PT  - JOURNAL ARTICLE
AU  - M. Zhang
AU  - L. Tam
AU  - J. Wright
AU  - M. Mohammadzadeh
AU  - M. Han
AU  - E. Chen
AU  - M. Wagner
AU  - J. Nemalka
AU  - H. Lai
AU  - A. Eghbal
AU  - C.Y. Ho
AU  - R.M. Lober
AU  - S.H. Cheshier
AU  - N.A. Vitanza
AU  - G.A. Grant
AU  - L.M Prolo
AU  - K.W. Yeom
AU  - A. Jaju
TI  - Radiomics Can Distinguish Pediatric Supratentorial Embryonal Tumors, High-Grade Gliomas, and Ependymomas
AID  - 10.3174/ajnr.A7481
DP  - 2022 Apr 01
TA  - American Journal of Neuroradiology
PG  - 603--610
VI  - 43
IP  - 4
4099  - http://www.ajnr.org/content/43/4/603.short
4100  - http://www.ajnr.org/content/43/4/603.full
SO  - Am. J. Neuroradiol.2022 Apr 01; 43
AB  - BACKGROUND AND PURPOSE: Pediatric supratentorial tumors such as embryonal tumors, high-grade gliomas, and ependymomas are difficult to distinguish by histopathology and imaging because of overlapping features. We applied machine learning to uncover MR imaging–based radiomics phenotypes that can differentiate these tumor types.MATERIALS AND METHODS: Our retrospective cohort of 231 patients from 7 participating institutions had 50 embryonal tumors, 127 high-grade gliomas, and 54 ependymomas. For each tumor volume, we extracted 900 Image Biomarker Standardization Initiative–based PyRadiomics features from T2-weighted and gadolinium-enhanced T1-weighted images. A reduced feature set was obtained by sparse regression analysis and was used as input for 6 candidate classifier models. Training and test sets were randomly allocated from the total cohort in a 75:25 ratio.RESULTS: The final classifier model for embryonal tumor-versus-high-grade gliomas identified 23 features with an area under the curve of 0.98; the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.85, 0.91, 0.79, 0.94, and 0.89, respectively. The classifier for embryonal tumor-versus-ependymomas identified 4 features with an area under the curve of 0.82; the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.93, 0.69, 0.76, 0.90, and 0.81, respectively. The classifier for high-grade gliomas-versus-ependymomas identified 35 features with an area under the curve of 0.96; the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.82, 0.94, 0.82, 0.94, and 0.91, respectively.CONCLUSIONS: In this multi-institutional study, we identified distinct radiomic phenotypes that distinguish pediatric supratentorial tumors, high-grade gliomas, and ependymomas with high accuracy. Incorporation of this technique in diagnostic algorithms can improve diagnosis, risk stratification, and treatment planning.AUCarea under the curveEPependymomaGLCMgray-level co-occurrence matrixHGGhigh-grade gliomaLRlogistic regressionNPVnegative predictive valuePNETprimitive neuroectodermal tumorPPVpositive predictive valueWHOWorld Health OrganizationXGBextreme gradient boostingLASSOleast absolute shrinkage and selection operator