Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown
Published: July 6, 2024
Language: Английский
Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown
Published: July 6, 2024
Language: Английский
Brain Disorders, Journal Year: 2025, Volume and Issue: unknown, P. 100238 - 100238
Published: May 1, 2025
Language: Английский
Citations
0Diagnostics, Journal Year: 2024, Volume and Issue: 15(1), P. 38 - 38
Published: Dec. 27, 2024
Background: The accurate and early distinction of glioblastomas (GBMs) from single brain metastases (BMs) provides a window opportunity for reframing treatment strategies enabling optimal timely therapeutic interventions. We sought to leverage physiologically sensitive parameters derived diffusion tensor imaging (DTI) dynamic susceptibility contrast (DSC)–perfusion-weighted (PWI) along with machine learning-based methods distinguish GBMs BMs. Methods: Patients histopathology-confirmed (n = 62) BMs 26) exhibiting contrast-enhancing regions (CERs) underwent 3T anatomical imaging, DTI DSC-PWI prior treatment. Median values mean diffusivity (MD), fractional anisotropy, linear, planar spheric anisotropic coefficients, relative cerebral blood volume (rCBV) maximum rCBV were measured CERs immediate peritumor regions. Data normalization scaling performed. In the next step, most relevant features extracted (non-interacting features), which subsequently used generate set new, innovative, high-order (interacting features) using feature engineering method. Finally, 10 learning classifiers employed in distinguishing Cross-validation receiver operating characteristic (ROC) curve analyses performed determine diagnostic performance. Results: A random forest classifier ANOVA F-value selection algorithm both interacting non-interacting provided best performance an area under ROC 92.67%, classification accuracy 87.8%, sensitivity 73.64% specificity 97.5%. Conclusions: based approach involving combined use physiological MRI shows promise differentiate between high accuracy.
Language: Английский
Citations
0Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown
Published: July 6, 2024
Language: Английский
Citations
0