Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with ''weak'' labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We frst train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate=2.5), ranking 4th/18 on the open leaderboard. We found no signifcant diference in sensitivity between aneurysm risk-of-rupture groups (p=0.75), locations (p=0.72), or sizes (p=0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.
Cross-modality image synthesis from TOF-MRA to CTA using diffusion-based models
Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Mie University Graduate School of Medicine（三重大学医学院）；Mie Chuo Medical Center（三重中央医疗中心）
Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs
Image Sciences Institute, University Medical Center Utrecht（乌得勒支大学医学中心影像科学研究所）；Department of Radiology, University Medical Center Utrecht（乌得勒支大学医学中心放射科）；Department of Neurology and Neurosurgery, UMC Utrecht Brain Center, University Medical Center Utrecht（乌得勒支大学医学中心神经病学与神经外科系，乌得勒支大学医学中心脑中心）
ArteryX: A Reliable End-to-End Toolbox for Standardized Intracranial Artery Feature Extraction from 3D TOF-MRA
Department of Neurology, University of Rochester（罗切斯特大学神经科部）；Department of Physics, University of Rochester（罗切斯特大学物理系）；Department of Imaging Sciences, University of Rochester（罗切斯特大学影像科学系）；Department of Electrical & Computer Engineering, University of Rochester（罗切斯特大学电气与计算机工程系）；Department of Biomedical Engineering, University of Rochester（罗切斯特大学生物医学工程系）
Two-Stage Deep Learning for Accelerated 3D Time-of-Flight MRA without Matched Training Data
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Seoul National University College of Medicine, Seoul National University Bundang Hospital（首尔大学医学院，首尔大学盆唐医院）
Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks
Charité Universitätsmedizin Berlin（柏林夏里特医学院）；Technical University Berlin（柏林工业大学）；Birmingham City University（伯明翰城市大学）；Fraunhofer MEVIS（弗劳恩霍夫医学图像计算研究所）；Beuth University of Applied Sciences（拜伊特应用科学大学）
数据的匿名化和共享是隐私保护和医学图像分析大数据集获取的关键。这是一个很大的挑战，尤其是对神经成像。在这里，大脑的独特结构允许重新识别，因此需要非传统的匿名化。生成对抗网络（GANs）有可能在保持预测特性的同时提供匿名图像。分析脑血管分割，我们在飞行时间（TOF）磁共振血管造影（MRA）贴片上训练了3个GANs，用于图像标签生成：1）深度卷积GAN，2）具有梯度惩罚的Wasserstein-GAN（WGAN-GP）和3）具有谱归一化的WGAN-GP（WGAN-GP-SN）。从每个GAN生成的图像标签被用于训练用于分割的U-网络，并在真实数据上进行测试。此外，我们使用迁移学习在第二个数据集上应用了我们的合成补丁。对于越来越多的多达15名患者，我们评估了有和没有预训练的真实数据的模型性能。通过Dice相似系数（DSC）和Hausdorff距离的第95百分位数（95 HD）评估所有模型的性能。比较3个GANs，在WGAN-GP-SN生成的合成数据上训练的U-网络显示出最高的预测血管的性能（DSC/95 HD 0.82/28.97），这是由在真实数据上训练的U-网络（0.89/26.61）进行基准测试的。对于相同的GAN，迁移学习方法显示出优于无预训练的性能，特别是对于仅一名患者（0.91/25.68 vs. 0.85/27.36）。在这项工作中，合成图像标签对保留了可推广的信息，并表现出…
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）
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）
Hessian-Based Lightweight Neural Network HessNet for State-of-the-Art Brain Vessel Segmentation on a Minimal Training Dataset
Institute of Artificial Intelligence, M.V.Lomonosov Moscow State University（人工智能研究所，莫斯科国立大学）；Laboratory of Analysis of Semantics, Centre for Language and Semantics Technologies, Faculty of Computer Science, HSE University（语义分析实验室，语言与语义技术中心，计算机科学系，高等经济大学）；Neurosputnik LLC（Neurosputnik公司）；Mechanics and Mathematics Faculty, M.V.Lomonosov Moscow State University（力学与数学系，莫斯科国立大学）；International Laboratory of Algebraic Topology and Its Applications, Faculty of Computer Science, HSE University（国际拓扑学及其应用实验室，计算机科学系，高等经济大学）
DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Erasmus MC（伊拉斯姆斯医学中心）；University of Copenhagen（哥本哈根大学）；German Center for Neurodegenerative Disease（德国神经退行性疾病中心）；Center for Behavioral Brain Sciences（行为脑科学中心）
