文献速递神经MR

以简化脑MRI扫描方案作为AI驱动实时扫描方案适配前提时检测关键发现的准确性

Accuracy of detecting critical findings using abbreviated brain MRI scan protocols as a prerequisite for AI-driven on-the-fly scan protocol adaptation.
PubMed 文献 · Eur J Radiol · 2025-08-17

该回顾性、连续富集队列研究纳入丹麦四家医院414例成人常规脑MRI扫描,评估AI工具与神经放射科顾问、放射科住院医师、MR技师使用3序列或4序列简化方案检测脑梗死、颅内出血和肿瘤的效能。AI检测脑梗死、出血和肿瘤的敏感度分别为94%、82%和74%,特异度分别为86%、84%和62%;AI敏感度与使用简化方案的神经放射科医师相当,肿瘤检测敏感度超过MR技师,但特异度较低。结论认为自动化实时扫描适配的初步步骤可行,可能提高检测敏感度,但需权衡较当前标准诊疗降低的特异度。

要点

  • AI工具使用简化3序列或4序列方案检测脑梗死敏感度94%(61/65),出血82%(53/65),肿瘤74%(48/65)。
  • AI对应特异度分别为86%(300/349)、84%(293/349)和62%(217/349),均低于神经放射科医师。
  • AI肿瘤检测敏感度超过MR技师,但特异度较低;敏感度与神经放射科医师使用简化方案相当。

核心结论

  • 自动化实时扫描适配的初步步骤可行,可能提高检测敏感度,但需权衡较当前标准诊疗降低的特异度。

研究设计与样本

  • 回顾性、连续富集队列研究,纳入丹麦四家医院414例成人常规脑MRI扫描,采用非重叠三向拆分交叉设计,由3名神经放射科顾问、3名放射科住院医师、3名MR技师及AI工具分别使用简化3序列方案(DWI、SWI/T2*-GRE、T2-FLAIR)或4序列方案(DWI、SWI/T2*-GRE、T2-FLAIR、T1W)检测脑梗死、出血和肿瘤;参考发现基于放射学报告和独立图像复核。

诊断标准与关键数值

  • AI工具检测脑梗死敏感度94%(61/65,95%CI:85-98%),特异度86%(300/349,95%CI:82-89%)。
  • AI工具检测颅内出血敏感度82%(53/65,95%CI:70-90%),特异度84%(293/349,95%CI:80-88%)。
  • AI工具检测肿瘤敏感度74%(48/65,95%CI:61-84%),特异度62%(217/349,95%CI:57-67%)。
  • AI工具敏感度与使用简化方案的神经放射科医师相当,肿瘤检测敏感度超过MR技师,但特异度较低。

临床应用与阅片要点

  • 使用简化3序列或4序列脑MRI方案时,AI工具对脑梗死检测敏感度最高(94%),对肿瘤检测敏感度较低(74%)。
  • AI工具的特异度均低于神经放射科医师,阅片时需注意其假阳性可能。
  • AI驱动实时扫描方案适配的初步步骤可行,但原文结论提示需权衡较当前标准诊疗降低的特异度。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: To evaluate the performance of an AI tool and relevant radiology professionals in detecting brain infarcts, intracranial hemorrhages, and tumors using abbreviated brain MRI scan protocols as prerequisite for an AI-driven workflow that dynamically selects additional imaging sequences based on real-time imaging findings.

MATERIALS AND METHODS: A retrospective, consecutively enriched cohort of routine adult brain MRI scans from four Danish hospitals was constructed. Three consultant neuroradiologists, three radiology residents, three MR technologists, and an AI tool detected brain infarcts, hemorrhages, and tumors using an abbreviated 3-sequence protocol (DWI, SWI/T2*-GRE, T2-FLAIR) or 4-sequence protocol (DWI, SWI/T2*-GRE, T2-FLAIR, T1W) in a non-overlapping three-way split cross-over design. Reference findings were established from radiological reports and independent image reviews.

RESULTS: A total of 414 patients were included (57 years ± 19, 238 men) with 65 confirmed brain infarcts, 65 hemorrhages, and 65 tumors. The AI tool achieved detection sensitivities of 94 % (61 of 65 scans, 95 %CI:85-98 %), 82 % (53 of 65 scans, 95 %CI:70-90 %), and 74 % (48 of 65 scans, 95 %CI:61-84 %) for brain infarcts, hemorrhages, and tumors, respectively, and corresponding specificities of 86 % (300 of 349 scans, 95 %CI:82-89 %), 84 % (293 of 349 scans, 95 %CI:80-88 %), and 62 % (217 of 349 scans, 95 %CI:57-67 %). The tool achieved sensitivities comparable to those of neuroradiologists using abbreviated scan protocols, and it surpassed MR technologists in tumor detection, though its specificities were lower.

CONCLUSION: The initial steps towards automated real-time scan adaptation are feasible and can potentially improve detection sensitivity, balancing reduced specificities compared to the current standard of care.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Sheng K, Ingala S, Brandt AH, et al. Accuracy of detecting critical findings using abbreviated brain MRI scan protocols as a prerequisite for AI-driven on-the-fly scan protocol adaptation. Eur J Radiol. 2025. PMID: 40902437. doi:10.1016/j.ejrad.2025.112365

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。