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

Rhein-Mn coordination nanomedicine for peritoneal metastatic colorectal cancer: synergistic mitochondrial targeting, immunogenic cell death, and reverses immunosuppression.

Journal of nanobiotechnology·2026

Same author

Gannan rare earth elements cohort: study design, methods, and baseline characteristics of the cohort.

BMC public health·2025

Same author

M<sup>6</sup>A-methylated MUC1 drives silica-induced lung inflammation and fibrosis.

Ecotoxicology and environmental safety·2025

Same author

Acrylonitrile exposure incurs lung function decline: Insights from lifestyle intervention and mechanistic pathway in an urban prospective cohort.

Environmental research·2025

Same author

Arsenic exposure, arsenic metabolism, and plasma lipidome in relation to type 2 diabetes and glycemic traits: a lipidome-wide association study.

Journal of advanced research·2025

Same author

[Retracted] Downregulation of Bmi‑1 is associated with suppressed tumorigenesis and induced apoptosis in CD44<sup>+</sup> nasopharyngeal carcinoma cancer stem‑like cells.

Oncology reports·2025

Search research articles

相关实验视频

Updated: Jul 16, 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

半TMS:一个高效的规范化导向的三人教师半监督的医疗图像细分模型.

Weihong Chen¹, Shangbo Zhou¹, Xiaojuan Liu²

¹College of Computer Science, Chongqing University, Chongqing 400044, People's Republic of China.

Physics in medicine and biology

|September 12, 2023

概括

本研究介绍了Semi-TMS,这是一种用于医疗图像细分的新型半监督学习方法,它使用三个教师模型来提高有限的标记数据的准确性. 它通过交叉学习和多尺度一致性利用未标记的数据来提高细分性能.

关键词:

图像细分图像细分多尺度一致性的一致性半监督学习半监督学习形状形状感知感知变压器的变压器是一个变压器.

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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

相关实验视频

Last Updated: Jul 16, 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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

科学领域:

医学图像分析医学图像分析
医疗保健中的人工智能
计算机视觉计算机视觉

背景情况:

医学图像细分对于诊断至关重要,但需要广泛的标记数据.
卷积神经网络 (CNN) 和变压器需要大量的数据集,这些数据集的注释是昂贵和耗时的.
半监督学习提供了一个解决方案,利用有限的标记数据与丰富的未标记数据.

研究的目的:

通过一种新的半监督方法来提高医疗图像细分性能.
通过三重教师交叉学习框架,有效地利用未标记的数据.
整合形状感知和多尺度一致性规范化,以提高准确性.

主要方法:

拟议的半TMS:一个多尺度的半监督方法,有三个教师的交叉学习和形状感知.
使用混合模型架构,有两个CNN教师 (A,C) 和一个变压器教师 (B).
实现了CNN和Transformer之间的交叉学习,包括形状感知和多尺度一致性规范化.

主要成果:

拟议的半TMS方法在公共数据集上优于现有的半监督细分模型.
通过多尺度一致性,证明有效利用和提高未标记数据的准确性.
隐式捕获的形状信息,提高了细分的稳定性.

结论:

半TMS有效地提高医疗图像细分精度,使用有限的标记数据.
该方法显示了在临床诊断和研究中实际应用的潜力.
它为使用医学成像的临床医生和研究人员提供了宝贵的辅助工具.