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

Ultrasound II: Endoscopic Ultrasound and FibroScan01:25

Ultrasound II: Endoscopic Ultrasound and FibroScan

879
Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):
879

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

Pre-existing intracranial arterial stenosis independently predicts delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage.

Neuroradiology·2026
Same author

Beyond Coiling: A Comparative Analysis of Survey-Reported Preferences for Endovascular Cerebral Aneurysm Occlusion.

Clinics and practice·2026
Same author

Three and a Half Decades of Pediatric Heart Transplantation: Evolution of Surgical Practice and Outcomes at a High-Volume Centre.

Journal of cardiovascular development and disease·2026
Same author

GreenAid: a confidence-weighted ensemble deep learning system for real-time plant disease detection and management.

Scientific reports·2026
Same author

De Novo Genome Assemblies of Four Rainbow Trout Genetic Lines Reveal Structural Variants in Pursuit of a Pangenome Reference.

Molecular ecology resources·2026
Same author

Effect of Cusp-Overlap View Technique on the Occurrence of Post-Procedural New Conduction Disturbance and Permanent Pacemaker Implantation Following Transcatheter Aortic Valve Replacement Using Self-Expanding Prostheses.

Journal of clinical medicine·2026

相关实验视频

Updated: Feb 28, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K

FibroidX:视觉变压器驱动的预后和子宫纤维瘤的复发预测使用超声波图像.

Fatma M Talaat1, Yathreb Bayan Mohamed2, Amira Abdulrahman1

  • 1Faculty of Artificial Intelligence, Kafr Elsheikh University, Kafr Elsheikh 33516, Egypt.

Cancers
|February 27, 2026
PubMed
概括

这项研究介绍了FibroidX,这是一种用于预测子宫纤维瘤 (UF) 预后和复发的AI工具. 与传统方法相比,FibroidX显著提高了准确性,为更好的女性提供了个性化的风险评估.

关键词:
可解释的人工智能药理疗法是一种药理疗法.复发预测的复发预测的子宫纤维化组织.

更多相关视频

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions
10:21

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions

Published on: March 3, 2023

2.4K
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

8.9K

相关实验视频

Last Updated: Feb 28, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K
A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions
10:21

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions

Published on: March 3, 2023

2.4K
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

8.9K

科学领域:

  • 妇科成像分析分析 妇科成像分析
  • 医疗保健中的人工智能
  • 机器学习用于疾病预测和预测.

背景情况:

  • 子宫纤维瘤 (UFs) 显著影响女性的生殖健康和生活质量.
  • 准确的预后和UF的复发预测对于个性化治疗和减少长期后果至关重要.
  • 使用成像和统计模型的传统预测方法往往缺乏准确性和客观性.

研究的目的:

  • 推出FibroidX,一个人工智能驱动的系统,用于增强子宫纤维瘤预后和复发预测.
  • 通过自动化特征提取和提供定制的风险评估,克服传统方法的局限性.
  • 提高预测UF疾病进展,症状严重程度,治疗反应和治疗后复发的准确性和可靠性.

主要方法:

  • 在FibroidX模型中使用视觉转换器和自我注意力机制.
  • 在1990年的超声波图像数据集上训练模型,分为80%的训练和20%的测试集.
  • 使用包括准确性,精度,回忆,F1得分和AUC-ROC在内的指标评估模型性能.

主要成果:

  • FibroidX实现了98.4%的高精度,超过了基线模型 (92.3%和94.1%).
  • 在精度 (97.8%),回忆 (96.9%) 和F1得分97.3%方面表现出强的表现.
  • 获得了0.99的AUC-ROC得分,这表明了出色的阶级区别.

结论:

  • 对于UF预测任务,FibroidX是有效和可靠的,适合实时应用,平均推断时间为0.02s.
  • 与传统的机器学习技术相比,人工智能模型的准确性增加了15%,假阳性率减少了12%.
  • FibroidX在个性化评估子宫纤维瘤风险方面取得了重大进展.