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
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.
Aneumo: A Large-Scale Comprehensive Synthetic Dataset of Aneurysm Hemodynamics
Artificial Intelligence Innovation and Incubation Institute, Fudan University(复旦大学人工智能创新与孵化研究院);Shanghai Academy of Artificial Intelligence for Science(上海科学人工智能研究院)
Deep Learning Based Detection and Localization of Intracranial Aneurysms in Computed Tomography Angiography
Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院高级医学计算与分析中心);Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院戈登医学影像中心);Department of Radiology, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院放射科)
An anatomically-informed 3D CNN for brain aneurysm classification with weak labels
Lausanne University Hospital and University of Lausanne(洛桑大学医院和洛桑大学);Center for Biomedical Imaging(生物医学成像中心);Ecole Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)
Uppsala University(乌普萨拉大学);Cornell University(康奈尔大学);Cornell Tech(康奈尔科技学院);Weill Cornell Medicine(威尔康奈尔医学院);Radiological Society of North America(北美放射学会);Taipei Medical University Hospital(台北医学大学附属医院);UC San Diego(加州大学圣地亚哥分校);Prince Sultan Military Medical City(苏丹王子军事医疗城);Liverpool Hospital(利物浦医院);Clinical Center of the University of Sarajevo(萨拉热窝大学临床中心);Memorial University of Newfoundland(纽芬兰纪念大学);Fleni(弗莱尼医院);University of California San Francisco(加州大学旧金山分校);Koç University School of Medicine(科奇大学医学院);Intermed IUHW Hospital(国际医疗福祉大学医院);Hacettepe University(哈塞特佩大学);Duke University(杜克大学);China Medical University Hospital(中国医药大学附属医院)
Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
Capital Medical University(首都医科大学);China National Clinical Research Center for Neurological Diseases(国家神经系统疾病临床医学研究中心);Tencent(腾讯);Shandong Jining Medical College(山东济宁医学院)
背景资料:开发一种人工智能系统,该系统可以基于非造影CT(NCCT)扫描准确识别急性非创伤性颅内出血(ICH)病因,并研究临床医生是否可以在诊断环境中从中受益。材料与方法:深度学习模型是使用2011年1月至2018年4月期间收集的1868例符合条件的非创伤性ICH NCCT扫描结果开发的。我们在2018年4月之后收集的两个独立数据集(TT 200和SD 98)上测试了该模型。该模型的诊断性能与临床医生的性能进行了比较。我们进一步设计了一项模拟研究,以比较临床医生在有和没有深度学习系统增强的情况下的表现。结果如下:所提出的深度学习系统实现了0.986的受试者工作曲线下面积(95% CI 0.967-1.000)动脉瘤,0.952(0.917-0.987)高血压出血,0.950(0.860-1.000)动静脉畸形(AVM),0.749 TT 200数据集中Moyamoya病(MMD)为0.586-0.912,海绵状血管畸形(CM)为0.837(0.704-0.969),其他原因为0.839(0.722-0.959)。在90%的特异性水平下,我们的模型对动脉瘤和AVM诊断的敏感性分别为97.1%和90.9%。该模型在独立数据集SD 98中也显示出令人印象深刻的普遍性。临床医生通过拟议的系统增强在某些出血病因诊断的灵敏度、特异性和准确性方面实现了显著改善。结论:提出的深度学习算法可以成为基…
Machine learning algorithms to predict the risk of rupture of intracranial aneurysms: a systematic review
King’s College London(伦敦国王学院);Guy’s and St. Thomas’ NHS Foundation Trust(盖伊和圣托马斯国民保健服务基金会信托);University College London Hospital NHS Foundation Trust(伦敦大学学院医院国民保健服务基金会信托);King’s College Hospital(国王学院医院)
Rethinking Intracranial Aneurysm Vessel Segmentation: A Perspective from Computational Fluid Dynamics Applications
Artificial Intelligence Innovation and Incubation Institute, Fudan University(复旦大学人工智能创新与孵化院);Shanghai Academy of Artificial Intelligence for Science(上海人工智能科学研究院);Department of Civil and Environmental Engineering, Hong Kong Polytechnic University(香港理工大学土木与环境工程系);Huashan Hospital, Fudan University(复旦大学华山医院)
Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior
Department of Computer Science and Software Engineering, Concordia University, Montréal, Canada(计算机科学与软件工程系,康科迪亚大学);NeuroRx Research, Montréal, Canada(NeuroRx研究公司);Department of Electrical and Computer Engineering, Concordia University, Montréal, Canada(电气与计算机工程系,康科迪亚大学)
Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection
Brigham and Women’s Hospital(布列根和妇女医院);Harvard Medical School(哈佛医学院);Northeastern University(东北大学);Dana-Farber Cancer Institute(丹娜-法伯癌症研究所);Washing University in St. Louis(圣路易斯华盛顿大学);First Affiliated Hospital of Guangzhou Medical University(广州医科大学附属第一医院)