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

Homologous recombination is essential for DNA damage-induced regeneration of Drosophila testis germline stem cells.

Development (Cambridge, England)·2026
Same author

The AI-native health science institution innovation theater vs. structural redesign.

npj health systems·2026
Same author

Sex Differences in the Protective Effect of Brain Volume: Age Attenuates Protection in Women.

Stroke (Hoboken, N.J.)·2026
Same author

Allergic Fungal Rhinosinusitis: Distinct Clinical Features, Diagnostic Challenges, and Evolving Therapeutic Strategies.

The journal of allergy and clinical immunology. In practice·2026
Same author

The Impact of Robot-Assisted Electrode Insertion on Cochlear Implant Surgery Time: A Retrospective Study.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026
Same author

Trends in Otolaryngology Match Dynamics Before and After the USMLE Step 1 Pass/Fail Transition.

Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery·2026

相关实验视频

Updated: Jun 4, 2025

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

使用机器学习预测鼻腔逆向乳头瘤的附着:当前的教训和未来的方向.

Sean P McKee1, Xiaomin Liang2, William C Yao3

  • 1Department of Otolaryngology, Massachusetts Eye & Ear Infimary, Boston, MA, USA.

American journal of otolaryngology
|December 31, 2024
PubMed
概括

开发了一种机器学习模型,用于在CT扫描上识别反向乳头瘤 (IP) 附着部位. 虽然在某些情况下取得了成功,但该模型需要更多的数据才能可靠地在临床上使用.

关键词:
人工智能的人工智能是人工智能.逆向乳头瘤的发生机器学习 机器学习无线电学 (Radiomics) 是一种无线电学.瘤是一个瘤.

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Identification of OTX1 and OTX2 As Two Possible Molecular Markers for Sinonasal Carcinomas and Olfactory Neuroblastomas
07:00

Identification of OTX1 and OTX2 As Two Possible Molecular Markers for Sinonasal Carcinomas and Olfactory Neuroblastomas

Published on: February 28, 2019

5.8K

相关实验视频

Last Updated: Jun 4, 2025

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
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Identification of OTX1 and OTX2 As Two Possible Molecular Markers for Sinonasal Carcinomas and Olfactory Neuroblastomas
07:00

Identification of OTX1 and OTX2 As Two Possible Molecular Markers for Sinonasal Carcinomas and Olfactory Neuroblastomas

Published on: February 28, 2019

5.8K

科学领域:

  • 放射学 放射学是一门学科.
  • 人工智能的人工智能
  • 在瘤学瘤学.

背景情况:

  • 倒置乳头瘤 (IP) 在CT扫描上经常与高静止症有关.
  • 确定IP瘤的起源和附着部位对于手术规划至关重要.
  • 计算机断层扫描 (CT) 是评估IP的关键成像方式.

研究的目的:

  • 开发和评估一种机器学习 (ML) 模型,用于识别CT图像上的IP附件位置.
  • 在此任务中评估深度学习细分算法 (nnU-Net) 的性能.
  • 确定影响模型准确性的因素.

主要方法:

  • 在该机构接受治疗的58名IP患者的回顾性审查.
  • 在手术外科医生的CT扫描上手动细分瘤附着部位.
  • 应用nnU-Net模型用于IP连接站点的自动识别和细分.
  • 使用5倍交叉验证和索伦森-迪斯系数进行评估.

主要成果:

  • 在55.2%的患者中,ML算法确定了IP附着部位.
  • 平均子得分为0.34 (+/- 0.24),表明细分表现适度.
  • 该模型在上鼻附着部位 (OR 4.6) 的表现更好,在修复手术 (OR 0.11) 中表现更差.

结论:

  • 一个最先进的ML模型证明了识别IP附加站点的能力.
  • 该模型在某些特定情况下显示出高准确性,特别是在上鼻起源方面.
  • 为了可靠的临床整合这种ML工具,需要更大,更多样化的数据集.