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

Undertraining is the floor, not the ceiling: when statistical and validation failures compound in radiomics.

European radiology·2026
Same author

Zero-shot performance of a general-purpose vision-language model for pediatric appendicitis diagnosis.

Pediatric radiology·2026
Same author

Radiation dose and objective image quality of photon-counting detector computed tomography in pediatric imaging: a systematic review and meta-analysis.

Pediatric radiology·2026
Same author

Glass-box agentic-style workflow for multiclass cine cardiac magnetic resonance imaging classification with a large language model.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Externally validated yet undertrained: sample size deficits in machine learning-based radiomics.

European radiology·2026
Same author

Reporting checklist for foundation and large language models in medical research (REFINE): an international consensus guideline.

Diagnostic and interventional radiology (Ankara, Turkey)·2026

相关实验视频

Updated: Jul 7, 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

1.9K

用ChatGPT辅助的深度学习模型进行甲状腺结节分析:超越人工智能.

Ismail Mese1, Neslihan Gokmen Inan2, Ozan Kocadagli2

  • 1Department of Radiology, Health Sciences University, Erenkoy Mental Health and Neurology Training and Research Hospital. ismail_mese@yahoo.com.

Medical ultrasonography
|December 27, 2023
PubMed
概括

这项研究开发了一个使用ChatGPT的AI模型来分析甲状腺超声波图像以诊断结节. 该模型实现了高精度,显示了提高甲状腺病理学诊断能力的前景.

更多相关视频

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

632
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

1.9K

相关实验视频

Last Updated: Jul 7, 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

1.9K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

632
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

1.9K

科学领域:

  • 人工智能在医学中的应用
  • 医学成像分析 医学成像分析
  • 深度学习用于诊断.

背景情况:

  • 甲状腺结节需要准确的诊断,通常依赖于细针吸收活检 (FNAB) 细胞病理学.
  • 深度学习模型为医疗图像的自动分析提供了潜力,包括甲状腺超声波.
  • 整合像ChatGPT这样的AI工具可以简化这些复杂模型的开发.

研究的目的:

  • 开发一种深度学习模型,使用超声波图像对甲状腺结节进行分类.
  • 为了利用ChatGPT在AI模型开发中的能力,用于医学图像分析.
  • 为了建立一个基线使用FNAB细胞病理学模型验证.

主要方法:

  • 对1,061名患者甲状腺超声波图像和FNAB结果 (2017-2022) 的回顾性分析.
  • 在成像特征和细胞学特征上训练深度学习模型,以识别甲状腺病理.
  • 使用ChatGPT进行AI模型开发,包括编码,预处理,优化和故障排除.

主要成果:

  • 深度学习模型在测试组中实现了0.81 (95% CI:0.76-0.87) 的准确性.
  • 在对良性结节 (F1分数:0.86) 和恶性结节 (F1分数:0.87) 的分类中观察到高性能.
  • 该模型在不同类别的甲状腺结节中表现出强大的精度和回忆.

结论:

  • 人工智能,特别是在ChatGPT的协助下,显示出在开发医疗图像分析强大的深度学习模型方面具有重大潜力.
  • 这种方法可以提高诊断甲状腺结节的准确性和效率.
  • 进一步的研究可以探索AI在诊断成像中的更广泛应用.