Added Prognostic Value of 3D Deep Learning-Derived Features from Preoperative MRI for Adult-type Diffuse Gliomas.
Jung Oh LeeSung Soo AhnKyu Sung ChoiJunhyeok LeeJoon JangJung Hyun ParkInpyeong HwangChul-Kee ParkSung Hye ParkJin Wook ChungSeung Hong ChoiPublished in: Neuro-oncology (2023)
The global morphologic feature derived from 3D-CNN models using whole-brain MRI has independent prognostic value for diffuse gliomas. Combining clinical, molecular genetic, and imaging data yields the best performance.
Keyphrases
- deep learning
- high grade
- low grade
- contrast enhanced
- convolutional neural network
- magnetic resonance imaging
- diffusion weighted imaging
- machine learning
- high resolution
- artificial intelligence
- patients undergoing
- white matter
- electronic health record
- genome wide
- computed tomography
- magnetic resonance
- copy number
- young adults
- childhood cancer
- blood brain barrier
- neural network