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

Perivascular epithelioid cell tumours of the genitourinary tract: clinicopathological features and molecular landscape.

Histopathology·2026
Same author

Clinicopathological and molecular study of two unique cases with microglandular and acinic cell-like breast carcinoma.

Histopathology·2026
Same author

Development and Internal Validation of a Side-Specific Nomogram Integrating mpMRI and Biopsy Features to Guide Nerve-Sparing Decision Making in Prostate Cancer with Capsular Contact.

Cancers·2026
Same author

Very Late Extramedullary Relapse of Acute Myeloid Leukemia 13 Years After Allogeneic Transplant: A Case Report.

Case reports in hematology·2026
Same author

Erythema nodosum-like panniculitis during BRAF inhibitor therapy for melanoma: never forget latent tuberculosis infection.

Dermatology reports·2026
Same author

Updates and controversies in contemporary grading of clear cell renal cell carcinoma and papillary renal cell carcinoma.

Histopathology·2026

相关实验视频

Updated: Jan 15, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

800

类似病理学家的可解释AI用于前列腺癌中可解释的格里森分级.

Gesa Mittmann1,2, Sara Laiouar-Pedari1, Hendrik A Mehrtens1

  • 1Division of Digital Prevention, Diagnostics and Therapy Guidance, German Cancer Research Center (DKFZ), Heidelberg, Germany.

Nature communications
|October 8, 2025
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种可解释的前列腺癌分级人工智能,提高了格里森得分预测准确度. 人工智能使用病理学家定义的术语和软标签进行强大的细分,帮助临床决策.

更多相关视频

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

1.1K
Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking
07:34

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking

Published on: November 17, 2023

1.1K

相关实验视频

Last Updated: Jan 15, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

800
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

1.1K
Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking
07:34

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking

Published on: November 17, 2023

1.1K

科学领域:

  • 数字病理学数字病理学
  • 医学中的人工智能
  • 计算病理学计算病理学

背景情况:

  • 前列腺癌的攻击性是由基因病理学的格里森评分系统决定的.
  • 目前用于格里森评分的AI模型缺乏可解释性,阻碍了临床采用.
  • 在病理学家之间,格里森评分存在很高的观察者间变异性.

研究的目的:

  • 开发一种内在可解释的AI模型,用于前列腺癌中的格里森模式细分.
  • 提高人工智能驱动的遗传病理学分析的稳定性和可解释性.
  • 为了应对医学图像细分中的观察者间变异性的挑战.

主要方法:

  • 在1015张前列腺组织微阵列核心图像上训练了一个AI模型.
  • 利用了54名国际病理学家注释的详细模式描述.
  • 采用病理学家定义的术语和软标签来管理数据不确定性.

主要成果:

  • 实现了强大的格里森模式细分,与直接细分方法相比 (子得分:0.713 ± 0.003).
  • 人工智能模型提供了可解释的输出,增强了临床信任.
  • 与传统方法相比,在细分精度方面表现优越.

结论:

  • 一种本质上可以解释的AI方法可以有效地对格里森模式进行细分,尽管观察者之间的变异性很高.
  • 这种方法为传统人工智能提供了一个有希望的替代方案,提高了临床接受度.
  • 发布的数据集将促进主观医学图像细分和病理学家推理方面的研究.