Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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

The impact of dietary patterns on the risk of asthma in children.

Allergy and asthma proceedings·2026
Same author

Flow-assembled Janus catalyst arrays for low-energy-barrier cascade dechlorination and mineralization of chlorinated organic compounds in water.

Journal of hazardous materials·2026
Same author

A Case of Short-Rib Thoracic Dysplasia: Diagnostic Clues in Early Pregnancy and Genetic Analysis.

Journal of clinical ultrasound : JCU·2026
Same author

Remote ischemic preconditioning for prevention of contrast-induced acute kidney injury in chronic kidney disease patients undergoing percutaneous vascular interventions: a systematic review and meta-analysis of randomized trials.

BMC nephrology·2026
Same author

PhenoRareAI: Phenotype-based intelligent diagnosis for rare neuromuscular disorders of glycogen storage disease and spinal muscular atrophy.

Health information science and systems·2026
Same author

A host-based antifouling gold nanotube sensor for the selective detection of mechanically sensitive serotonin release in intestinal mucosa.

Science bulletin·2026

相关实验视频

Updated: Jun 1, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.6K

使用编码器-解码器架构模型从骨光学图片进行转移病变细分,采用多重注意力和多尺度学习.

Ailing Xie1,2, Qiang Lin1,2,3, Yang He2,3

  • 1School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, China.

Quantitative imaging in medicine and surgery
|January 22, 2025
PubMed
概括

这项研究引入了一种深度学习模型,用于在光学扫描上对骨转移 (BM) 进行细分. 该模型通过自动识别病变来提高诊断准确性,优于现有方法.

关键词:
瘤发生骨转移.骨头光学图片 骨头光学图片损伤细分 损伤细分多重注意力模式多尺度的特征学习是多尺度的特征学习.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

364

相关实验视频

Last Updated: Jun 1, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

364

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 在瘤学瘤学.

背景情况:

  • 骨扫描在诊断骨转移 (BM) 方面面临挑战,原因是分辨率限制和病变变化.
  • 深度学习为识别和划分BM病变提供了自动化解决方案,提高了诊断准确度.

研究的目的:

  • 开发一种基于深度学习的方法来自动细分骨scintigrams.
  • 通过自动化病变细分,提高诊断骨转移 (BM) 的准确性.

主要方法:

  • 为细分开发了一个编码器-解码器深度学习模型.
  • 采用了多注意力学习 (非局部注意力,视觉转换器) 和多规模学习策略.
  • 该模型旨在增强骨对比度,并突出显示热点,以准确检测病变.

主要成果:

  • 拟议的模型在SPECT骨头光图上实现了0.6720的子相似系数 (DSC).
  • 与现有模型相比,拟议的方法在DSC中显示了5.6%的改进,在精度中为2.03%,在回忆中为7.9%.

结论:

  • 开发的细分模型是一个有前途的工具,可以自动从SPECT骨scintigram中提取转移病变.
  • 这种方法支持深度学习的进步,用于自动表征骨转移 (BM).