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

Pubertal exposure to low doses of zearalenone disrupting spermatogenesis through ERα related genetic and epigenetic pathways.

Toxicology letters·2019

Same author

The role of sulfate and its corresponding S(IV)+NO<sub>2</sub> formation pathway during the evolution of haze in Beijing.

The Science of the total environment·2019

Same author

Hydrologic alteration and possible underlying causes in the Wuding River, China.

The Science of the total environment·2019

Same author

In vivo imaging reveals transient microglia recruitment and functional recovery of photoreceptor signaling after injury.

Proceedings of the National Academy of Sciences of the United States of America·2019

Same author

Investigation of Acoustic Injection on the MPU6050 Accelerometer.

Sensors (Basel, Switzerland)·2019

Same author

An Easily Available Ratiometric Reaction-Based AIE Probe for Carbon Monoxide Light-up Imaging.

Analytical chemistry·2019

Search research articles

相关实验视频

Updated: Jun 18, 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

形状预先受限的深度学习网络用于医疗图像细分.

Pengfei Zhang¹, Yuanzhi Cheng², Shinichi Tamura³

¹School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China.

Computers in biology and medicine

|July 30, 2024

概括

此摘要是机器生成的。

这项研究引入了一种新的医疗图像细分网络,该网络集成形状先验和多尺度特征. 这种方法提高了对具有挑战性的细分的准确性,在基准数据集上实现了最高性能.

关键词:

循环协作框架循环协作框架有合作效应的合作效应.医疗图像细分医疗图像细分多尺度的特点是核聚变.之前的形状之前的形状

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

相关实验视频

Last Updated: Jun 18, 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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
人工智能的人工智能

背景情况:

医学图像细分对于诊断和治疗计划至关重要.
挑战包括低对比度,相似的器官强度和解剖学变异.
现有的方法难以处理复杂的细分任务.

研究的目的:

为医疗图像开发一个先进的细分网络.
通过结合形状先验和多尺度特征来提高细分精度.
为了解决当前细分技术的局限性.

主要方法:

一个新的培训框架,具有形状先前约束和多尺度特征融合模块.
在细分神经网络中嵌入一个形状先前学习模型.
在测试期间结合形状生成器和细分网络的循环协作框架.

主要成果:

提出的方法在ACDC MICCAI'17挑战数据集上在子分数中获得了第1名.
在COVID-19CT肺部和LiTS2017肝脏细分数据集上表现出高度竞争力的性能.
成功解决了低对比度和解剖学变异性的问题.

结论:

形状先前表示受限制的多尺度特征融合网络提供了卓越的医疗图像细分.
提出的培训和测试策略有效地提高了细分精度.
这种方法显示出临床应用的巨大潜力.