Image-based deep learning identifies glioblastoma risk groups with genomic and transcriptomic heterogeneity: a multi-center study.

Jing YanQiuchang SunXiangliang TanChaofeng LiangHongmin BaiWenchao DuanTianhao MuYang GuoYuning QiuWeiwei WangQiaoli YaoDongling PeiYuanshen ZhaoDanni LiuJingxian DuanShifu ChenChen SunWenqing WangZhen LiuXuanke HongXiangxiang WangYu GuoYikai XuXianzhi LiuJingliang ChengZhi-Cheng LiZhenyu Zhang

Published in: European radiology (2022)

• MRI-based deep learning imaging signature (DLIS) stratifies GBM into risk groups with distinct molecular characteristics. • DLIS is associated with P53, RB, and RTK pathways and del_CDNK2A mutation. • The prognostic value of DLIS-correlated pathway genes is externally demonstrated.

Keyphrases

deep learning
genome wide
artificial intelligence
convolutional neural network
single cell
magnetic resonance imaging
machine learning
contrast enhanced
copy number
single molecule
mass spectrometry
rna seq
diffusion weighted imaging
fluorescence imaging
genome wide analysis