorT). However, their analysis can be time-demanding and biased. We present a fully automated pipeline that performs (i) coronary artery segmentation and (ii) CAC and CorT objective analysis. Our method exploits supervised learning for the segmentation of the lumen, and then, CAC and CorT are automatically quantified. 281 manually annotated CCTA images were used to train a two-stage U-Net-based architecture. The first stage employed a 2.5D U-Net trained on axial, coronal, and sagittal slices for preliminary segmentation, while the second stage utilized a multichannel 3D U-Net for refinement. Then, a geometric post-processing was implemented: vessel centerlines were extracted, and tortuosity score was quantified as the count of branches with three or more bends with change in direction forming an angle >45°. CAC scoring relied on image attenuation. CAC was detected by setting a patient specific threshold, then a region growing algorithm was applied for refinement. The application of the complete pipeline required <5 min per patient. The model trained for coronary segmentation yielded a Dice score of 0.896 and a mean surface distance of 1.027 mm compared to the reference ground truth. Tracts that presented stenosis were correctly segmented. The vessel tortuosity significantly increased locally, moving from proximal, to distal regions (p < 0.001). Calcium volume score exhibited an opposite trend (p < 0.001), with larger plaques in the proximal regions. Volume score was lower in patients with a higher tortuosity score (p < 0.001). Our results suggest a linked negative correlation between tortuosity and calcific plaque formation. We implemented a fast and objective tool, suitable for population studies, that can help clinician in the quantification of CAC and various coronary morphological parameters, which is helpful for CAD risk assessment.

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
APL Bioengineering
APL Bioengineering ENGINEERING, BIOMEDICAL-
CiteScore
9.30
自引率
6.70%
发文量
39
审稿时长
19 weeks
期刊介绍: APL Bioengineering is devoted to research at the intersection of biology, physics, and engineering. The journal publishes high-impact manuscripts specific to the understanding and advancement of physics and engineering of biological systems. APL Bioengineering is the new home for the bioengineering and biomedical research communities. APL Bioengineering publishes original research articles, reviews, and perspectives. Topical coverage includes: -Biofabrication and Bioprinting -Biomedical Materials, Sensors, and Imaging -Engineered Living Systems -Cell and Tissue Engineering -Regenerative Medicine -Molecular, Cell, and Tissue Biomechanics -Systems Biology and Computational Biology
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信