Scholarlink

Introduction <p>Automated segmentation of intracranial vessels in 3D black-blood T1W-MRI is feasible. This study evaluates its utility for detecting recurrent aneurysms and compares automatically labeled MRI (AL-BB-MRI) with time-of-flight MRA (TOF-MRA) and digital subtraction angiography (DSA).</p> Materials (patients) and methods <p>For model development, the basal intracranial arteries were manually labeled in 37 3D black-blood T1W-MRI examinations from 31 patients with previously endovascularly treated aneurysms. An independent, consecutive series of 84 patients with 90 aneurysms was assessed by three readers to identify recurrences in AL-BB-MRI and TOF-MRA. DSA served as the reference standard when available.</p> Results <p>The model achieved adequate vessel segmentation (Dice = 0.81). Agreement between AL-BB-MRI and TOF-MRA was in 70/90 (78%) aneurysms. Major recurrence rates were similar: 16/90 (18%) aneurysms on AL-BB-MRI and in 14/90 (16%) aneurysms on TOF-MRA. Discrepancies were most common in anterior communicating aneurysms (seven seen only in AL-BB-MRI) and basilar artery aneurysms (five only in TOF-MRA). Compared to DSA (<i>n</i> = 22), AL-BB-MRI had similar accuracy (73% vs. 77%), sensitivity (62% each), and specificity (79% vs. 86%). AL-BB-MRI and TOF disagreed in nine aneurysms: AL-BB-MRI was false positive in three and false negative in two, while TOF-MRA was false positive in two and false negative in another two aneurysms.</p> Conclusions <p>AL-BB-MRI showed high agreement with TOF-MRA in recurrence detection of aneurysms in the anterior circulation. Both modalities performed similarly against DSA. AL-BB-MRI was superior after flow-diverter or stent-assisted treatment but less reliable for intrasaccular flow disruption. (Level of Evidence: 5B).</p> <p>The study was registered in the German Clinical Trials Register (DRKS00014644) on 07.05.2018.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning-based vessel segmentation in non-contrast black-blood MRI for treated aneurysm follow-up: a comparative study with TOF-MRA and DSA

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月6日

查看全文
  • Samer Elsheikh,
  • Alexander Rau,
  • Petra Cimflova,
  • Urs Würtemberger,
  • Elias Kellner,
  • Horst Urbach,
  • Marco Reisert

摘要

Introduction

Automated segmentation of intracranial vessels in 3D black-blood T1W-MRI is feasible. This study evaluates its utility for detecting recurrent aneurysms and compares automatically labeled MRI (AL-BB-MRI) with time-of-flight MRA (TOF-MRA) and digital subtraction angiography (DSA).

Materials (patients) and methods

For model development, the basal intracranial arteries were manually labeled in 37 3D black-blood T1W-MRI examinations from 31 patients with previously endovascularly treated aneurysms. An independent, consecutive series of 84 patients with 90 aneurysms was assessed by three readers to identify recurrences in AL-BB-MRI and TOF-MRA. DSA served as the reference standard when available.

Results

The model achieved adequate vessel segmentation (Dice = 0.81). Agreement between AL-BB-MRI and TOF-MRA was in 70/90 (78%) aneurysms. Major recurrence rates were similar: 16/90 (18%) aneurysms on AL-BB-MRI and in 14/90 (16%) aneurysms on TOF-MRA. Discrepancies were most common in anterior communicating aneurysms (seven seen only in AL-BB-MRI) and basilar artery aneurysms (five only in TOF-MRA). Compared to DSA (n = 22), AL-BB-MRI had similar accuracy (73% vs. 77%), sensitivity (62% each), and specificity (79% vs. 86%). AL-BB-MRI and TOF disagreed in nine aneurysms: AL-BB-MRI was false positive in three and false negative in two, while TOF-MRA was false positive in two and false negative in another two aneurysms.

Conclusions

AL-BB-MRI showed high agreement with TOF-MRA in recurrence detection of aneurysms in the anterior circulation. Both modalities performed similarly against DSA. AL-BB-MRI was superior after flow-diverter or stent-assisted treatment but less reliable for intrasaccular flow disruption. (Level of Evidence: 5B).

The study was registered in the German Clinical Trials Register (DRKS00014644) on 07.05.2018.