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

Immunomodulatory Food Processing Compounds: Mechanisms in Food Allergic Sensitization and Future Safety Paradigms.

Journal of agricultural and food chemistry·2026

Same author

RAD51-targeting small molecule degrader sensitizes <i>BRCA</i>-proficient prostate cancer cells to PARP inhibitors <i>via</i> synthetic lethality.

Acta pharmaceutica Sinica. B·2026

Same author

Pan-Cancer Prognostic Analysis of NMDAR Genes Discovered Therapeutic Implications of Neuronal-Cancer Crosstalk Mediator GRIN2A for Small Cell Lung Cancer.

Biomedicines·2026

Same author

Hierarchical Semantic Concept Modeling for Generalizable Myocardial Pathology Segmentation on Multisequence CMR Images.

IEEE transactions on neural networks and learning systems·2026

Same author

Targeting the mevalonate pathway with statins overcomes acquired resistance to KRAS<sup>G12C</sup> inhibitors in non-small cell lung cancer.

Experimental hematology & oncology·2026

Same author

Large thermoelectric effect driven by high-order anharmonicity from synergistic lone-pair electrons and rattling modes in K<sub>3</sub>Au<sub>3</sub>Sb<sub>2</sub>.

Physical chemistry chemical physics : PCCP·2026

Search research articles

相关实验视频

Updated: Jul 23, 2025

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

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

Published on: November 30, 2022

BayeSeg:贝叶斯对医疗图像细分的建模,具有可解释的概括性.

Shangqi Gao¹, Hangqi Zhou¹, Yibo Gao¹

¹School of Data Science, Fudan University, Shanghai, 200433, China.

Medical image analysis

|July 19, 2023

概括

本研究介绍了BayeSeg,这是一个可解释的贝叶斯框架,用于医学图像细分. BayeSeg通过建模域稳定的形状和外观,增强跨多种成像系统的模型通用性,改善未见数据的性能.

关键词:

图像细分图像细分图像细分解释和概括的解释.统计建模统计建模变量贝叶斯是变量的贝叶斯.

更多相关视频

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

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

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

Published on: January 7, 2019

相关实验视频

Last Updated: Jul 23, 2025

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

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

Published on: November 30, 2022

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

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

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

Published on: January 7, 2019

科学领域:

医疗图像分析医学图像分析
深度学习是一种深度学习.
计算机成像成像技术

背景情况:

深度学习细分方法在医学成像中与跨域分布转移作斗争.
现有的域泛化技术缺乏可解释性.
当前方法在现实世界中的适用性受到未见数据表现不佳的限制.

研究的目的:

提出一个可解释的贝叶斯框架 (BayeSeg),以提高医疗图像细分的普遍性.
为解决域不变特征提取中可解释性的挑战.
提高深度学习模型在各种医学成像场景中的可靠性和适用性.

主要方法:

开发了一个贝叶斯框架 (BayeSeg),使用贝叶斯对图像和标签统计的建模.
将图像分解为空间相关 (形状) 和空间变量 (外观) 变量,并具有层次化的贝叶斯先验.
模拟细分作为与形状相关的局部光滑变量,并使用变量贝叶斯框架进行推理.

主要成果:

通过定量和定性结果证明了BayeSeg在前列腺和心脏细分任务上的有效性.
通过解释推断后分布来验证框架的可解释性.
通过废除研究确定了影响概括能力的因素.

结论:

BayeSeg提供了一种可解释的方法,以提高医疗图像细分的概括性.
拟议的框架通过分离形状和外观建模,有效地处理域名转移.
该方法显示了在医疗成像中提高深度学习的稳定性和适用性的巨大潜力.