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

Ultra-Wide-Field Optical Coherence Tomography Assessment of Choroidal Parameters in Central Serous Chorioretinopathy.

Diagnostics (Basel, Switzerland)·2026
Same author

Assessment of Dietary Nutritional Profile in Turkish Patients with Age-Related Macular Degeneration.

Turkish journal of ophthalmology·2026
Same author

Refractive and Visual Outcomes in Unilateral Duane Retraction Syndrome: Influence of Ocular Motility.

Turkish journal of ophthalmology·2026
Same author

Comparative analysis of GPT-4o as a representative multimodal large language model and human fitters in orthokeratology lens fitting: Assessing accuracy, efficiency and cost-effectiveness in initial lens parameter selection.

Acta ophthalmologica·2026
Same author

Early detection of tamoxifen-induced retinal injury: ellipsoid zone reflectivity as a sensitive structural marker.

BMC ophthalmology·2026
Same author

Animal models in human ophthalmology: new insights from birds' research.

Eye (London, England)·2026

相关实验视频

Updated: May 10, 2025

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model
07:40

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Published on: January 12, 2022

4.6K

将自动机器学习与专家设计的模型进行比较,用于诊断瘤界面障碍.

Ceren Durmaz Engin1,2, Mahmut Ozan Gokkan2, Seher Koksaldi3

  • 1Department of Ophthalmology, Izmir Democracy University Buca Seyfi Demirsoy Education and Research Hospital, Izmir 35390, Turkey.

Journal of clinical medicine
|April 26, 2025
PubMed
概括

一个专家设计的深度学习模型在从OCT图像中分类玻璃细胞界面障碍方面超过了AutoML,在特定条件 (如斑点孔) 中实现了更高的准确性.

关键词:
在AutoML中使用AutoML.有效网 B0 有效网这就是ResNet-50的特点.深度学习是一种深度学习.光学连贯性断层扫描 (optical coherence tomography) 是一种光学连贯性断层扫描技术.玻璃眼界面疾病 玻璃眼界面疾病

更多相关视频

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.3K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

205

相关实验视频

Last Updated: May 10, 2025

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model
07:40

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Published on: January 12, 2022

4.6K
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.3K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

205

科学领域:

  • 眼科医生 眼科 眼科
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 玻璃瘤接口 (VMI) 障碍显著影响视力,需要精确的分类.
  • 准确诊断VMI疾病对于有效的患者管理至关重要.
  • 光学连贯断层扫描 (OCT) 是VMI评估的关键成像方式.

研究的目的:

  • 将自定义深度学习 (DL) 模型的诊断性能与自动机器学习 (AutoML) 模型进行比较.
  • 评估这些人工智能模型在使用OCT图像对各种VMI疾病的分类方面的有效性.
  • 在临床环境中确定专家设计的AI与自动化AI的优越性.

主要方法:

  • 一个平衡的OCT图像数据集被策划,包括正常病例和五个VMI障碍类别:表皮膜 (ERM),异常全厚黄斑孔 (FTMH),状黄斑孔 (LMH) 和玻璃引力 (VMT).
  • 一个专家设计的DL模型集成ResNet-50和EfficientNet-B0架构与蒙特卡洛交叉验证.
  • 在Google Vertex AI上实现了一个无代码的AutoML模型,用于自动化数据处理,模型选择和超参数调整.

主要成果:

  • 专家设计的DL模型实现了95.97%的平衡精度和94.65%的MCC,在分类FTMH,ERM和LMH方面表现优于AutoML.
  • 两种模型都表现出完美的精度和回忆正常的OCT图像.
  • 自动ML在VMT检测方面表现强 (99.5%的精度),但在LMH分类方面落后 (72.3%的精度).

结论:

  • 与当前的AutoML平台相比,专家设计的深度学习模型在特定的玻璃瘤界面障碍分类方面表现出卓越的准确性.
  • 虽然AutoML为医疗保健专业人员提供了可访问性,但需要进一步的进展,以匹配专家驱动的AI性能在临床OCT图像分析中.
  • 这些发现突出了定制AI解决方案的潜力,以提高视网膜疾病的诊断准确度.