Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

A Rhombic Pt(II) Metallacycle with Enhanced Third-Order Nonlinear Optical Response and Optical Power Limiting Performance.

ACS applied materials & interfaces·2026

Same author

Magnetically Driven Dual-miRNA Framework Nucleic Acid Biosensing Platform for Precise Classification of Breast Cancer Subtypes.

ACS applied materials & interfaces·2026

Same author

<i>Dendrobium officinale</i> polysaccharide ameliorates high-fat diet-induced hepatic lipid metabolic disorder via the SIRT6/PGC-1α signaling axis.

Frontiers in nutrition·2026

Same author

A systematic scoping review and interpretive ethical synthesis of ethical decision-making about physical restraints for older adults in Confucian-influenced care contexts.

BMC medical ethics·2026

Same author

Integrated analysis of muscle developmental features and molecular characterization of myogenic regulatory factors in two hybrid breams.

Fish physiology and biochemistry·2026

Same author

A High-Precision Screen-Printed Glucose Sensor with In Situ Impedance-Based HCT Correction and Temperature Compensation.

Biosensors·2026

Search research articles

相关实验视频

Updated: May 14, 2025

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

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

Published on: September 25, 2019

多PI-TransBTS:基于多物理信息的脑瘤图像细分的多路径学习框架.

Hongjun Zhu¹, Jiaohang Huang², Kuo Chen³

¹School of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China; Chongqing Engineering Research Center of Software Quality Assurance, Testing and Assessment, Chongqing, 400065, China; Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China.

Computers in biology and medicine

|April 11, 2025

概括

此摘要是机器生成的。

这项研究介绍了multiPI-TransBTS,这是一种用于精确脑瘤细分的新型变压器框架. 它通过整合多物理信息,显著提高了BraTS数据集的细分精度.

关键词:

大脑瘤的细分脑瘤的细分深度学习是一种深度学习.信息融合是一个信息融合.磁共振成像技术磁共振成像技术

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

相关实验视频

Last Updated: May 14, 2025

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

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

Published on: September 25, 2019

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

科学领域:

医疗成像医学成像
人工智能的人工智能
神经科学是一个神经科学.

背景情况:

脑瘤细分 (BraTS) 对于临床管理至关重要,但由于瘤异质性和MRI变异性而受到挑战.
自动化细分方法在不同的MRI模式中与不同的瘤外观,大小和强度作斗争.

研究的目的:

提出一种基于变压器的新型框架,多PI-TransBTS,以提高脑瘤细分的准确性.
利用多物理信息,包括空间,语义和多模式数据,以解决瘤异质性问题.

主要方法:

多PI-TransBTS框架使用多分支编码器进行模式特定的特征提取.
适应性特征融合 (AFF) 模块采用通道智能和元素智能注意力,以实现有效的特征重新校准.
具有任务特定特征引入 (TSFI) 的多源,多尺度解码器生成了整个瘤 (WT),瘤核心 (TC) 和增强瘤 (ET) 区域的细分.

主要成果:

与最先进的方法相比,multiPI-TransBTS在BraTS2019和BraTS2020数据集上表现出卓越的性能.
该模型实现了大脑瘤细分的改善子系数,豪斯多夫距离和灵敏度得分.
进一步的分析强调了需要平衡精度和回忆,以增强瘤 (ET) 细分.

结论:

拟议的多PI-TransBTS框架在自动化脑瘤细分方面取得了重大进展.
整合多物理信息有效地解决了脑瘤异质性带来的挑战.
这种方法有可能改善脑瘤患者管理的临床结果.