Tumor mutation burden-related histopathological features for predicting overall survival in gliomas using graph deep learning
This study aimed to identify the TMB-related histopathological features from hematoxylin and eosin slides and explore their prognostic value in gliomas. We detected the TMB-related features using a graph convolutional neural network from whole slide image (WSI) of patients from The Cancer Genome Atlas dataset (619 patients), and evaluated the correlation between features and TMB in an external validation set (237 patients).
Source: American Journal of Pathology - Category: Pathology Authors: Caixia Sun, Tao Luo, Zhenyu Liu, Jia Ge, Lizhi Shao, Xiangyu Liu, Bao Li, Song Zhang, Qi Qiu, Wei Wei, Shuo Wang, Xiu-Wu Bian, Jie Tian Tags: Regular Article Source Type: research
More News: Brain Tumor | Cancer | Cancer & Oncology | Glioma | Learning | Pathology | Study | Universities & Medical Training