对于卵巢癌组织学图像的域-通用分类的强大框架
1School of Computer Science, China West Normal University, Nanchong 637009, China.
Diagnostics (Basel, Switzerland)
|December 11, 2025
概括
本研究介绍了WSI-P2P,这是一个计算病理学框架,使用缩小的补丁采样和多实例学习 (MIL) 来进行高效的全幻灯片图像分析. 在K-TOP MIL聚合器显著提高了准确性和计算效率强大的组织学研究.
科学领域:
- 计算病理学计算病理学
- 数字病理学数字病理学
- 机器学习在组织学中的应用
背景情况:
- 计算病理 (CP) 分析要求高计算效率和准确的分类可扩展的解决方案.
- 整个幻灯片图像 (WSIs) 存在异质性挑战,阻碍了深度学习模型中强大的概括.
- 现有的深度学习框架在WSIs中与域变化作斗争.
研究的目的:
- 介绍WSI-P2P (全幻灯片成像-补丁预测),一个新的框架解决计算效率和概括在WSI分析.
- 引入K-TOP MIL聚合器,用于选择性处理信息实例.
- 开发一种适应性特征提取器,用于处理多中心数据集的变化.
主要方法:
- 利用缩小的补丁采样和多实例学习 (MIL) 与转移学习.
- 介绍了K-TOP MIL聚合器,这是基于注意力的MIL的一个变体,可以处理K顶级最有信息的实例.
- 具有在线,自适应的特征提取器,用于预训练模型的端到端微调.
主要成果:
- WSI-P2P实现了最先进的准确性,展示了卓越的域名适应性和计算效率.
- K-TOP MIL聚合器提高了性能,达到大约100%的AUROC和95.72%的测试准确度.
- 与基础聚合器相比,K-TOP MIL聚合器显示了2.3倍的计算效率,在各个领域的性能一致.
结论:
- WSI-P2P的性能优于传统的线下特征提取,在各种数据分布中保持高的辨别能力.
- 该框架在亚型分类方面表现出色,证明了它对大规模组织学研究的可靠性.
- WSI-P2P为临床环境和广泛的组织学研究提供了一个可扩展和可靠的工具.
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: Stratified Epithelium
12.4K
Stratified epithelium consists of several stacked layers of cells. They provide the durability to withstand constant physical and chemical attacks. Stratified epithelium is named after the shape of the most apical layer of cells. Stratified squamous epithelium is the most common type found in the human body. In this tissue, the apical cells are squamous, whereas the basal layer contains either columnar or cuboidal cells. The basal cells divide to form new daughter cells, which gradually become...
12.4K
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


