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

Association of the Primary Aldosteronism Severity Classification with Lateralization and Treatment Outcomes.

The Journal of clinical endocrinology and metabolism·2026
Same author

The Limited Role of Hypocortisolism in the Development of Delayed Postoperative Hyponatremia After Pituitary Surgery.

Pituitary·2026
Same author

A foundation model of cancer genotype enables precise predictions of therapeutic response.

Cancer discovery·2026
Same author

Clinical characteristics and cardiometabolic association of non-suppressed cortisol after dexamethasone suppression test in patients with pheochromocytoma.

European journal of endocrinology·2026
Same author

Plasma proteomic profiling identifies apolipoprotein A4 as a downregulated biomarker of adrenocortical carcinoma: a multi-platform discovery and validation study.

European journal of endocrinology·2026
Same author

Reply to the Letter to the Editor: Automated deep learning model for the accurate detection and measurement of adrenal masses in contrast-enhanced abdominal CT.

European radiology·2026

相关实验视频

Updated: May 24, 2025

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

1.7K

在CT图像上检测上腺节的双阶段深度学习模型:一项回顾性研究

Chang Ho Ahn1,2, Taewoo Kim3, Kyungmin Jo3

  • 1Department of Internal Medicine, Seoul National University Hospital, Seoul National University College of Medicine, 101 Dae-hak ro, Seoul 03080, Republic of Korea.

Radiology
|March 4, 2025
PubMed
概括

一个新的深度学习模型在CT扫描上准确地检测上腺节,提高诊断能力. 这种人工智能工具显示了在临床实践中增强偶然上腺节结的检测的潜力.

更多相关视频

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.7K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.3K

相关实验视频

Last Updated: May 24, 2025

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

1.7K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.7K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.3K

科学领域:

  • 放射学 放射学是一门学科.
  • 人工智能的人工智能
  • 医疗成像医学成像

背景情况:

  • 精确检测和分类上腺节块对于有效的患者管理至关重要.
  • 在腹部成像期间经常发现偶然的上腺结节.

研究的目的:

  • 开发和验证深度学习 (DL) 模型,用于CT图像上的上腺节的自动检测和细分.
  • 评估DL模型在与人类解释相结合时模拟分类中的性能.

主要方法:

  • 一项回顾性研究,利用内部和外部数据集进行训练和测试,以测试一个两阶段DL模型 (检测和细分).
  • 模型性能评估使用接收器运行特征曲线下的面积 (AUC) 进行检测,以及对联盟 (IoU) 的交叉点进行细分.
  • 模拟分类性能通过将DL模型输出与人类解释相结合来评估.

主要成果:

  • 在内部和外部测试组中,检测右 (0.98) 和左 (0.93-0.97) 上腺节的高AUC被实现.
  • 平均0.64 (右) 和0.53 (左) 的IoU值表明了良好的细分性能.
  • 结合DL模型和人类解释显示出高灵敏度 (高达100%) 和特异性 (高达99%),分类性能在0.77到0.98.9之间.

结论:

  • 开发的深度学习模型在检测上腺节块方面表现出很高的性能.
  • 这种人工智能工具具有显著的潜力,可以提高偶然上腺节结的检测率.
  • 该模型与人类解释的整合可以提高诊断准确性和工作流效率.