Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
11025277 | European Journal of Radiology | 2018 | 49 Pages |
Abstract
The performance of machine learning based on histogram and texture features in multi-parametric MRI was superior to that of conventional cut-off method and the board certified radiologists to differentiate a GBM from a PCNSL.
Keywords
GLCMXGBoostT2-weighted imagesPCNSLITArCBVDWIGBMROCADCDSCAUCMRIImage texture analysisdiffusion-weighted imagingMagnetic resonance imagingExtreme gradient boostingRelative cerebral blood volumeCNStwo dimensionalcentral nervous systemapparent diffusion coefficientLymphomaarea under the curveGadoliniumGlioblastoma multiformereceiver operating characteristicMachine learning
Related Topics
Health Sciences
Medicine and Dentistry
Radiology and Imaging
Authors
Masataka Nakagawa, Takeshi Nakaura, Tomohiro Namimoto, Mika Kitajima, Hiroyuki Uetani, Machiko Tateishi, Seitaro Oda, Daisuke Utsunomiya, Keishi Makino, Hideo Nakamura, Akitake Mukasa, Toshinori Hirai, Yasuyuki Yamashita,