深度学习歧视胸膜上皮瘤 组织学亚型 使用数字病理学
Matteo Sacco1, Erica Pietroluongo2, Anna Di Lello1
1Department of Medicine, Section of Hematology/Oncology, University of Chicago, Chicago, IL, USA.
概括
一个新的深度学习模型准确地分类胸膜上皮瘤 (TETs),提高诊断一致性. 这种人工智能工具对胸膜癌的检测具有很高的准确性,有助于病理学家在临床决策中做出决定.
科学领域:
- 计算病理学计算病理学
- 人工智能在瘤学中的应用
- 组织病理学图像分析分析.
背景情况:
- 胸膜上皮瘤 (TETs) 由于组织学异质性和观察者间的变异性而存在诊断挑战.
- 目前世界卫生组织 (WHO) 的分类显示出低于最佳的一致性,高达57%的病例在审查时被重新分类.
- 深度学习提供了一种潜在的解决方案,可以减少诊断变化,提高分类一致性.
研究的目的:
- 开发和验证一个深度学习模型来分类胸膜上皮瘤 (TETs).
- 通过临床相关的等级体系和标准的六类世卫组织分类来评估模型的性能.
- 评估该模型在病理学环境中提高诊断一致性的潜力.
主要方法:
- 一个深度学习模型被训练在整个幻灯片图像从癌症基因组图谱使用血素和素 (H&E) 染色.
- 整合了一种新的等级损失函数,以与临床瘤分组和患者结果保持一致.
- 模型的性能在芝加哥大学的112个病例中得到验证,与专家胸腔病理学家的诊断进行了比较.
主要成果:
- 该模型在三组层次分类中 (As,Bs,胸膜癌) 实现了91.1%的准确性 (κ=0.859).
- 在世卫组织六类分类中,准确率为77.7% (κ=0.716).
- 该模型显示了100%的灵敏度和94.6%的精度用于胸腺癌检测,大多数错误分类不会影响临床管理.
结论:
- 深度学习模型显示出作为TET分类的诊断辅助的巨大潜力,尤其是在胸腔病理学专业知识有限的地方.
- 对胸膜癌的高灵敏度和强大的性能表明,它可用于提高诊断一致性的临床应用.
- 该工具可以在专业和一般环境中支持病态决策.
关键词:
支持决定的决定支持.深度学习是一种深度学习.数字病理学数字病理学外部验证的验证方法层次上的损失.历史学分类 历史学分类观察者之间的可变性.胸腺癌 (thymic carcinoma) 是一种癌症.胸膜上皮瘤 胸膜上皮瘤胸腺瘤是什么 胸腺瘤是什么整个幻灯片图像的图像.更多相关视频
13:01Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
Published on: June 3, 2022
4.4K
08:16X-ray Visualization of Intraductal Ethanol-based Ablative Infusion for Prevention of Breast Cancer in Rabbit Models
Published on: September 12, 2025
791
相关概念视频
Classification of Epithelial Tissues: Overview
19.5K
Epithelial tissues are classified according to the shape of the cells and the number of cell layers formed. Cell shapes can be squamous (flattened and thin), cuboidal (square-like, as wide as it is tall), or columnar (rectangular, taller than it is wide). Additionally, the nucleus shape helps identify the type of epithelial cells. Squamous cells have flattened disc-shaped nuclei, cuboidal cells have spherical nuclei, and columnar cells have elongated nuclei.
Based on the number of cell layers,...
Based on the number of cell layers,...
19.5K
Classification of Epithelial Tissues: Glandular Epithelium
11.6K
The glandular epithelium is made of one or more epithelial cells modified to synthesize and secrete chemical substances. Glandular epithelia can be classified based on cell number. Unicellular glands have individual secretory cells scattered across the epithelial monolayer. In contrast, multicellular glands consist of a hollow tubular duct attached to the cluster of secretory cells located in the deep pockets.
Multicellular glands are formed during early development when epithelial budding...
Multicellular glands are formed during early development when epithelial budding...
11.6K
