Glioma survival prediction from whole-brain MRI without tumor segmentation using deep attention network: a multicenter study.
Zhi-Cheng LiJing YanShenghai ZhangChaofeng LiangXiaofei LvYan ZouHuailing ZhangDong LiangZhenyu ZhangYinsheng ChenPublished in: European radiology (2022)
• DeepRisk can predict overall survival directly from whole-brain MRI without tumor segmentation. • DeepRisk achieves comparable accuracy in survival prediction with deep learning model built using expert-segmented tumor images. • DeepRisk has independent and incremental prognostic value over existing clinical parameters and IDH mutation status.
Keyphrases
- deep learning
- convolutional neural network
- magnetic resonance imaging
- artificial intelligence
- free survival
- contrast enhanced
- resting state
- machine learning
- computed tomography
- low grade
- multiple sclerosis
- diffusion weighted imaging
- magnetic resonance
- optical coherence tomography
- brain injury
- clinical practice
- cerebral ischemia
- blood brain barrier
- high grade