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

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

MRI-based assessment of tumor aggressiveness in nasopharyngeal carcinoma: risk stratification and survival prediction.

European radiology·2026
Same author

Diffusion weighted imaging-based tumor growth rate for predicting long-term survival in nasopharyngeal carcinoma.

Cancer imaging : the official publication of the International Cancer Imaging Society·2026
Same author

A Systematic Review and Meta-Analysis of the Impact of Tumour Mutation Burden on Survival Outcomes in Solid Tumours.

Cancer medicine·2026
Same author

Differentiation of MPNSTs from benign neurofibromas in neurofibromatosis patients using ADC and SUV biomarkers in children and young adults.

Current problems in diagnostic radiology·2026
Same author

Neuroimaging evaluation of high dose methotrexate-induced neurotoxicity in pediatric and young adults: a PET/MRI study.

Frontiers in neuroimaging·2026
Same author

Mammary small cell neuroendocrine carcinomas that showed excellent pathologic response following etoposide-based neoadjuvant chemotherapy.

Breast cancer research and treatment·2025
Same journal

The efficacy of multisite MRI scanners for total brain volume measurements: a cross-sectional study in Saudi Arabia.

Frontiers in radiology·2026
Same journal

Deep learning image reconstruction technique for improving image quality and radiation dose reduction compared to iterative reconstruction technique in non-contrast CT head imaging.

Frontiers in radiology·2026
Same journal

Self-adaptive forward-forward network for anomaly detection and medical image analysis.

Frontiers in radiology·2026
Same journal

Case Report: Structured MRI assessment of posterior thalamic infarction in a distribution compatible with posterior choroidal artery territory presenting as Déjerine-Roussy syndrome in an adolescent: differentiating arterial ischemia from venous thrombosis and thalamic neoplasm.

Frontiers in radiology·2026
Same journal

Bringing light to the reading room.

Frontiers in radiology·2026
Same journal

Transarterial embolization in the management of chronic shoulder pain: clinical evidence and emerging therapeutic role.

Frontiers in radiology·2026
查看所有相关文章

相关实验视频

Updated: Sep 14, 2025

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.0K

使用深度学习进行脑瘤细分:高性能,最小化MRI数据.

Jacky Huang1, Banu Yagmurlu2, Powell Molleti1

  • 1Department of Medicine, Division of Oncology, Stanford University School of Medicine, Stanford, CA, United States.

Frontiers in radiology
|July 23, 2025
PubMed
概括
此摘要是机器生成的。

深度学习模型可以使用仅两个MRI序列 (T1C + FLAIR) 准确地细分脑瘤,减少数据需求. 这种优化提高了医疗成像中的临床和研究应用的效率和通用性.

关键词:
3D脑瘤细分 3D脑瘤细分人工智能的人工智能是人工智能.计算机视觉 计算机视觉卷积神经网络 (CNN) 是一种神经网络.深度学习 (DL) 是指深度学习.质瘤 质瘤 是一种磁共振成像 (MRI) 的使用.语义细分 语义细分 语义细分 语义细分

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.4K

相关实验视频

Last Updated: Sep 14, 2025

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.4K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经瘤学神经瘤学

背景情况:

  • 从MRI手动脑瘤细分是劳动密集型和耗时的.
  • 深度学习 (DL) 为自动化和优化这一过程提供了一个潜在的解决方案.
  • 尽量减少所需的MRI序列的数量可以提高DL模型的通用性和临床采用.

研究的目的:

  • 通过最大限度地减少MRI序列的数量来优化基于深度学习的脑瘤细分.
  • 为了评估3DU-Net模型的性能,使用不同的MRI序列组合进行质瘤细分.
  • 为了比较训练在T1C-only,FLAIR-only,T1C + FLAIR和T1 + T2 + T1C + FLAIR序列上的模型的细分精度.

主要方法:

  • 在2018年MICCAI BraTS数据集上训练了一个3D U-Net深度学习模型.
  • 专注于增强瘤 (ET) 和瘤核心 (TC) 的子细分.
  • 使用5倍交叉验证和单独的测试数据集 (358个样本) 评估模型性能,比较四种MRI序列组合.

主要成果:

  • 在T1C + FLAIR序列组合中,在ET和TC细分的交叉验证和测试数据集中,实现了与全部四个序列相比或超过的Dice分数.
  • 仅T1C也在TC细分方面表现强.
  • 在所有配置中,特异性仍然很高 (≥0.958),T1C + FLAIR在ET划分方面表现出卓越的性能.

结论:

  • 深度学习模型可以使用仅两个MRI序列 (T1C + FLAIR) 实现大脑瘤细分的高精度.
  • 减少对多个序列的依赖可以提高DL模型的概括性,并促进在临床和研究环境中更广泛的传播.
  • 这种方法有可能显著减少大脑瘤细分所涉及的手工劳动.