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 multimodal deep learning classifier for prediction of HER2-low expression in triple-negative breast cancer.

BMC medical imaging·2026

Same author

Graph Network Feature Space Fusion for Predicting Irregularly Sampled Medical Time-Series Data: Deep Learning Model Development and Validation Study.

JMIR medical informatics·2026

Same author

OrdPrune-KD: An Ordinal-Consistency-Based Model Compression Framework for Diabetic Retinopathy Grading.

Sensors (Basel, Switzerland)·2026

Same author

Quantitative Assessment of Brain Glucose Metabolism Using Dynamic Glucose-Enhanced Magnetic Resonance Fingerprinting (DGE-MRF).

Chemical & biomedical imaging·2026

Same author

HiCAF-Net: A Hierarchical Cross-Attention Fusion framework for cross-cancer subtype classification using histopathological and genomic data.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same author

A Multimodal Deep Learning Model for Objective Identification of Sub-health Status in Traditional Chinese Medicine.

Combinatorial chemistry & high throughput screening·2026

Search research articles

相关实验视频

Updated: Jul 2, 2025

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

运动工件增强的伪标签网络,用于半监督的大脑瘤细分.

Guangcan Qu¹, Beichen Lu¹, Jialin Shi¹

¹School of the 1st Clinical Medical Sciences (School of Information and Engineering), Wenzhou Medical University, Wenzhou 325000, People's Republic of China.

Physics in medicine and biology

|February 26, 2024

概括

这项研究引入了一种新的半监督学习方法,用于使用运动工件增强来对脑瘤进行细分. 拟议的方法,MAPSS,提高了有限的标记数据的准确性,并提高了对图像工件的稳定性.

关键词:

大脑瘤是什么?医疗图像细分医疗图像细分强度坚固性坚固性半监督学习半监督学习

更多相关视频

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

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

相关实验视频

Last Updated: Jul 2, 2025

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

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

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

科学领域:

医学成像分析医学成像分析
医疗保健中的人工智能
神经瘤学成像学成像学

背景情况:

准确的MRI图像细分对于脑瘤诊断和治疗计划至关重要.
完全监督的方法面临由于高的注释成本和有限的数据集的限制.
像噪音和运动工件这样的图像质量问题阻碍了细分性能.

研究的目的:

开发一种自动化,准确和强大的脑瘤细分方法.
为了应对医疗图像细分中的有限的标记数据和运动工件的挑战.
为了减少临床医生在脑瘤诊断中的工作量.

主要方法:

拟议的MAPSS (运动文物增强伪标签网络) 用于半监督的细分.
组合运动工件数据增强与伪标签训练框架.
在BraTS2020数据集上进行了针对脑瘤细分的实验.

主要成果:

MAPSS通过最小的标记数据实现了精确的脑瘤细分.
该方法在MRI图像中证明了对MRI图像中的运动工件的稳定性.
在左心室数据集上评估了概括性能.

结论:

在半监督脑瘤细分方面,MAPSS提供了显著的进步.
该方法有效地处理有限的数据和图像工件,提高临床效用.
这种方法在帮助治疗规划和提高患者护理质量方面具有很大的潜力.