arXiv 2310.179542023-10-27eess.IVcs.CV

基于集成学习的多支冠状动脉分割与狭窄定位

Multivessel Coronary Artery Segmentation and Stenosis Localisation using Ensemble Learning

Birmingham City University（伯明翰城市大学）；University of the West of England (UWE)（西英格兰大学）；Institute of Accounting and Administration, University of Aveiro（阿威罗大学会计与行政学院）；NUS High School of Math and Science（新加坡国立大学数学与科学高中）；Qatar University（卡塔尔大学）；Information Technology University（信息技术大学）；Bristol Heart Institute, University of Bristol（布里斯托大学布里斯托心脏研究所）

Muhammad Bilal, Dinis Martinho, Reiner Sim, Adnan Qayyum, Hunaid Vohra, Massimo Caputo, Taofeek Akinosho, Sofiat Abioye, Zaheer Khan, Waleed Niaz, Junaid Qadir

备注：: Submission report for ARCADE challenge hosted at MICCAI2023

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于五阶段训练策略和加权集成学习的端到端方案，用于多支冠状动脉分割与狭窄定位，并在 MICCAI 2023 ARCADE 挑战赛两个榜单上均获第 5 名。

摘要：

冠状动脉造影分析是心内科医生通过评估动脉粥样硬化斑块积聚来诊断冠状动脉疾病（CAD）的一项常见临床任务。本研究介绍了一种端到端机器学习解决方案，该方案是我们为 MICCAI 2023 基于区域的冠状动脉疾病自动诊断——使用 X 射线血管造影图像（ARCADE）挑战赛所开发解决方案的一部分，该挑战赛旨在为基于 X 射线冠状动脉造影的多支冠状动脉分割和潜在狭窄病变定位提供基准。我们采用了一种稳健的基线模型训练策略以逐步提升性能，该策略包括五个连续阶段：二分类预训练、多支血管分割、使用类别频率加权数据加载器进行微调、使用基于 F1 的课程学习策略（F1-CLS）进行微调，以及最后基于多目标血管造影视图分类器的集体自适应。与许多其他医学成像任务不同，该任务表现出显著的观察者间变异性。我们的集成模型使用加权集成方法将六个基线模型的输出进行组合，我们的分析表明该方法使所提出解决方案的预测准确率提高了一倍。最终预测进一步得到细化，针对误分类斑块进行校正。我们的解决方案在冠状动脉分割上取得了 37.69% 的平均 F1 分数，在狭窄定位上取得了 39.41% 的平均 F1 分数，使我们的团队在两个排行榜上均位列第 5 名。这项工作证明了自动化工具在辅助 CAD 诊断、指导干预以及提高临床环境中支架植入准确性方面的潜力。

英文摘要：

Coronary angiography analysis is a common clinical task performed by cardiologists to diagnose coronary artery disease (CAD) through an assessment of atherosclerotic plaque's accumulation. This study introduces an end-to-end machine learning solution developed as part of our solution for the MICCAI 2023 Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) challenge, which aims to benchmark solutions for multivessel coronary artery segmentation and potential stenotic lesion localisation from X-ray coronary angiograms. We adopted a robust baseline model training strategy to progressively improve performance, comprising five successive stages of binary class pretraining, multivessel segmentation, fine-tuning using class frequency weighted dataloaders, fine-tuning using F1-based curriculum learning strategy (F1-CLS), and finally multi-target angiogram view classifier-based collective adaptation. Unlike many other medical imaging procedures, this task exhibits a notable degree of interobserver variability. %, making it particularly amenable to automated analysis. Our ensemble model combines the outputs from six baseline models using the weighted ensembling approach, which our analysis shows is found to double the predictive accuracy of the proposed solution. The final prediction was further refined, targeting the correction of misclassified blobs. Our solution achieved a mean F1 score of $37.69\%$ for coronary artery segmentation, and $39.41\%$ for stenosis localisation, positioning our team in the 5th position on both leaderboards. This work demonstrates the potential of automated tools to aid CAD diagnosis, guide interventions, and improve the accuracy of stent injections in clinical settings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文