Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Neuroplasticity01:01

Neuroplasticity

267
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
267

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Accuracy of ankle versus arm oscillometric non-invasive blood pressure in detecting hypotension during shoulder surgery in the beach-chair position: A prospective observational study.

Indian journal of anaesthesia·2026
Same author

Long-term outcomes of evolving treatment regimens in Ewing sarcoma survivors diagnosed 1970-1999: A report from the Childhood Cancer Survivor Study.

Cancer·2026
Same author

Mitochondrial dysfunction in schizophrenia and its modulation by atypical antipsychotic drugs: A randomized controlled trial.

Journal of psychopharmacology (Oxford, England)·2026
Same author

Comparative assessment of asparaginase activity, population pharmacokinetics, and safety of biosimilar native Escherichia coli and pegylated asparaginase in children with newly diagnosed acute lymphoblastic leukemia: a pharmacometrics-based randomized clinical trial.

BMC cancer·2026
Same author

Longitudinal Functional Outcomes Among Survivors of Childhood Lower Extremity Osteosarcoma.

Cancers·2026
Same author

Understanding Childhood Cancer Survivorship: A Qualitative Study on Global Care Approaches.

JCO global oncology·2026

相关实验视频

Updated: May 26, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

971

图表神经网络在儿科结构连接组上的学习.

Anand Srinivasan1, Rajikha Raja1, John O Glass1

  • 1Departments of Radiology, St. Jude Children's Research Hospital, Memphis, TN 38105, USA.

Tomography (Ann Arbor, Mich.)
|February 25, 2025
PubMed
概括
此摘要是机器生成的。

图形神经网络 (GNN) 在儿科大脑连接组数据中显示出性别分类的前景. 将较小的儿科数据集与成人数据相结合,提高了GNN的性能,强调了需要有效的培训策略的需要.

关键词:
数据丰富的数据丰富.图形神经网络的神经网络结构性大脑连接体 - 连接体

更多相关视频

A Neonatal Mouse Spinal Cord Compression Injury Model
13:31

A Neonatal Mouse Spinal Cord Compression Injury Model

Published on: March 27, 2016

12.4K
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
07:01

A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)

Published on: February 7, 2025

347

相关实验视频

Last Updated: May 26, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

971
A Neonatal Mouse Spinal Cord Compression Injury Model
13:31

A Neonatal Mouse Spinal Cord Compression Injury Model

Published on: March 27, 2016

12.4K
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
07:01

A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)

Published on: February 7, 2025

347

科学领域:

  • 神经科学是一个神经科学.
  • 机器学习 机器学习
  • 脑部成像 脑部成像

背景情况:

  • 使用结构连接组数据进行性别分类是脑图学习中的关键基准.
  • 图形神经网络 (GNN) 擅长从图形数据中学习,但它们在儿科患者中的应用尚未得到充分探索.

研究的目的:

  • 调查GNN学习儿科连接组模式的能力.
  • 探索儿童性别分类中GNN的培训技术和建筑设计.
  • 将GNN性能与成人和儿科数据集中的其他机器学习模型进行比较.

主要方法:

  • 使用的成人 (BRIGHT) 和儿科 (HCP-D) 连接组数据集.
  • 训练有素的GNN模型 (GCN简单,GCN残留),深度神经网络 (MLP) 和标准ML模型 (RF,SVM).
  • 进行了架构探索 (深度,聚合,跳过连接) 并评估了对抗性稳定性.

主要成果:

  • 在成人和儿科人口中,GNN的表现优于其他模型.
  • 成年GNN在成年人性别分类方面实现了85.1%的准确性.
  • 将儿科数据与成人数据相结合,获得了类似的准确性 (83.0%儿科,81.3%成人).
  • 与剩余GCN和MLP相比,简单的GCN显示出更高的对抗性稳定性.

结论:

  • 在理解性别特异性神经发育和疾病方面,GNN具有显著的潜力.
  • 数据增强对于克服小型儿科数据集的挑战至关重要.
  • 在GNN模型的复杂性,准确性和对抗性稳定性之间存在权衡.