- Browse by Author
Browsing by Author "Lober, Robert M."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item MRI-based radiomics for prognosis of pediatric diffuse intrinsic pontine glioma: an international study(Oxford University Press, 2021-03-05) Tam, Lydia T.; Yeom, Kristen W.; Wright, Jason N.; Jaju, Alok; Radmanesh, Alireza; Han, Michelle; Toescu, Sebastian; Maleki, Maryam; Chen, Eric; Campion, Andrew; Lai, Hollie A.; Eghbal, Azam A.; Oztekin, Ozgur; Mankad, Kshitij; Hargrave, Darren; Jacques, Thomas S.; Goetti, Robert; Lober, Robert M.; Cheshier, Samuel H.; Napel, Sandy; Said, Mourad; Aquilina, Kristian; Ho, Chang Y.; Monje, Michelle; Vitanza, Nicholas A.; Mattonen, Sarah A.; Radiology and Imaging Sciences, School of MedicineBackground: Diffuse intrinsic pontine gliomas (DIPGs) are lethal pediatric brain tumors. Presently, MRI is the mainstay of disease diagnosis and surveillance. We identify clinically significant computational features from MRI and create a prognostic machine learning model. Methods: We isolated tumor volumes of T1-post-contrast (T1) and T2-weighted (T2) MRIs from 177 treatment-naïve DIPG patients from an international cohort for model training and testing. The Quantitative Image Feature Pipeline and PyRadiomics was used for feature extraction. Ten-fold cross-validation of least absolute shrinkage and selection operator Cox regression selected optimal features to predict overall survival in the training dataset and tested in the independent testing dataset. We analyzed model performance using clinical variables (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variables. Results: All selected features were intensity and texture-based on the wavelet-filtered images (3 T1 gray-level co-occurrence matrix (GLCM) texture features, T2 GLCM texture feature, and T2 first-order mean). This multivariable Cox model demonstrated a concordance of 0.68 (95% CI: 0.61-0.74) in the training dataset, significantly outperforming the clinical-only model (C = 0.57 [95% CI: 0.49-0.64]). Adding clinical features to radiomics slightly improved performance (C = 0.70 [95% CI: 0.64-0.77]). The combined radiomics and clinical model was validated in the independent testing dataset (C = 0.59 [95% CI: 0.51-0.67], Noether's test P = .02). Conclusions: In this international study, we demonstrate the use of radiomic signatures to create a machine learning model for DIPG prognostication. Standardized, quantitative approaches that objectively measure DIPG changes, including computational MRI evaluation, could offer new approaches to assessing tumor phenotype and serve a future role for optimizing clinical trial eligibility and tumor surveillance.Item Transient Neurologic Deficit without Vascular Pathology Correlates with Reversible Focal Hypoperfusion on Arterial Spin Labeled Perfusion Imaging(Thieme, 2019-04) Diller, Emily E.; Parker, Jason G.; Ey, Elizabeth H.; Lober, Robert M.; Radiology and Imaging Sciences, School of MedicineWe present the case of a 16-year-old boy with altered mental status and magnetic resonance imaging demonstrating left hemispheric hypoperfusion without evidence of stroke, based on arterial spin labeling (ASL) and dynamic contrast-enhanced perfusion imaging. Vessel imaging on magnetic resonance angiography and computed tomography angiography, in addition to an echocardiogram, showed no evidence of an embolic source. Electroencephalography showed left posterior temporal slowing. Within 8 hours, he was awake and alert but with receptive aphasia, and within 24 hours his symptoms completely resolved. Repeat ASL perfusion imaging demonstrated complete resolution of the perfusion abnormality, and diffusion imaging revealed no areas of infarct. This report demonstrates the correlation between a transient neurologic deficit and reversible focal hypoperfusion measured by ASL cerebral perfusion.