MRI Radiogenomics of Pediatric Medulloblastoma: A Multicenter Study.

Background Radiogenomics of pediatric medulloblastoma (MB) offers an opportunity for MB risk stratification, which may aid therapeutic decision making, family counseling, and selection of patient groups suitable for targeted genetic analysis. Purpose To develop machine learning strategies that identify the four clinically significant MB molecular subgroups. Materials and Methods In this retrospective study, consecutive pediatric patients with newly diagnosed MB at MRI at 12 international pediatric sites between July 1997 and May 2020 were identified. There were 1800 features extracted from T2- and contrast-enhanced T1-weighted preoperative MRI scans. A two-stage sequential classifier was designed-one that first identifies non-wingless (WNT) and non-sonic hedgehog (SHH) MB and then differentiates therapeutically relevant WNT from SHH. Further, a classifier that distinguishes high-risk group 3 from group 4 MB was developed. An independent, binary subgroup analysis was conducted to uncover radiomics features unique to infantile versus childhood SHH subgroups. The best-performing models from six candidate classifiers were selected, and performance was measured on holdout test sets. CIs were obtained by bootstrapping the test sets for 2000 random samples. Model accuracy score was compared with the no-information rate using the Wald test. Results The study cohort comprised 263 patients (mean age ± SD at diagnosis, 87 months ± 60; 166 boys). A two-stage classifier outperformed a single-stage multiclass classifier. The combined, sequential classifier achieved a microaveraged F1 score of 88% and a binary F1 score of 95% specifically for WNT. A group 3 versus group 4 classifier achieved an area under the receiver operating characteristic curve of 98%. Of the Image Biomarker Standardization Initiative features, texture and first-order intensity features were most contributory across the molecular subgroups. Conclusion An MRI-based machine learning decision path allowed identification of the four clinically relevant molecular pediatric medulloblastoma subgroups. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Verschakelen in this issue.

[1]  Omneya Attallah,et al.  MB-AI-His: Histopathological Diagnosis of Pediatric Medulloblastoma and its Subtypes via AI , 2021, Diagnostics.

[2]  Jingliang Cheng,et al.  Radiomic Features From Multi-Parameter MRI Combined With Clinical Parameters Predict Molecular Subgroups in Patients With Medulloblastoma , 2020, Frontiers in Oncology.

[3]  Nikos Paragios,et al.  Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics , 2020, Scientific Reports.

[4]  P. Northcott,et al.  Bridging the treatment gap in infant medulloblastoma: Molecularly informed outcomes of a globally feasible regimen. , 2020, Neuro-oncology.

[5]  F. Gilles,et al.  Excellent Outcome of Young Children with Nodular Desmoplastic Medulloblastoma Treated on "Head Start" III: A Multi-Institutional, Prospective Clinical Trial. , 2020, Neuro-oncology.

[6]  Lipi B Mahanta,et al.  Classification of childhood medulloblastoma into WHO‐defined multiple subtypes based on textural analysis , 2020, Journal of microscopy.

[7]  P. Varlet,et al.  Role of neoadjuvant chemotherapy in metastatic medulloblastoma: a comparative study in 92 children , 2020, Neuro-oncology.

[8]  R. Steenbakkers,et al.  The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. , 2020, Radiology.

[9]  B. Győrffy,et al.  Molecular stratifications, biomarker candidates and new therapeutic options in current medulloblastoma treatment approaches , 2020, Cancer and Metastasis Reviews.

[10]  Till Acker,et al.  DNA methylation-based classification of central nervous system tumours , 2018, Nature.

[11]  H. Gohlke,et al.  Minimal methylation classifier (MIMIC): A novel method for derivation and rapid diagnostic detection of disease-associated DNA methylation signatures , 2017, Scientific Reports.

[12]  A. Goldenberg,et al.  Intertumoral Heterogeneity within Medulloblastoma Subgroups. , 2017, Cancer cell.

[13]  M. Roussel,et al.  Medulloblastoma Genotype Dictates Blood Brain Barrier Phenotype. , 2016, Cancer cell.

[14]  M. Kool,et al.  Risk stratification of childhood medulloblastoma in the molecular era: the current consensus , 2016, Acta Neuropathologica.

[15]  B. Cukrowska,et al.  Contrast enhancement pattern predicts poor survival for patients with non-WNT/SHH medulloblastoma tumours , 2015, Journal of Neuro-Oncology.

[16]  G. Kristiansen,et al.  Molecular stratification of medulloblastoma: comparison of histological and genetic methods to detect Wnt activated tumours , 2015, Neuropathology and applied neurobiology.

[17]  P. Northcott,et al.  Duration of the pre‐diagnostic interval in medulloblastoma is subgroup dependent , 2014, Pediatric blood & cancer.

[18]  Volker Hovestadt,et al.  Prognostic significance of clinical, histopathological, and molecular characteristics of medulloblastomas in the prospective HIT2000 multicenter clinical trial cohort , 2014, Acta Neuropathologica.

[19]  Scott L. Pomeroy,et al.  Rapid, reliable, and reproducible molecular sub-grouping of clinical medulloblastoma samples , 2011, Acta Neuropathologica.