Many atlases used for brain parcellation are hierarchically organised, progressively dividing the brain into smaller sub-regions. However, state-of-the-art parcellation methods tend to ignore this structure and treat labels as if they are `flat'. We introduce a hierarchically-aware brain parcellation method that works by predicting the decisions at each branch in the label tree. We further show how this method can be used to model uncertainty separately for every branch in this label tree. Our method exceeds the performance of flat uncertainty methods, whilst also providing decomposed uncertainty estimates that enable us to obtain self-consistent parcellations and uncertainty maps at any level of the label hierarchy. We demonstrate a simple way these decision-specific uncertainty maps may be used to provided uncertainty-thresholded tissue maps at any level of the label tree.
Parcellation of Visual Cortex on high-resolution histological Brain Sections using Convolutional Neural Networks
1 Institute of Neuroscience;O. Vogt Institute for Brain Research, Heinrich-Heine University D\"usseldorf, Germany 3 Institut f\"ur Informatik, Heinrich-Heine University D\"usseldorf, Germany
DDEvENet: Evidence-based Ensemble Learning for Uncertainty-aware Brain Parcellation Using Diffusion MRI
University of Electronic Science and Technology of China(电子科技大学);The First Affiliated Hospital, Sun Yat-sen University(中山大学附属第一医院);The Second Affiliated Hospital, Zhejiang University School of Medicine(浙江大学医学院附属第二医院);Nanjing University of Science and Technology(南京理工大学);East China University of Science and Technology(华东理工大学);Harvard Medical School(哈佛医学院);School of Mathematical Sciences, University of Tel Aviv(特拉维夫大学数学科学学院)
GOUHFI 2.0: A Next-Generation Toolbox for Brain Segmentation and Cortex Parcellation at Ultra-High Field MRI
Department of Physics, Norwegian University of Science and Technology(挪威科学技术大学物理系);Department of Radiology and Nuclear Medicine, St. Olavs Hospital HF(斯托尔奥斯医院HF放射科和核医学部);Department of Neurology and Clinical Neurophysiology, St. Olavs Hospital HF(斯托尔奥斯医院HF神经科和临床神经生理学部);Department of Neuromedicine and Movement Science, St. Olavs Hospital HF(斯托尔奥斯医院HF神经医学与运动科学部);Neuro-SysMed Center for Clinical Treatment Research, Department of Neurology, Haukeland University Hospital(Haukeland大学医院神经科临床治疗研究神经系医学中心);Department of Clinical Medicine, University of Bergen(卑尔根大学临床医学系);K.G. Jebsen Center for Translational Research in Parkinson’s disease, University of Bergen(帕金森病转化研究Jebsen中心,卑尔根大学)
Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions
Brigham and Women’s Hospital(布莱根妇女医院);Harvard Medical School(哈佛医学院);University of Sydney(悉尼大学);University of New South Wales(新南威尔士大学);Massachusetts General Hospital(麻省总医院)
Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks
Institute of Neuroscience and Medicine INM-1, Forschungszentrum Jülich(于利希研究中心神经科学与医学研究所(INM-1));C. and O. Vogt Institute of Brain Research, Heinrich-Heine University Düsseldorf(杜塞尔多夫海因里希·海涅大学C.和O.福格特脑研究所);Institute of Computer Science, Heinrich-Heine University Düsseldorf(杜塞尔多夫海因里希·海涅大学计算机科学研究所)
Frequency-specific segregation and integration of human cerebral cortex: an intrinsic functional atlas
National University of Defense Technology(国防科技大学)
人脑功能网络的频率特异性耦合机制是其复杂认知和行为功能的基础。然而,它并没有很好地揭示什么是人类大脑的频率特定的细分和网络拓扑结构。本研究利用频谱连接法估计了人类大脑皮层的功能连接,并利用特征聚类和梯度法对大脑皮层进行了频率特异性分组,探讨了其拓扑结构。使用HCP数据集中的184名受试者的7 T fMRI数据进行分组并探索功能网络的拓扑性质,使用另外890名受试者的3 T fMRI数据来确认频率特异性拓扑的稳定性。7 ~ 10个功能网络在特定频率下被2 ~ 4个可分离的枢纽类别稳定整合,根据跨频率的包裹,我们提出了一个包含456个包裹的内在功能图谱。结果表明,功能网络包含稳定的频率特异性拓扑结构,这可能意味着更丰富的功能单元的角色和更复杂的相互作用。
Global Context Is All You Need for Parallel Efficient Tractography Parcellation
University of Bonn(波恩大学);Center for X-ray and Nano Science CXNS, DESY(欧洲同步辐射中心X射线与纳米科学中心);University Hospital Bonn(波恩大学医院);German Center for Neurodegenerative Diseases (DZNE)(德国神经退行性疾病中心);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究院)
Recon-all-clinical: Cortical surface reconstruction and analysis of heterogeneous clinical brain MRI
Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);Copenhagen University Hospital - Amager and Hvidovre(哥本哈根大学医院阿莫尔与维杜夫院区);Danish Research Centre for Magnetic Resonance(丹麦磁共振研究中心);Centre for Functional and Diagnostic Imaging and Research(功能与诊断成像及研究中心)
Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
Shanghai University(上海大学);Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences(中国科学院苏州生物医学工程技术研究所);University of Science and Technology of China(中国科学技术大学);Wenzhou Medical University(温州医科大学)
NeuroGAN-3D: Enhancing Intrinsic Functional Brain Networks via High-Fidelity 3D Generative Super-Resolution
Georgia State University(佐治亚州立大学);Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS)(神经影像与数据科学转化研究三机构中心(TReNDS));Georgia Institute of Technology(佐治亚理工学院);Emory University(埃默里大学)
Hierarchical Generalized Category Discovery for Brain Tumor Classification in Digital Pathology
Institute of Clinical Epidemiology, Public Health, Health Economics, Medical Statistics and Informatics(临床流行病学、公共卫生、健康经济学、医学统计与信息学研究所);Institute of Neuropathology and Neuromolecular Pathology(神经病理学与神经分子病理学研究所)
UniBrain: Universal Brain MRI Diagnosis with Hierarchical Knowledge-enhanced Pre-training
Shanghai AI Laboratory(上海人工智能实验室);Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University(上海交通大学附属第六人民医院);Shanghai Jiao Tong University(上海交通大学);University of Science Technology of China(中国科学技术大学)
Hierarchical Brain Structure Modeling for Predicting Genotype of Glioma
College of Medicine and Biological Information Engineering, Northeastern University, Liaoning, China(医学与生物信息工程学院,东北大学,辽宁,中国);School of Science and Engineering, University of Dundee, Dundee, UK(科学与工程学院,邓迪大学,邓迪,英国);School of Medicine, University of Dundee, Dundee, UK(医学院,邓迪大学,邓迪,英国);Department of Applied Maths and Theoretical Physics, University of Cambridge, Cambridge, UK(应用数学与理论物理系,剑桥大学,剑桥,英国)
3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);School of Biomedical Engineering, Shenzhen University(深圳大学生物医学工程学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);College of Computer Science and Technology, Qingdao University(青岛大学计算机科学与技术学院)