Enhancing precision in aneurysm volume measurement: A comparative study of techniques including an artificial intelligence-based method for endovascular coiling.

Surgical neurology international Pub Date : 2025-05-30 eCollection Date: 2025-01-01 DOI:10.25259/SNI_1118_2024
Rafael Trindade Tatit, Carlos Eduardo Baccin, Priya Nair, Emmanuel O Mensah, James Ryan Mason, Seena Dehkharghani, Karen Copeland, Christopher S Ogilvy
{"title":"Enhancing precision in aneurysm volume measurement: A comparative study of techniques including an artificial intelligence-based method for endovascular coiling.","authors":"Rafael Trindade Tatit, Carlos Eduardo Baccin, Priya Nair, Emmanuel O Mensah, James Ryan Mason, Seena Dehkharghani, Karen Copeland, Christopher S Ogilvy","doi":"10.25259/SNI_1118_2024","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Durable occlusion after endovascular coiling can be compromised by recanalization, underscoring the need for accurate cerebral aneurysm assessment. Precise volume measurement not only informs treatment decisions and detects subtle aneurysm growth but also refines calculations of packing density, historically linked to occlusion success. This study compares three volume-measurement approaches-traditional two-dimensional (2D) estimation, a semi-automated three-dimensional (3D) technique, and an artificial intelligence (AI)-based 3D method.</p><p><strong>Methods: </strong>In this retrospective analysis, 24 aneurysms were assessed using 3D rotational angiography. Manual segmentation by three specialists using ITK-SNAP or mimics served as the reference standard. These results were compared with volumes from a semi-automated 3D platform (Philips Advanced Visualization Workspace), an AI-based tool (RapidAI for Aneurysm), and traditional 2D estimations. Agreement with the reference standard was quantified through Passing-Bablok regression slopes and mean biases.</p><p><strong>Results: </strong>Passing-Bablok slopes for the 2D, Philips, and RapidAI methods were 0.83, 0.87, and 0.94, respectively, while mean biases were -24.7 mm<sup>3</sup> (2D), -19.5 mm<sup>3</sup> (Philips), and -14.5 mm<sup>3</sup> (RapidAI). RapidAI demonstrated the strongest correlation with the reference standard, whereas 2D estimations showed the largest discrepancy. The semi-automated 3D method exhibited intermediate accuracy, potentially influenced by the clinician input required for segmentation.</p><p><strong>Conclusion: </strong>All methods underestimated aneurysm volumes compared to the reference standard, suggesting that inaccurate volume measurements may mask early aneurysm growth. Among the techniques assessed, the AI-based approach provided the closest agreement with the reference, indicating that improved volumetric methods-particularly AI-driven ones-can enhance early detection of aneurysm expansion, guide treatment decisions, and help establish more reliable follow-up strategies for both treated and conservatively managed aneurysms.</p>","PeriodicalId":94217,"journal":{"name":"Surgical neurology international","volume":"16 ","pages":"213"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12134790/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Surgical neurology international","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.25259/SNI_1118_2024","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Durable occlusion after endovascular coiling can be compromised by recanalization, underscoring the need for accurate cerebral aneurysm assessment. Precise volume measurement not only informs treatment decisions and detects subtle aneurysm growth but also refines calculations of packing density, historically linked to occlusion success. This study compares three volume-measurement approaches-traditional two-dimensional (2D) estimation, a semi-automated three-dimensional (3D) technique, and an artificial intelligence (AI)-based 3D method.

Methods: In this retrospective analysis, 24 aneurysms were assessed using 3D rotational angiography. Manual segmentation by three specialists using ITK-SNAP or mimics served as the reference standard. These results were compared with volumes from a semi-automated 3D platform (Philips Advanced Visualization Workspace), an AI-based tool (RapidAI for Aneurysm), and traditional 2D estimations. Agreement with the reference standard was quantified through Passing-Bablok regression slopes and mean biases.

Results: Passing-Bablok slopes for the 2D, Philips, and RapidAI methods were 0.83, 0.87, and 0.94, respectively, while mean biases were -24.7 mm3 (2D), -19.5 mm3 (Philips), and -14.5 mm3 (RapidAI). RapidAI demonstrated the strongest correlation with the reference standard, whereas 2D estimations showed the largest discrepancy. The semi-automated 3D method exhibited intermediate accuracy, potentially influenced by the clinician input required for segmentation.

Conclusion: All methods underestimated aneurysm volumes compared to the reference standard, suggesting that inaccurate volume measurements may mask early aneurysm growth. Among the techniques assessed, the AI-based approach provided the closest agreement with the reference, indicating that improved volumetric methods-particularly AI-driven ones-can enhance early detection of aneurysm expansion, guide treatment decisions, and help establish more reliable follow-up strategies for both treated and conservatively managed aneurysms.

提高动脉瘤体积测量精度:包括基于人工智能的血管内盘绕方法在内的技术比较研究。
背景:血管内盘绕后的持久闭塞可能会因再通而受损,这强调了准确评估脑动脉瘤的必要性。精确的体积测量不仅可以为治疗决策提供信息,检测细微的动脉瘤生长,还可以精确计算填充密度,这在历史上与闭塞成功有关。本研究比较了三种体积测量方法-传统的二维(2D)估计,半自动三维(3D)技术和基于人工智能(AI)的三维方法。方法:采用三维旋转血管造影对24例动脉瘤进行回顾性分析。由三名专家使用ITK-SNAP或mimics作为参考标准进行手动分割。这些结果与半自动3D平台(Philips Advanced Visualization Workspace)、基于人工智能的工具(RapidAI for动脉瘤)和传统2D估计的体积进行了比较。通过pass - bablok回归斜率和平均偏差来量化与参考标准的一致性。结果:2D、Philips和RapidAI方法的pass - bablok斜率分别为0.83、0.87和0.94,而平均偏差为-24.7 mm3 (2D)、-19.5 mm3 (Philips)和-14.5 mm3 (RapidAI)。RapidAI与参考标准的相关性最强,而2D估价值的差异最大。半自动3D方法表现出中等精度,可能受到分割所需的临床医生输入的影响。结论:与参考标准相比,所有方法均低估了动脉瘤体积,提示不准确的体积测量可能掩盖了动脉瘤早期生长。在评估的技术中,基于人工智能的方法与参考文献最接近,这表明改进的体积测量方法-特别是人工智能驱动的方法-可以增强动脉瘤扩张的早期检测,指导治疗决策,并有助于为治疗和保守治疗的动脉瘤建立更可靠的随访策略。
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
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信