TY - JOUR T1 - Radiomic Phenotypes Distinguish Atypical Teratoid/Rhabdoid Tumors from Medulloblastoma JF - American Journal of Neuroradiology JO - Am. J. Neuroradiol. DO - 10.3174/ajnr.A7200 AU - M. Zhang AU - S.W. Wong AU - S. Lummus AU - M. Han AU - A. Radmanesh AU - S.S. Ahmadian AU - L.M. Prolo AU - H. Lai AU - A. Eghbal AU - O. Oztekin AU - S.H. Cheshier AU - P.G. Fisher AU - C.Y. Ho AU - H. Vogel AU - N.A. Vitanza AU - R.M. Lober AU - G.A. Grant AU - A. Jaju AU - K.W. Yeom Y1 - 2021/07/15 UR - http://www.ajnr.org/content/early/2021/07/15/ajnr.A7200.abstract N2 - BACKGROUND AND PURPOSE: Atypical teratoid/rhabdoid tumors and medulloblastomas have similar imaging and histologic features but distinctly different outcomes. We hypothesized that they could be distinguished by MR imaging–based radiomic phenotypes.MATERIALS AND METHODS: We retrospectively assembled T2-weighted and gadolinium-enhanced T1-weighted images of 48 posterior fossa atypical teratoid/rhabdoid tumors and 96 match-paired medulloblastomas from 7 institutions. Using a holdout test set, we measured the performance of 6 candidate classifier models using 6 imaging features derived by sparse regression of 900 T2WI and 900 T1WI Imaging Biomarker Standardization Initiative–based radiomics features.RESULTS: From the originally extracted 1800 total Imaging Biomarker Standardization Initiative–based features, sparse regression consistently reduced the feature set to 1 from T1WI and 5 from T2WI. Among classifier models, logistic regression performed with the highest AUC of 0.86, with sensitivity, specificity, accuracy, and F1 scores of 0.80, 0.82, 0.81, and 0.85, respectively. The top 3 important Imaging Biomarker Standardization Initiative features, by decreasing order of relative contribution, included voxel intensity at the 90th percentile, inverse difference moment normalized, and kurtosis—all from T2WI.CONCLUSIONS: Six quantitative signatures of image intensity, texture, and morphology distinguish atypical teratoid/rhabdoid tumors from medulloblastomas with high prediction performance across different machine learning strategies. Use of this technique for preoperative diagnosis of atypical teratoid/rhabdoid tumors could significantly inform therapeutic strategies and patient care discussions.ATRTatypical teratoid/rhabdoid tumorAUCarea under the curveGLCMgray level co-occurrence matrixMBmedulloblastoma ER -