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

Organelle interactome disruption: The systemic pathological mechanisms and therapeutic prospects of mitochondria-lysosome-ER crosstalk in Alzheimer's disease.

Ageing research reviews·2026
Same author

Bifunctional Electrocatalysts with High-Entropy Alloys: Bridging Hydrogen Evolution and Oxygen Reduction.

Chemistry of materials : a publication of the American Chemical Society·2026
Same author

Regulating C-C Coupling via CO Generation and Utilization in CO<sub>2</sub>RR on Ag-Cu Catalysts.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Discovery of novel CSF1R inhibitor for triple-negative breast cancer (TNBC) treatment through TAMs reprogramming.

Biochemical pharmacology·2026
Same author

Rational Design, Synthesis, and Biological Evaluation of Potent, Highly Selective 1,2,4-Oxadiazole-Based S1PR1 Agonists for UC Treatment.

Journal of medicinal chemistry·2026
Same author

Unraveling the molecular mechanisms of smoking-associated non-small cell lung cancer: a comprehensive analysis of genetic, therapeutic, and immunological.

Journal of thoracic disease·2026

相关实验视频

Updated: Jun 21, 2025

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment &#8212; Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.3K

基准测试路径CLIP用于病理学图像分析.

Sunyi Zheng1,2, Xiaonan Cui1, Yuxuan Sun3

  • 1Tianjin's Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin, China.

Journal of imaging informatics in medicine
|July 9, 2024
PubMed
概括

专门用于病理学的CLIP (PathCLIP) 显示了强大的零射击分类,但其强度因图像损坏而异. 仔细的图像质量评估对于可靠的临床AI应用至关重要.

关键词:
深度学习是一种深度学习.基金会模型 基金会模型图像检索 图像检索 图像检索病理学 图像分析 图像分析零射击分类的分类是零射击.

更多相关视频

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma
09:52

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

140
Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.0K

相关实验视频

Last Updated: Jun 21, 2025

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment &#8212; Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.3K
DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma
09:52

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

140
Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.0K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算病理学计算病理学

背景情况:

  • 准确的图像分类和检索对于临床诊断和治疗决策至关重要.
  • 对比的语言图像预训练 (CLIP) 模型在自然图像理解方面表现出色.
  • 专门用于病理学的CLIP (PathCLIP) 利用了广泛的病理图像文本数据.

研究的目的:

  • 为了评估PathCLIP对各种图像损坏的稳定性.
  • 将PathCLIP的性能与受损条件下的OpenAI-CLIP和PLIP进行比较.
  • 评估PathCLIP在零拍摄分类和图像检索任务中的可靠性.

主要方法:

  • 在骨髓瘤和WSSS4LUAD数据集上测试了PathCLIP,其中有11种腐败类型 (例如亮度,对比度,色调,变形).
  • 对零拍摄分类和图像到图像检索的性能进行了分析.
  • 对OpenAI-CLIP和病理语言图像预训 (PLIP) 进行了比较分析.

主要成果:

  • 在零射击分类中,PathCLIP的表现优于OpenAI-CLIP和PLIP.
  • 在对比,和,不完整性和定向腐败方面,PathCLIP表现出相对稳健性.
  • 颜色,标记,变形,失焦和分辨率损坏严重影响了PathCLIP的性能.
  • 检索性能各不相同,PathCLIP在骨髓瘤上的表现低于PLIP,但在WSSS4LUAD上的表现优于PLIP.

结论:

  • PathCLIP对病理图像分析具有很强的潜力,但需要仔细考虑图像质量.
  • 图像质量保证对于AI在临床环境中可靠部署至关重要.
  • 进一步研究PathCLIP对特定腐败的抵抗力是有必要的.