计算机科学
图形
背景(考古学)
卷积神经网络
特征(语言学)
源代码
深度学习
模式识别(心理学)
人工智能
机器学习
理论计算机科学
操作系统
语言学
生物
哲学
古生物学
作者
Richard J. Chen,Ming Lu,Muhammad Shaban,Chengkuan Chen,Tiffany Chen,Drew F. K. Williamson,Faisal Mahmood
标识
DOI:10.1007/978-3-030-87237-3_33
摘要
Cancer prognostication is a challenging task in computational pathology that requires context-aware representations of histology features to adequately infer patient survival. Despite the advancements made in weakly-supervised deep learning, many approaches are not context-aware and are unable to model important morphological feature interactions between cell identities and tissue types that are prognostic for patient survival. In this work, we present Patch-GCN, a context-aware, spatially-resolved patch-based graph convolutional network that hierarchically aggregates instance-level histology features to model local- and global-level topological structures in the tumor microenvironment. We validate Patch-GCN with 4,370 gigapixel WSIs across five different cancer types from the Cancer Genome Atlas (TCGA), and demonstrate that Patch-GCN outperforms all prior weakly-supervised approaches by 3.58–9.46%. Our code and corresponding models are publicly available at https://github.com/mahmoodlab/Patch-GCN .
科研通智能强力驱动
Strongly Powered by AbleSci AI