通过利用多个组织切片的共同性,通过使用图形卷积网络来增强整个幻灯片图像分类
Sakonporn Noree1, Willmer Rafell Quinones Robles1, Young Sin Ko2
1Graduate School of Data Science, Department of Industrial and System Engineering, Korea Advanced Institute of Science and Technology, Deajeon, South Korea.
这项研究引入了一种基于图形的全幻灯片图像 (WSI) 分类新方法,该方法利用整个组织切片的共同模式. 这种方法显著提高了癌症诊断的分类准确性和AUROC.
科学领域:
- 计算病理学计算病理学
- 数字病理学数字病理学
- 机器学习在医疗保健中的应用
背景情况:
- 准确的组织病理整体幻灯片图像 (WSI) 分类对于癌症诊断和治疗计划至关重要.
- 传统的WSI分析往往忽略了来自同一活检的不同组织切片中存在的共享模式.
- 深度学习模型已经显示出潜力,但通常会独立分析切片.
研究的目的:
- 开发一种新的WSI分类技术,利用切片间的共同性来提高诊断准确性.
- 改进现有的深度学习和多重实例学习方法,用于WSI分析.
主要方法:
- 构建单个组织切片的图形表示.
- 根据空间关系和特征相似性,提取相关特征和连接图.
- 利用图形卷积网络在集成图形结构上进行WSI分类.
主要成果:
- 拟议的方法通过结合切片间的共同性,显著改善了基于图的WSI分类.
- 与现有方法相比,获得了更高的准确性 (胃: 91.5%,结直肠: 91.2%).
- 与多个实例学习方法相比,证明了更高的AUROC (胃:98.8%,结直肠:98.2%).
结论:
- 这种新的方法提供了一个更准确,更有效的方法来进行WSI分类,通过有效地利用跨片的信息来进行分类.
- 这种技术在改善癌症诊断中的临床应用方面具有重大前景.
- 源代码是公开可用的,用于进一步的研究和开发.
更多相关视频
03:38Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
Published on: June 20, 2025
11:27Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions
Published on: September 22, 2013
相关概念视频
Classification of Epithelial Tissues: Overview
Based on the number of cell layers,...
Classification of Connective Tissues
Connective Tissue Proper
Connective tissue proper is the most abundant class of connective tissues. As its name implies, it predominantly connects different tissues in the body. Depending on the cell types, ground substance, viscosity, and fiber types in the ECM, connective tissue proper is further categorized into loose and dense....
Classification of Epithelial Tissues: Stratified Epithelium
Classification of Epithelial Tissues: Simple Epithelium
Because of the thinness of the cells, simple squamous epithelium is present where the rapid passage of chemical compounds is observed. For example, the endothelium that lines the capillaries and vessels...
