Imaging recommendations in pediatric lymphoma: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper.

Hodgkin lymphoma (HL) and non-Hodgkin lymphoma (NHL) are both malignancies originating in the lymphatic system and both affect children, but many features differ considerably, impacting workup and management. This paper provides consensus-based imaging recommendations for evaluation of patients with HL and NHL at diagnosis and response assessment for both interim and end of therapy (follow-up).

Imaging of pediatric spine and spinal cord tumors: A COG Diagnostic Imaging Committee/SPR Oncology Committee/ASPNR White Paper.

Childhood spinal tumors are rare. Tumors can involve the spinal cord, the meninges, bony spine, and the paraspinal tissue. Optimized imaging should be utilized to evaluate tumors arising from specific spinal compartments. This paper provides consensus-based recommendations for optimized imaging of tumors arising from specific spinal compartments at diagnosis, follow-up during and after therapy, and response assessment.

Imaging of pediatric adrenal tumors: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper.

Adrenal tumors other than neuroblastoma are uncommon in children. The most frequently encountered are adrenocortical carcinoma and pheochromocytoma. This paper offers consensus recommendations for imaging of pediatric patients with a known or suspected primary adrenal malignancy other than neuroblastoma at diagnosis and during follow-up.

Imaging of pediatric neuroblastoma: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper.

Neuroblastoma is the most common extracranial solid neoplasm in children. This manuscript provides consensus-based imaging recommendations for pediatric neuroblastoma patients at diagnosis and during follow-up.

Imaging of pediatric thyroid tumors: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper.

Pediatric thyroid cancer is rare in children; however, incidence is increasing. Papillary thyroid cancer and follicular thyroid cancer are the most common subtypes, comprising about 90% and 10% of cases, respectively. This paper provides consensus imaging recommendations for evaluation of pediatric patients with thyroid cancer at diagnosis and during follow-up.

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 Chaudhary and Bapuraj in this issue.

A safety and feasibility trial of 131 I-MIBG in newly diagnosed high-risk neuroblastoma: A Children's Oncology Group study.

INTRODUCTION: 131 I-meta-iodobenzylguanidine (131 I-MIBG) is effective in relapsed neuroblastoma. The Children's Oncology Group (COG) conducted a pilot study (NCT01175356) to assess tolerability and feasibility of induction chemotherapy followed by 131 I- MIBG therapy and myeloablative busulfan/melphalan (Bu/Mel) in patients with newly diagnosed high-risk neuroblastoma. METHODS: Patients with MIBG-avid high-risk neuroblastoma were eligible. After the first two patients to receive protocol therapy developed severe sinusoidal obstruction syndrome (SOS), the trial was re-designed to include an 131 I-MIBG dose escalation (12, 15, and 18 mCi/kg), with a required 10-week gap before Bu/Mel administration. Patients who completed induction chemotherapy were evaluable for assessment of 131 I-MIBG feasibility; those who completed 131 I-MIBG therapy were evaluable for assessment of 131 I-MIBG + Bu/Mel feasibility. RESULTS: Fifty-nine of 68 patients (86.8%) who completed induction chemotherapy received 131 I-MIBG. Thirty-seven of 45 patients (82.2%) evaluable for 131 I-MIBG + Bu/Mel received this combination. Among those who received 131 I-MIBG after revision of the study design, one patient per dose level developed severe SOS. Rates of moderate to severe SOS at 12, 15, and 18 mCi/kg were 33.3%, 23.5%, and 25.0%, respectively. There was one toxic death. The 131 I-MIBG and 131 I-MIBG+Bu/Mel feasibility rates at the 15 mCi/kg dose level designated for further study were 96.7% (95% CI: 83.3%-99.4%) and 81.0% (95% CI: 60.0%-92.3%). CONCLUSION: This pilot trial demonstrated feasibility and tolerability of administering 131 I-MIBG followed by myeloablative therapy with Bu/Mel to newly diagnosed children with high-risk neuroblastoma in a cooperative group setting, laying the groundwork for a cooperative randomized trial (NCT03126916) testing the addition of 131 I-MIBG during induction therapy.

Fetal neurodevelopmental recovery in donors after laser surgery for twin-twin transfusion syndrome.

BACKGROUND: Fetal magnetic resonance imaging (MRI) and spectroscopy (MRS) provide a unique opportunity to non-invasively measure markers of neurodevelopment in survivors of twin-twin transfusion syndrome (TTTS). OBJECTIVE: To characterize fetal brain maturation after laser surgery for TTTS by measuring brain volumes and cerebral metabolite concentrations using fetal MRI + MRS. STUDY DESIGN: Prospective study of dual surviving fetuses treated with laser surgery for TTTS. At 4-5 postoperative weeks, fetal MRI was used together with novel image analysis to automatically extract major brain tissue volumes. Fetal MRS was used to measure major metabolite concentrations in the fetal brain. RESULTS: Twenty-one twin pairs were studied. The average (±SD) gestational age at MRI was 25.89 (±2.37) weeks. Total brain volume (TBV) was lower in the donors, although cerebral volumes were not different between twin pairs. Recipients showed lower proportions of cortical and cerebellar volumes, normalized to TBV and cerebral volumes. MRS data showed that biochemical differences between twin brains were related to discrepancy in their brain volumes. CONCLUSION: Although donors have a smaller TBV compared to recipients, proportionality of brain tissue volumes are preserved in donors. MRS maturational markers of fetal brain development show that recovery in donors persists 4 weeks after surgery.

Structural network topology correlates of microstructural brain dysmaturation in term infants with congenital heart disease.

Neonates with complex congenital heart disease (CHD) demonstrate microstructural brain dysmaturation, but the relationship with structural network topology is unknown. We performed diffusion tensor imaging (DTI) in term neonates with CHD preoperatively (N = 61) and postoperatively (N = 50) compared with healthy term controls (N = 91). We used network topology (graph) analyses incorporating different weighted and unweighted approaches and subject-specific white matter segmentation to investigate structural topology differences, as well as a voxel-based analysis (VBA) to confirm the presence of microstructural dysmaturation. We demonstrate cost-dependent network inefficiencies in neonatal CHD in the pre- and postoperative period compared with controls, related to microstructural differences. Controlling for cost, we show the presence of increased small-worldness (hierarchical fiber organization) in CHD infants preoperatively, that persists in the postoperative period compared with controls, suggesting the early presence of brain reorganization. Taken together, topological microstructural dysmaturation in CHD infants is accompanied by hierarchical fiber organization during a protracted critical period of early brain development. Our methodology also provides a pipeline for quantitation of network topology changes in neonates and infants with microstructural brain dysmaturation at risk for perinatal brain injury.

Predictors of response, progression-free survival, and overall survival using NANT Response Criteria (v1.0) in relapsed and refractory high-risk neuroblastoma.

PURPOSE: The New Approaches to Neuroblastoma Therapy Response Criteria (NANTRC) were developed to optimize response assessment in patients with recurrent/refractory neuroblastoma. Response predictors and associations of the NANTRC version 1.0 (NANTRCv1.0) and prognostic factors with outcome were analyzed. METHODS: A retrospective analysis was performed of patients with recurrent/refractory neuroblastoma enrolled from 2000 to 2009 on 13 NANT Phase 1/2 trials. NANTRC overall response integrated CT/MRI (Response Evaluation Criteria in Solid Tumors [RECIST]), metaiodobenzylguanidine (MIBG; Curie scoring), and percent bone marrow (BM) tumor (morphology). RESULTS: Fourteen (6.9%) complete response (CR) and 14 (6.9%) partial response (PR) occurred among 203 patients evaluable for response. Five-year progression-free survival (PFS) was 16 ± 3%; overall survival (OS) was 27 ± 3%. Disease sites at enrollment included MIBG-avid lesions (100% MIBG trials; 84% non-MIBG trials), measurable CT/MRI lesions (48%), and BM (49%). By multivariable analysis, Curie score of 0 (P < 0.001), lower Curie score (P = 0.003), no measurable CT/MRI lesions (P = 0.044), and treatment on peripheral blood stem cell (PBSC) supported trials (P = 0.005) were associated with achieving CR/PR. Overall response of stable disease (SD) or better was associated with better OS (P < 0.001). In multivariable analysis, MYCN amplification (P = 0.037) was associated with worse PFS; measurable CT/MRI lesions (P = 0.041) were associated with worse OS; prior progressive disease (PD; P < 0.001/P < 0.001), Curie score ≥ 1 (P < 0.001; P = 0.001), higher Curie score (P = 0.048/0.037), and treatment on non-PBSC trials (P = < 0.001/0.003) were associated with worse PFS and OS. CONCLUSIONS: NANTRCv1.0 response of at least SD is associated with better OS in patients with recurrent/refractory neuroblastoma. Patient and tumor characteristics may predict response and outcome. Identifying these variables can optimize Phase 1/2 trial design to select novel agents for further testing.

Computer-assisted Curie scoring for metaiodobenzylguanidine (MIBG) scans in patients with neuroblastoma.

BACKGROUND: Radiolabeled metaiodobenzylguanidine (MIBG) is sensitive and specific for detecting neuroblastoma. The extent of MIBG-avid disease is assessed using Curie scores. Although Curie scoring is prognostic in patients with high-risk neuroblastoma, there is no standardized method to assess the response of specific sites of disease over time. The goal of this study was to develop approaches for Curie scoring to facilitate the calculation of scores and comparison of specific sites on serial scans. PROCEDURE: We designed three semiautomated methods for determining Curie scores, each with increasing degrees of computer assistance. Method A was based on visual assessment and tallying of MIBG-avid lesions. For method B, scores were tabulated from a schematic that associated anatomic regions to MIBG-positive lesions. For method C, an anatomic mesh was used to mark MIBG-positive lesions with automatic assignment and tallying of scores. Five imaging physicians experienced in MIBG interpretation scored 38 scans using each method, and the feasibility and utility of the methods were assessed using surveys. RESULTS: There was good reliability between methods and observers. The user-interface methods required 57 to 110 seconds longer than the visual method. Imaging physicians indicated that it was useful that methods B and C enabled tracking of lesions. Imaging physicians preferred method B to method C because of its efficiency. CONCLUSIONS: We demonstrate the feasibility of semiautomated approaches for Curie score calculation. Although more time was needed for strategies B and C, the ability to track and document individual MIBG-positive lesions over time is a strength of these methods.

Radiologic discrepancies in children with special healthcare needs in a pediatric emergency department.

BACKGROUND: After-hours radiologic interpretation by nonradiology attendings or resident radiologists introduces the risk of discrepancies. Clinical outcomes following radiologic discrepancies among pediatric emergency department (ED) patients are poorly described. In particular, children with special healthcare needs (CSHCN), have more opportunities for discrepancies and potential consequences than non- CSHCN. Our objective was to determine the rates and types of radiologic discrepancies, and to compare CSHCN to non-CSHCN. METHODS: From July 2014 to February 2015, all children who underwent a diagnostic imaging study at a free-standing children's ED were included. Data collected included radiologic studies - type and location - and clinical details - chief complaint and CSHCN type. Differences between preliminary reads and final pediatric radiology attending reads were defined as discrepancies, and categorized by clinical significance. Descriptive statistics, z-tests, and chi-square were used. RESULTS: Over 8months, 8310 visits (7462 unique patients) had radiologic studies (2620 CSHCN, 5690 non-CSHCN). A total of 198 (2.4%) radiologic discrepancies [56 (28.3%) CSHCN, 142 (71.7%) non-CSHCN] were found. Chief complaints for CSCHN were more often within the cardiac, pulmonary and neurologic systems (p<0.001 for each), whereas non-CSHCN presented with more trauma (p<0.001). The rates of discrepancies (CSHCN 2.1%, non- CSHCN 2.5%, p=0.3) and severity of clinical consequences (p=0.6) were not significantly different between CSHCN and non-CSHCN. CONCLUSION: Though the frequency and type of radiologic studies performed between CSHCN and non-CSHCN were different, we found no significant difference in the rate of radiologic discrepancies or the rate of clinically significant radiologic discrepancies.

Clinical Factors Associated with Cerebral Metabolism in Term Neonates with Congenital Heart Disease.

OBJECTIVE: To determine associations between patient and clinical factors with postnatal brain metabolism in term neonates with congenital heart disease (CHD) via the use of quantitative magnetic resonance spectroscopy. STUDY DESIGN: Neonates with CHD were enrolled prospectively to undergo pre- and postoperative 3T brain magnetic resonance imaging. Short-echo single-voxel magnetic resonance spectroscopy of parietal white matter was used to quantify metabolites related to brain maturation (n-acetyl aspartate, choline, myo- inositol), neurotransmitters (glutamate and gamma-aminobutyric acid), energy metabolism (glutamine, citrate, glucose, and phosphocreatine), and injury/apoptosis (lactate and lipids). Multivariable regression was performed to search for associations between (1) patient-specific/prenatal/preoperative factors with concurrent brain metabolism and (2) intraoperative and postoperative factors with postoperative brain metabolism. RESULTS: A total of 83 magnetic resonance images were obtained on 55 subjects. No patient-specific, prenatal, or preoperative factors associated with concurrent metabolic brain dysmaturation or elevated lactate could be identified. Chromosome 22q11 microdeletion and age at surgery were predictive of altered concurrent white matter phosphocreatine (P < .0055). The only significant intraoperative association found was increased deep hypothermic circulatory arrest time with reduced postoperative white matter glutamate and gamma-aminobutyric acid (P < .0072). Multiple postoperative factors, including increased number of extracorporeal membrane oxygenation days (P < .0067), intensive care unit, length of stay (P < .0047), seizures in the intensive care unit (P < .0009), and home antiepileptic use (P < .0002), were associated with reduced postoperative white matter n-acetyl aspartate. CONCLUSION: Multiple postoperative factors were found to be associated with altered brain metabolism in term infants with CHD, but not patient-specific, preoperative, or intraoperative factors.

A Phase I New Approaches to Neuroblastoma Therapy Study of Buthionine Sulfoximine and Melphalan With Autologous Stem Cells for Recurrent/Refractory High-Risk Neuroblastoma.

BACKGROUND: Myeloablative therapy for high-risk neuroblastoma commonly includes melphalan. Increased cellular glutathione (GSH) can mediate melphalan resistance. Buthionine sulfoximine (BSO), a GSH synthesis inhibitor, enhances melphalan activity against neuroblastoma cell lines, providing the rationale for a Phase 1 trial of BSO-melphalan. PROCEDURES: Patients with recurrent/resistant high-risk neuroblastoma received BSO (3 gram/m(2) bolus, then 24 grams/m(2) /day infusion days -4 to -2), with escalating doses of intravenous melphalan (20-125 mg/m(2) ) days -3 and -2, and autologous stem cells day 0 using 3 + 3 dose escalation. RESULTS: Among 28 patients evaluable for dose escalation, one dose-limiting toxicity occurred at 20 mg/m(2) melphalan (grade 3 aspartate aminotransferase/alanine aminotransferase) and one at 80 mg/m(2) (streptococcal bacteremia, grade 4 hypotension/pulmonary/hypocalcemia) without sequelae. Among 25 patients evaluable for response, there was one partial response (PR) and two mixed responses (MRs) among eight patients with prior melphalan exposure; one PR and three MRs among 16 patients without prior melphalan; one stable disease with unknown melphalan history. Melphalan pharmacokinetics with BSO were similar to reports for melphalan alone. Melphalan Cmax for most patients was below the 10 µM concentration that showed neuroblastoma preclinical activity with BSO. CONCLUSIONS: BSO (75 gram/m(2) ) with melphalan (125 mg/m(2) ) is tolerable with stem cell support and active in recurrent/refractory neuroblastoma. Further dose escalation is feasible and may increase responses.

Hodgkin lymphoma involving the extra-axial CNS: an AHOD1331, PHL-C1, and PHL-C2 report from the COG and EuroNet-PHL.

ABSTRACT: Hodgkin lymphoma (HL) involving the central nervous system (CNS) is exceedingly rare. Information regarding the presentation, management, treatment, and outcome of patients with CNS HL is limited to case reports or small series. We describe 45 pediatric patients with 55 extra-axial CNS lesions at diagnosis with HL from a cohort of 4995 patients enrolled on Children's Oncology Group AHOD1331 and the European Network for Pediatric Hodgkin lymphoma C1 and C2 trials, with an overall incidence of 0.9%. Up to 82.2% of patients had a single CNS lesion in the thoracic, lumbar, or sacral spine. In the evaluated cohort, HL did not occur within the CNS parenchyma. Lesions extended into the extra-axial CNS space from adjacent soft tissue or bone and never directly infiltrated through the dura into the brain or spinal cord. Patients with CNS involvement had a twofold greater incidence of extranodal lesions than previously reported cohorts without CNS involvement. After 2 cycles of chemotherapy, 89.1% of CNS lesions demonstrated a complete metabolic response and >75% decrease in volume. Thirteen CNS lesions (23.6%) received irradiation; none were sites of disease relapse. Relapse occurred at the site of 2 lesions involving the CNS, both of which had an adequate interim response to chemotherapy. In summary, we present, to our knowledge, the largest reported cohort of systemic HL involving the CNS at diagnosis, demonstrating that these lesions originate from surrounding tissues, extend into the extra-axial CNS space, and respond similarly to other nodal and extranodal disease. The trials were registered at www.clinicaltrials.gov as #NCT02166463, #NCT00433459, and #NCT02684708.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs).

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.

An international study presenting a federated learning AI platform for pediatric brain tumors.

While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.

Importance of Central Imaging Review in a Pediatric Hodgkin Lymphoma Trial Using Positron Emission Tomography Response Adapted Radiation Therapy.

PURPOSE: We investigated the effects of central review of the interim fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) scan response (iPET) assessment on treatment allocation in the risk-based, response-adapted, Children's Oncology Group study AHOD1331 (ClinicalTrials.gov identifier: NCT02166463) for pediatric patients with high-risk Hodgkin lymphoma. METHODS AND MATERIALS: Per protocol, after 2 cycles of systemic therapy, patients underwent iPET, with visual response assessment by 5-point Deauville score (DS) at their treating institution and a real-time central review, with the latter considered the reference standard. An area of disease with a DS of 1 to 3 was considered a rapid-responding lesion, whereas a DS of 4 to 5 was considered a slow-responding lesion (SRL). Patients with 1 or more SRLs were considered iPET positive, whereas patients with only rapid-responding lesions were considered iPET negative. We conducted a predefined exploratory evaluation of concordance in iPET response assessment between institutional and central reviews of 573 patients. The concordance rate was evaluated using the Cohen κ statistic (κ > 0.80 was considered very good agreement and κ > 0.60-0.80, good agreement). RESULTS: The concordance rate (514 of 573 [89.7%]) had a κ of 0.685 (95% CI, 0.610-0.759), consistent with good agreement. In terms of the direction of discordance, among the 126 patients who were considered iPET positive by institutional review, 38 (30.2%) were categorized as iPET negative by central review, preventing overtreatment with radiation therapy. Conversely, among the 447 patients who were considered iPET negative by institutional review, 21 patients (4.7%) were categorized as iPET positive by the central review and would have been undertreated without radiation therapy. CONCLUSIONS: Central review is integral to PET response-adapted clinical trials for children with Hodgkin lymphoma. Continued support of central imaging review and education about DS are needed.

Crizotinib-associated Renal Cyst Formation in a Pediatric Patient With ALK+ Epithelioid Inflammatory Myofibroblastic Sarcoma.

BACKGROUND: Crizotinib is a first-generation tyrosine kinase inhibitor used for anaplastic lymphoma kinase (ALK) positive cancers. Simple and complex renal cyst formation is a rare complication of crizotinib use that has been reported previously in the adult population. CASE: We report a case of a right renal mass in a 17-year-old with ALK-positive epithelioid inflammatory myofibroblastic sarcoma treated with Crizotinib. After cessation of Crizotinib and initiating Alectenib, a second generation ALK inhibitor, the mass decreased in size and the patient remained asymptomatic without evidence of recurrence at three months of follow-up.

Machine Assist for Pediatric Posterior Fossa Tumor Diagnosis: A Multinational Study.

BACKGROUND: Clinicians and machine classifiers reliably diagnose pilocytic astrocytoma (PA) on magnetic resonance imaging (MRI) but less accurately distinguish medulloblastoma (MB) from ependymoma (EP). One strategy is to first rule out the most identifiable diagnosis. OBJECTIVE: To hypothesize a sequential machine-learning classifier could improve diagnostic performance by mimicking a clinician's strategy of excluding PA before distinguishing MB from EP. METHODS: We extracted 1800 total Image Biomarker Standardization Initiative (IBSI)-based features from T2- and gadolinium-enhanced T1-weighted images in a multinational cohort of 274 MB, 156 PA, and 97 EP. We designed a 2-step sequential classifier - first ruling out PA, and next distinguishing MB from EP. For each step, we selected the best performing model from 6-candidate classifier using a reduced feature set, and measured performance on a holdout test set with the microaveraged F1 score. RESULTS: Optimal diagnostic performance was achieved using 2 decision steps, each with its own distinct imaging features and classifier method. A 3-way logistic regression classifier first distinguished PA from non-PA, with T2 uniformity and T1 contrast as the most relevant IBSI features (F1 score 0.8809). A 2-way neural net classifier next distinguished MB from EP, with T2 sphericity and T1 flatness as most relevant (F1 score 0.9189). The combined, sequential classifier was with F1 score 0.9179. CONCLUSION: An MRI-based sequential machine-learning classifiers offer high-performance prediction of pediatric posterior fossa tumors across a large, multinational cohort. Optimization of this model with demographic, clinical, imaging, and molecular predictors could provide significant advantages for family counseling and surgical planning.