arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.17115cs.CV
收藏

用于3D TOF-MRI中未破裂颅内动脉瘤检测与体积分割的多中心AI模型

Multi-centric AI Model for Unruptured Intracranial Aneurysm Detection and Volumetric Segmentation in 3D TOF-MRI

University Hospital Basel(巴塞尔大学医院)

Ashraya K. Indrakanti, Jakob Wasserthal, Martin Segeroth, Shan Yang, Victor Schulze-Zachau, Joshy Cyriac, Michael Bach, Marios Psychogios, Matthias A. Mutke

AI总结:

本文开发了一个基于nnU-Net的开源多中心AI模型,用于在3D TOF-MRI中联合检测和分割未破裂颅内动脉瘤,在独立测试集上实现了85%的敏感度和0.23的假阳性/病例率,优于ADAM挑战赛获胜者,展示了改善临床诊断和监测的潜力。

摘要:

目的:开发一个基于nnU-Net的开源AI模型,用于在3D TOF-MRI中联合检测和分割未破裂颅内动脉瘤(UICA),并比较在包含动脉瘤样鉴别诊断的数据集上训练的模型。方法:这项回顾性研究(2020-2023年)纳入了来自多个中心的364名患者(平均年龄59岁,60%为女性)的385例匿名化3D TOF-MRI图像,以及来自ADAM挑战赛的113名受试者。图像包含未经治疗或可能的UICA及鉴别诊断。构建了四个不同的训练数据集,并使用nnU-Net框架进行模型开发。在独立测试集上评估性能,检测指标采用敏感度和假阳性(FP)/病例率,分割指标采用DICE评分和阈值为0.5mm的NSD(归一化表面距离)。统计分析包括卡方检验、Mann-Whitney-U检验和Kruskal-Wallis检验,显著性水平设为p < 0.05。结果:各模型的总体敏感度在82%至85%之间,FP/病例率为0.20至0.31,无显著差异(p = 0.90和p = 0.16)。主模型实现了85%的敏感度和0.23的FP/病例率,在敏感度上优于ADAM挑战赛获胜者(61%)和在ADAM数据上训练的nnU-Net(51%)(p < 0.05)。对于正确检测到的UICA,该模型实现了0.73的平均DICE评分和0.84的NSD。结论:我们的开源、基于nnU-Net的AI模型(可在10.5281/zenodo.13386859获取)在3D TOF-MRI中展示了高敏感度、低假阳性率和一致的分割精度,表明其具有改善UICA临床诊断和监测的潜力。

英文摘要:

Purpose: To develop an open-source nnU-Net-based AI model for combined detection and segmentation of unruptured intracranial aneurysms (UICA) in 3D TOF-MRI, and compare models trained on datasets with aneurysm-like differential diagnoses. Methods: This retrospective study (2020-2023) included 385 anonymized 3D TOF-MRI images from 364 patients (mean age 59 years, 60% female) at multiple centers plus 113 subjects from the ADAM challenge. Images featured untreated or possible UICAs and differential diagnoses. Four distinct training datasets were created, and the nnU-Net framework was used for model development. Performance was assessed on a separate test set using sensitivity and False Positive (FP)/case rate for detection, and DICE score and NSD (Normalized Surface Distance) with a 0.5mm threshold for segmentation. Statistical analysis included chi-square, Mann-Whitney-U, and Kruskal-Wallis tests, with significance set at p < 0.05. Results: Models achieved overall sensitivity between 82% and 85% and a FP/case rate of 0.20 to 0.31, with no significant differences (p = 0.90 and p = 0.16). The primary model showed 85% sensitivity and 0.23 FP/case rate, outperforming the ADAM-challenge winner (61%) and a nnU-Net trained on ADAM data (51%) in sensitivity (p < 0.05). It achieved a mean DICE score of 0.73 and an NSD of 0.84 for correctly detected UICA. Conclusions: Our open-source, nnU-Net-based AI model (available at 10.5281/zenodo.13386859) demonstrates high sensitivity, low false positive rates, and consistent segmentation accuracy for UICA detection and segmentation in 3D TOF-MRI, suggesting its potential to improve clinical diagnosis and for monitoring of UICA.

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。

↑