Differentiating IDH status in human gliomas using machine learning and multiparametric MR/PET.
Hiroyuki TatekawaAkifumi HagiwaraHiroyuki UetaniShadfar BahriCatalina RaymondAlbert LaiTimothy F CloughesyPhioanh L NghiemphuLinda M LiauWhitney B PopeNoriko SalamonBenjamin M EllingsonPublished in: Cancer imaging : the official publication of the International Cancer Imaging Society (2021)
Machine learning using an unsupervised two-level clustering approach followed by a support vector machine classified the IDH mutation status of gliomas, and visualized voxel-wise features from multiparametric MRI and FDOPA PET images. Unsupervised clustered features may improve the understanding of prioritizing multiparametric imaging for classifying IDH status.
Keyphrases
- machine learning
- low grade
- high grade
- contrast enhanced
- deep learning
- computed tomography
- positron emission tomography
- endothelial cells
- pet ct
- magnetic resonance imaging
- artificial intelligence
- high resolution
- wild type
- magnetic resonance
- pet imaging
- big data
- convolutional neural network
- single cell
- optical coherence tomography
- diffusion weighted imaging
- mass spectrometry
- pluripotent stem cells