Neuroimaging of pediatric posterior fossa tumors including review of the literature

Applications of machine learning to MR imaging of pediatric low-grade gliomas

INTRODUCTION

Machine learning (ML) shows promise for the automation of routine tasks related to the treatment of pediatric low-grade gliomas (pLGG) such as tumor grading, typing, and segmentation. Moreover, it has been shown that ML can identify crucial information from medical images that is otherwise currently unattainable. For example, ML appears to be capable of preoperatively identifying the underlying genetic status of pLGG.

METHODS

In this chapter, we reviewed, to the best of our knowledge, all published works that have used ML techniques for the imaging-based evaluation of pLGGs. Additionally, we aimed to provide some context on what it will take to go from the exploratory studies we reviewed to clinically deployed models.

RESULTS

Multiple studies have demonstrated that ML can accurately grade, type, and segment and detect the genetic status of pLGGs. We compared the approaches used between the different studies and observed a high degree of variability throughout the methodologies. Standardization and cooperation between the numerous groups working on these approaches will be key to accelerating the clinical deployment of these models.

CONCLUSION

The studies reviewed in this chapter detail the potential for ML techniques to transform the treatment of pLGG. However, there are still challenges that need to be overcome prior to clinical deployment.

Medulloblastoma in a 13-Year-Old Female: A Comprehensive Case Report

The majority of children's brain cancers are posterior fossa tumours, which include brainstem gliomas, medulloblastomas (MBs), juvenile pilocytic astrocytomas, and ependymomas. This report details a 13-year-old female presenting with headache, nausea, and ataxia. With typical magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) results, the MRI indicated a solid lesion in the fourth ventricle, producing obstructive hydrocephalus. Pilocytic astrocytoma, ependymoma, MB, and other conditions are examples of differential diagnoses. In addition to underscoring the need for early intervention to enhance prognosis and outcomes for paediatric patients with posterior fossa tumours, the case highlights the vital role that sophisticated imaging plays in early detection and therapy.

Machine Learning Analysis in Diffusion Kurtosis Imaging for Discriminating Pediatric Posterior Fossa Tumors: A Repeatability and Accuracy Pilot Study

Background and purpose: Differentiating pediatric posterior fossa (PF) tumors such as medulloblastoma (MB), ependymoma (EP), and pilocytic astrocytoma (PA) remains relevant, because of important treatment and prognostic implications. Diffusion kurtosis imaging (DKI) has not yet been investigated for discrimination of pediatric PF tumors. Estimating diffusion values from whole-tumor-based (VOI) segmentations may improve diffusion measurement repeatability compared to conventional region-of-interest (ROI) approaches. Our purpose was to compare repeatability between ROI and VOI DKI-derived diffusion measurements and assess DKI accuracy in discriminating among pediatric PF tumors. Materials and methods: We retrospectively analyzed 34 children (M, F, mean age 7.48 years) with PF tumors who underwent preoperative examination on a 3 Tesla magnet, including DKI. For each patient, two neuroradiologists independently segmented the whole solid tumor, the ROI of the area of maximum tumor diameter, and a small 5 mm ROI. The automated analysis pipeline included inter-observer variability, statistical, and machine learning (ML) analyses. We evaluated inter-observer variability with coefficient of variation (COV) and Bland-Altman plots. We estimated DKI metrics accuracy in discriminating among tumor histology with MANOVA analysis. In order to account for class imbalances, we applied SMOTE to balance the dataset. Finally, we performed a Random Forest (RF) machine learning classification analysis based on all DKI metrics from the SMOTE dataset by partitioning 70/30 the training and testing cohort. Results: Tumor histology included medulloblastoma (15), pilocytic astrocytoma (14), and ependymoma (5). VOI-based measurements presented lower variability than ROI-based measurements across all DKI metrics and were used for the analysis. DKI-derived metrics could accurately discriminate between tumor subtypes (Pillai's trace: p < 0.001). SMOTE generated 11 synthetic observations (10 EP and 1 PA), resulting in a balanced dataset with 45 instances (34 original and 11 synthetic). ML analysis yielded an accuracy of 0.928, which correctly predicted all but one lesion in the testing set. Conclusions: VOI-based measurements presented improved repeatability compared to ROI-based measurements across all diffusion metrics. An ML classification algorithm resulted accurate in discriminating PF tumors on a SMOTE-generated dataset. ML techniques based on DKI-derived metrics are useful for the discrimination of pediatric PF tumors.

Correlation of ADC values of adult brain tumors with the diagnosis and pathological grade: A cross-sectional multicenter study

Background and Aim

Brain tumors are common, requiring physicians to have a precise understanding of them for accurate diagnosis and treatment. Considering that various histological tumor types present different cellularity, we conducted this research to examine the role of apparent diffusion coefficient (ADC) values in the differential diagnosis and pathologic grading of brain tumor types.

Methods

In this cross-sectional study, we gathered pathology reports of histological samples of adult brain tumors. The tissue sample of brain tumors were examined histologically by a pathologist. The magnetic resonance imaging data of these patients were interpreted by a neuroradiologist. The measured ADC values and ADC ratios were calculated. Standard mean ADC values were expressed as 10- 6 mm2/s. The findings were compared according to the histological diagnosis of each tumor.

Results

Sixty-eight patients were included in the study: 34 (50%) were male, and 34 (50%) were female. The average age of the patients was 51.69 + 16.40 years. In the examination of tumor type, 16 (23.5%) were astrocytoma, 9 (13.2%) were oligodendroglioma, 20 (29.4%) were glioblastoma, 4 (5.9%) were medulloblastoma, and 19 (27.9%) were metastatic tumors. the average value of ADC was statistically significantly different according to the pathological type of tumor (p < 0.001). The two-by-two comparison of average ADC among tumor types revealed significant differences, except for oligodendroglioma and glioblastoma (p-value = 0.87) and glioblastoma and medulloblastoma (p-value = 0.347). The average value of ADC and ADC ratio was statistically significantly different according to the pathological grade of the tumor (p < 0.001). In the two-by-two comparison of average ADC between all pathological grades of the tumor showed a significance difference except for Grade I and Grade II (p-value = 0.355). The mean value of ADC and ADC ratio for glioblastoma and metastatic tumors showed no significant difference.

Conclusion

The assessment of brain tumor grade through ADC examination will help to estimate prognosis and devising suitable therapeutic strategies.

The performance of diffusion tensor imaging parameters for the distinction between medulloblastoma and pilocytic astrocytoma

BACKGROUND

The aim of this study was to evaluate the performance of diffusion tensor imaging (DTI) parameters for the distinction between pediatric medulloblastomas and pilocytic astrocytomas.

METHODS

DTI was performed in 36 patients, who were divided into two groups: group 1 consisted of 26 patients with medulloblastoma, whereas group 2 consisted of 10 patients with pilocytic astrocytoma. The Mann-Whitney U Test was utilized to compare the tumoral fractional anisotropy (tFA) and diffusivity (tMD) values and the tumor to parenchyma ratios for these values (rFA and rMD, respectively) between these two groups. Receiver operating characteristic (ROC) curve analysis and the Youden Index were applied to compute the cut-off point, and then the area under the curve (AUC), sensitivity, and specificity were calculated.

RESULTS

The tFA and rFA values of group 1 were significantly higher than those of group 2 (P<0.05). In contrast, the tMD and rMD values of group 1 were significantly lower than those of group 2 (P<0.05). Among the FA parameters, a cut-off tFA value of 0.37 provided the best ability to discriminate between medulloblastomas and pilocytic astrocytomas, producing a sensitivity value of 84.6%, a specificity of 80%, and an AUC of 81.7%. The cut-off values for MD and rMD were determined to be 1.06 × 10-3 mm2/s and 1.33, respectively, and were determined to be the most efficacious parameters for the differential diagnosis between medulloblastoma and pilocytic astrocytoma, which generated sensitivity, specificity, and AUC values of 100%.

CONCLUSIONS

DTI parameters can play pivotal roles in the discrimination between medulloblastoma and pilocytic astrocytoma.

Radiomics for Differentiation of Pediatric Posterior Fossa Tumors: A Meta-Analysis and Systematic Review of the Literature

PURPOSE

To better define the overall performance of the current radiomics-based models for the discrimination of pediatric posterior fossa tumors.

METHODS

A comprehensive literature search of the databases PubMed, Ovid MEDLINE, Ovid EMBASE, Web of Science, and Scopus was designed and conducted by an experienced librarian. We estimated overall sensitivity (SEN) and specificity (SPE). Event rates were pooled across studies using a random-effects meta-analysis, and the χ2 test was performed to assess the heterogeneity.

RESULTS

Overall SEN and SPE for differentiation between MB, PA, and EP were found to be promising, with SEN values of 93% (95% CI = 0.88-0.96), 83% (95% CI = 0.66-0.93), and 85% (95% CI = 0.71-0.93), and corresponding SPE values of 87% (95% CI = 0.82-0.90), 95% (95% CI = 0.90-0.98) and 90% (95% CI = 0.84-0.94), respectively. For MB, there is a better trend for LR classifiers, while textural features are the most used and the best performing (ACC 96%). As for PA and EP, a synergistic employment of LR and NN classifiers, accompanied by geometrical or morphological features, demonstrated superior performance (ACC 94% and 96%, respectively).

CONCLUSIONS

The diagnostic performance is high, making radiomics a helpful method to discriminate these tumor types. In the forthcoming years, we expect even more precise models.

Semiquantitative analysis of cerebral [18F]FDG-PET uptake in pediatric patients

BACKGROUND

Glycolytic metabolism in the brain of pediatric patients, imaged with [18F]  fluorodeoxyglucose-positron emission tomography (FDG-PET) is incompletely characterized.

OBJECTIVE

The purpose of the current study was to characterize [18F]FDG-PET brain uptake in a large sample of pediatric patients with non-central nervous system diseases as an alternative to healthy subjects to evaluate changes at different pediatric ages.

MATERIALS AND METHODS

Seven hundred ninety-five [18F]FDG-PET examinations from children < 18 years of age without central nervous system diseases were included. Each brain image was spatially normalized, and the standardized uptake value (SUV) was obtained. The SUV and the SUV relative to different pseudo-references were explored as a function of age.

RESULTS

At all evaluated ages, the occipital lobe showed the highest [18F]FDG uptake (0.27 ± 0.04 SUV/year), while the parietal lobe and brainstem had the lowest uptake (0.17 ± 0.02 SUV/year, for both regions). An increase [18F]FDG uptake was found for all brain regions until 12 years old, while no significant uptake differences were found between ages 13 (SUV = 5.39) to 17 years old (SUV = 5.52) (P < 0.0001 for the whole brain). A sex dependence was found in the SUVmean for the whole brain during adolescence (SUV 5.04-5.25 for males, 5.68-5.74 for females, P = 0.0264). Asymmetries in [18F]FDG uptake were found in the temporal and central regions during infancy.

CONCLUSIONS

Brain glycolytic metabolism of [18F]FDG, measured through the SUVmean, increased with age until early adolescence (< 13 years old), showing differences across brain regions. Age, sex, and brain region influence [18F]FDG uptake, with significant hemispheric asymmetries for temporal and central regions.

Posterior fossa tumors in children: current insights

While in adults most intracranial tumors develop around the cerebral hemispheres, 45 to 60% of pediatric lesions are found in the posterior fossa, although this anatomical region represents only 10% of the intracranial volume. The latest edition of the WHO classification for CNS tumors presented some fundamental paradigm shifts that particularly affected the classification of pediatric tumors, also influencing those that affect posterior fossa. Molecular biomarkers play an important role in the diagnosis, prognosis, and treatment of childhood posterior fossa tumors and can be used to predict patient outcomes and response to treatment and monitor its effectiveness. Although genetic studies have identified several posterior fossa tumor types, differing in terms of their location, cell of origin, genetic mechanisms, and clinical behavior, recent management strategies still depend on uniform approaches, mainly based on the extent of resection. However, significant progress has been made in guiding therapy decisions with biological or molecular stratification criteria and utilizing molecularly targeted treatments that address specific tumor biological characteristics. The primary focus of this review is on the latest advances in the diagnosis and treatment of common subtypes of posterior fossa tumors in children, as well as potential therapeutic approaches in the future.   Conclusion: Molecular biomarkers play a central role, not only in the diagnosis and prognosis of posterior fossa tumors in children but also in customizing treatment plans. They anticipate patient outcomes, measure treatment responses, and assess therapeutic effectiveness. Advances in neuroimaging and treatment have significantly enhanced outcomes for children with these tumors. What is Known: • Central nervous system tumors are the most common solid neoplasms in children and adolescents, with approximately 45 to 60% of them located in the posterior fossa. • Multimodal approaches that include neurosurgery, radiation therapy, and chemotherapy are typically used to manage childhood posterior fossa tumors What is New: • Notable progress has been achieved in the diagnosis, categorization and management of posterior fossa tumors in children, leading to improvement in survival and quality of life.

Magnetic resonance imaging characteristics of pediatric pilocytic astrocytoma

PURPOSE

MRI has an important role in diagnosing pilocytic astrocytoma and post-surgical follow-up since the surgical approach has a leading role in its treatment. The purpose of our study is to provide an overview of the typical and atypical MRI findings in a series of pediatric patients with isolated-not NF1-related-pilocytic astrocytomas and to correlate specific MRI patterns with clinical variables.

METHODS

This is a cross-sectional retrospective study providing the analysis of several clinical and neuroradiological findings from a cohort of pediatric pilocytic astrocytoma, starting from the data collected in the Fondazione IRCCS Istituto Neurologico Carlo Besta (FINCB) internal Cancer Registry during an 11-year time period (January 2008-January 2019).

RESULTS

Fifty-six patients were included in the study. Median age at diagnosis was 9.4 years; a slight female prevalence was noticed (m/f ratio 44.6%/55.4%). The majority of pPAs had well-defined contours: 51 (91.1%), 47 (88.7%) were hypointense on T1-wi, all of them were hyperintense on T2-wi, 46 (90.2%) were hyperintense on FLAIR, and 48 (85.7%) were heterogeneous on T1-wi and T2-wi sequences. We found positive correlation between pPAs location and age (r = 0.017), and small degree of connection between pPAs location and gender (Cramer's V = 0.268).

CONCLUSIONS

We presented typical and atypical pPAs MRI findings. Age and tumor location were positevely correlated, while degree of connection between gender and pPAs location was small. All of this may aid clinicians, most of all neuroradiologists, neurosurgeons, and neurologists in proper diagnoses and follow-up of these specific patient population.

Deep learning based clinico-radiological model for paediatric brain tumor detection and subtype prediction

Aim

Early diagnosis of paediatric brain tumors significantly improves the outcome. The aim is to study magnetic resonance imaging (MRI) features of paediatric brain tumors and to develop an automated segmentation (AS) tool which could segment and classify tumors using deep learning methods and compare with radiologist assessment.

Methods

This study included 94 cases, of which 75 were diagnosed cases of ependymoma, medulloblastoma, brainstem glioma, and pilocytic astrocytoma and 19 were normal MRI brain cases. The data was randomized into training data, 64 cases; test data, 21 cases and validation data, 9 cases to devise a deep learning algorithm to segment the paediatric brain tumor. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the deep learning model were compared with radiologist's findings. Performance evaluation of AS was done based on Dice score and Hausdorff95 distance.

Results

Analysis of MRI semantic features was done with necrosis and haemorrhage as predicting features for ependymoma, diffusion restriction and cystic changes were predictors for medulloblastoma. The accuracy of detecting abnormalities was 90%, with a specificity of 100%. Further segmentation of the tumor into enhancing and non-enhancing components was done. The segmentation results for whole tumor (WT), enhancing tumor (ET), and non-enhancing tumor (NET) have been analyzed by Dice score and Hausdorff95 distance. The accuracy of prediction of all MRI features was compared with experienced radiologist's findings. Substantial agreement observed between the classification by model and the radiologist's given classification [K-0.695 (K is Cohen's kappa score for interrater reliability)].

Conclusions

The deep learning model had very high accuracy and specificity for predicting the magnetic resonance (MR) characteristics and close to 80% accuracy in predicting tumor type. This model can serve as a potential tool to make a timely and accurate diagnosis for radiologists not trained in neuroradiology.

Deciphering Machine Learning Decisions to Distinguish between Posterior Fossa Tumor Types Using MRI Features: What Do the Data Tell Us?

Machine learning (ML) models have become capable of making critical decisions on our behalf. Nevertheless, due to complexity of these models, interpreting their decisions can be challenging, and humans cannot always control them. This paper provides explanations of decisions made by ML models in diagnosing four types of posterior fossa tumors: medulloblastoma, ependymoma, pilocytic astrocytoma, and brainstem glioma. The proposed methodology involves data analysis using kernel density estimations with Gaussian distributions to examine individual MRI features, conducting an analysis on the relationships between these features, and performing a comprehensive analysis of ML model behavior. This approach offers a simple yet informative and reliable means of identifying and validating distinguishable MRI features for the diagnosis of pediatric brain tumors. By presenting a comprehensive analysis of the responses of the four pediatric tumor types to each other and to ML models in a single source, this study aims to bridge the knowledge gap in the existing literature concerning the relationship between ML and medical outcomes. The results highlight that employing a simplistic approach in the absence of very large datasets leads to significantly more pronounced and explainable outcomes, as expected. Additionally, the study also demonstrates that the pre-analysis results consistently align with the outputs of the ML models and the clinical findings reported in the existing literature.

MRI findings of primary intracranial sarcomas in children

BACKGROUND

Primary intracranial sarcoma is a very rare high-grade tumor. Scant reports exist on this malignancy in children, which limit the information about its imaging characteristics.

OBJECTIVE

We aimed to describe the main characteristics of primary intracranial sarcoma on MRI.

MATERIALS AND METHODS

In this cross-sectional descriptive observational study, we reviewed 18 patients (aged 1-18 years) with primary intracranial sarcomas diagnosed between 2015 and 2021.

RESULTS

The main findings were contrast enhancement (100%), diffusion restriction (78%), hemorrhage (89%), meningeal extension (67%), necrosis (67%), and supratentorial location (72%).

CONCLUSION

Primary intracranial sarcoma are typically supratentorial in location. MRI findings of primary intracranial sarcoma are similar to other intracranial malignancies.

A Radiologist's Guide to the 2021 WHO Central Nervous System Tumor Classification: Part 2-Newly Described and Revised Tumor Types

The fifth edition of the World Health Organization classification of tumors of the central nervous system (CNS), published in 2021, introduces major shifts in the classification of brain and spine tumors. These changes were necessitated by rapidly increasing knowledge of CNS tumor biology and therapies, much of which is based on molecular methods in tumor diagnosis. The growing complexity of CNS tumor genetics has required reorganization of tumor groups and acknowledgment of new tumor entities. For radiologists interpreting neuroimaging studies, proficiency with these updates is critical in providing excellent patient care. This review will focus on new or revised CNS tumor types and subtypes, beyond infiltrating glioma (described in part 1 of this series), with an emphasis on imaging features.

Characterizing Various Posterior Fossa Tumors in Children and Adults With Diffusion-Weighted Imaging and Spectroscopy

Background The posterior fossa is situated between the tentorium cerebelli above and the foramen magnum below. Vital structures like the cerebellum, the pons, and the medulla are situated within it; hence, tumors within the posterior fossa are considered one of the most critical brain lesions. Children are more likely to develop posterior fossa tumors than adults. Diffusion-weighted imaging (DWI) and magnetic resonance spectroscopy (MRS) sequences along with the conventional MRI help in providing additional information in the characterization of the various posterior fossa tumors. We hereby present a series of 30 patients with clinically suspected posterior fossa masses who underwent preoperative MRI. Objectives This study aims to differentiate the neoplastic from non-neoplastic posterior fossa mass by evaluating the diffusion restriction pattern on DWI, quantifying the apparent diffusion coefficient (ADC) map in various posterior fossa tumors, and comparing the different metabolites of various posterior fossa tumors on MRS. Results Out of the 30 patients with posterior fossa lesions, 18 were males and 12 were females. Eight of them were in the pediatric age group, while twenty-two of them were adults. Metastasis was the most common posterior fossa lesion in our study sample and was found in six patients (20%), followed by vestibular schwannomas (17%) and arachnoid cysts (13%), meningiomas, medulloblastoma, and pilocytic astrocytoma (10% each) and epidermoid, ependymoma, and hemangioblastoma (7% each). The mean ADC value of benign tumors was higher than that of malignant tumors, and this difference was found to be significant (p = 0.012). The cut-off ADC value 1.21x 10^-3mm²/s had a sensitivity of 81.82% and specificity of 80.47%. MRS metabolites played an additional role in differentiating benign from malignant tumors. Conclusion A combination of conventional MRI, DWI, ADC values, and MRS metabolites showed good diagnostic accuracy to differentiate between the various posterior fossa neoplastic tumors both in adults and children.

Apparent Diffusion Coefficient in the Differentiation of Common Pediatric Brain Tumors in the Posterior Fossa: Different Region-of-Interest Selection Methods for Time Efficiency, Measurement Reproducibility, and Diagnostic Utility

OBJECTIVES

This study aimed to explore the diagnostic ability of apparent diffusion coefficient (ADC) values obtained from different region of interest (ROI) measurements in tumor parenchyma for differentiating posterior fossa tumors (PFTs) and the correlations between ADC values and Ki-67.

METHODS

Seventy-three pediatric patients with PFTs who underwent conventional diffusion-weighted imaging were recruited in this study. Five different ROIs were manually drawn by 2 radiologists (ROI-polygon, ROI-3 sections, ROI-3-5 ovals, ROI-more ovals, and ROI-whole). The interreader/intrareader repeatability, time required, diagnostic ability, and Ki-67 correlation analysis of the ADC values based on these ROI strategies were calculated.

RESULTS

Both interreader and intrareader reliabilities were excellent for ADC values among the different ROI strategies (intraclass correlation coefficient, 0.899-0.992). There were statistically significant differences in time consumption among the 5 ROI selection methods ( P < 0.001). The time required for the ROI-3-5 ovals was the shortest (32.23 ± 5.14 seconds), whereas the time required for the ROI-whole was the longest (204.52 ± 92.34 seconds). The diagnostic efficiency of the ADC values showed no significant differences among the different ROI measurements ( P > 0.05). The ADC value was negatively correlated with Ki-67 ( r = -0.745 to -0.798, all P < 0.0001).

CONCLUSIONS

The ROI-3-5 ovals method has the best interobserver repeatability, the shortest amount of time spent, and the best diagnostic ability. Thus, it is considered an effective measurement to produce ADC values in the evaluation of pediatric PFTs.

Advanced intraoperative MRI in pediatric brain tumor surgery

Introduction: In the pediatric brain tumor surgery setting, intraoperative MRI (ioMRI) provides "real-time" imaging, allowing for evaluation of the extent of resection and detection of complications. The use of advanced MRI sequences could potentially provide additional physiological information that may aid in the preservation of healthy brain regions. This review aims to determine the added value of advanced imaging in ioMRI for pediatric brain tumor surgery compared to conventional imaging. Methods: Our systematic literature search identified relevant articles on PubMed using keywords associated with pediatrics, ioMRI, and brain tumors. The literature search was extended using the snowball technique to gather more information on advanced MRI techniques, their technical background, their use in adult ioMRI, and their use in routine pediatric brain tumor care. Results: The available literature was sparse and demonstrated that advanced sequences were used to reconstruct fibers to prevent damage to important structures, provide information on relative cerebral blood flow or abnormal metabolites, or to indicate the onset of hemorrhage or ischemic infarcts. The explorative literature search revealed developments within each advanced MRI field, such as multi-shell diffusion MRI, arterial spin labeling, and amide-proton transfer-weighted imaging, that have been studied in adult ioMRI but have not yet been applied in pediatrics. These techniques could have the potential to provide more accurate fiber tractography, information on intraoperative cerebral perfusion, and to match gadolinium-based T1w images without using a contrast agent. Conclusion: The potential added value of advanced MRI in the intraoperative setting for pediatric brain tumors is to prevent damage to important structures, to provide additional physiological or metabolic information, or to indicate the onset of postoperative changes. Current developments within various advanced ioMRI sequences are promising with regard to providing in-depth tissue information.

Application of Apparent Diffusion Coefficient Histogram Metrics for Differentiation of Pediatric Posterior Fossa Tumors : A Large Retrospective Study and Brief Review of Literature

PURPOSE

This study aimed to evaluate the application of apparent diffusion coefficient (ADC) histogram analysis to differentiate posterior fossa tumors (PFTs) in children.

METHODS

A total of 175 pediatric patients with PFT, including 75 pilocytic astrocytomas (PA), 59 medulloblastomas, 16 ependymomas, and 13 atypical teratoid rhabdoid tumors (ATRT), were analyzed. Tumors were visually assessed using DWI trace and conventional MRI images and manually segmented and post-processed using parametric software (pMRI). Furthermore, tumor ADC values were normalized to the thalamus and cerebellar cortex. The following histogram metrics were obtained: entropy, minimum, 10th, and 90th percentiles, maximum, mean, median, skewness, and kurtosis to distinguish the different types of tumors. Kruskal Wallis and Mann-Whitney U tests were used to evaluate the differences. Finally, receiver operating characteristic (ROC) curves were utilized to determine the optimal cut-off values for differentiating the various PFTs.

RESULTS

Most ADC histogram metrics showed significant differences between PFTs (p < 0.001) except for entropy, skewness, and kurtosis. There were significant pairwise differences in ADC metrics for PA versus medulloblastoma, PA versus ependymoma, PA versus ATRT, medulloblastoma versus ependymoma, and ependymoma versus ATRT (all p < 0.05). Our results showed no significant differences between medulloblastoma and ATRT. Normalized ADC data showed similar results to the absolute ADC value analysis. ROC curve analysis for normalized ADC_median values to thalamus showed 94.9% sensitivity (95% CI: 85-100%) and 93.3% specificity (95% CI: 87-100%) for differentiating medulloblastoma from ependymoma.

CONCLUSION

ADC histogram metrics can be applied to differentiate most types of posterior fossa tumors in children.

The Diagnostic Efficiency of Quantitative Diffusion Weighted Imaging in Differentiating Medulloblastoma from Posterior Fossa Tumors: A Systematic Review and Meta-Analysis

Medulloblastoma (MB) is considered the most common and highly malignant posterior fossa tumor (PFT) in children. The accurate preoperative diagnosis of MB is beneficial in choosing the appropriate surgical methods and treatment strategies. Diffusion-weighted imaging (DWI) has improved the accuracy of differential diagnosis of posterior fossa tumors. Nonetheless, further studies are needed to confirm its value for clinical application. This study aimed to evaluate the performance of DWI in differentiating MB from other PFT. A literature search was conducted using databases PubMed, Embase, and Web of Science for studies reporting the diagnostic performance of DWI for PFT from January 2000 to January 2022. A bivariate random-effects model was employed to evaluate the pooled sensitivities and specificities. A univariable meta-regression analysis was used to assess relevant factors for heterogeneity, and subgroup analyses were performed. A total of 15 studies with 823 patients were eligible for data extraction. Overall pooled sensitivity and specificity of DWI were 0.94 (95% confident interval [CI]: 0.89-0.97) and 0.94 (95% CI: 0.90-0.96) respectively. The area under the curve (AUC) of DWI was 0.98 (95% CI: 0.96-0.99). Heterogeneity was found in the sensitivity (I² = 62.59%) and the specificity (I² = 35.94%). Magnetic field intensity, region of interest definition and DWI diagnostic parameters are the factors that affect the diagnostic performance of DWI. DWI has excellent diagnostic accuracy for differentiating MB from other PFT. Hence, it is necessary to set DWI as a routine examination sequence for posterior fossa tumors.

The Current State of Radiotherapy for Pediatric Brain Tumors: An Overview of Post-Radiotherapy Neurocognitive Decline and Outcomes

Tumors of the central nervous system are the most common solid malignancies diagnosed in children. While common, they are also found to have some of the lowest survival rates of all malignancies. Treatment of childhood brain tumors often consists of operative gross total resection with adjuvant chemotherapy or radiotherapy. The current body of literature is largely inconclusive regarding the overall benefit of adjuvant chemo- or radiotherapy. However, it is known that both are associated with conditions that lower the quality of life in children who undergo those treatments. Chemotherapy is often associated with nausea, emesis, significant fatigue, immunosuppression, and alopecia. While radiotherapy can be effective for achieving local control, it is associated with late effects such as endocrine dysfunction, secondary malignancy, and neurocognitive decline. Advancements in radiotherapy grant both an increase in lifetime survival and an increased lifetime for survivors to contend with these late effects. In this review, the authors examined all the published literature, analyzing the results of clinical trials, case series, and technical notes on patients undergoing radiotherapy for the treatment of tumors of the central nervous system with a focus on neurocognitive decline and survival outcomes.

Neuroimaging in cerebellar ataxia in childhood: A review

Ataxia is one of the most common pediatric movement disorders and can be caused by a large number of congenital and acquired diseases affecting the cerebellum or the vestibular or sensory system. It is mainly characterized by gait abnormalities, dysmetria, intention tremor, dysdiadochokinesia, dysarthria, and nystagmus. In young children, ataxia may manifest as the inability or refusal to walk. The diagnostic approach begins with a careful clinical history including the temporal evolution of ataxia and the inquiry of additional symptoms, is followed by a meticulous physical examination, and, depending on the results, is complemented by laboratory assays, electroencephalography, nerve conduction velocity, lumbar puncture, toxicology screening, genetic testing, and neuroimaging. Neuroimaging plays a pivotal role in either providing the final diagnosis, narrowing the differential diagnosis, or planning targeted further workup. In this review, we will focus on the most common form of ataxia in childhood, cerebellar ataxia (CA). We will discuss and summarize the neuroimaging findings of either the most common or the most important causes of CA in childhood or present causes of pediatric CA with pathognomonic findings on MRI. The various pediatric CAs will be categorized and presented according to (a) the cause of ataxia (acquired/disruptive vs. inherited/genetic) and (b) the temporal evolution of symptoms (acute/subacute, chronic, progressive, nonprogressive, and recurrent). In addition, several illustrative cases with their key imaging findings will be presented.

Magnetic Resonance Imaging of Unusual Neoplasms Related to Foramen of Luschka: A Review for Differential Diagnosis

There are many types of neoplasms in or around the foramen of Luschka (FL), and definitive diagnosis in some cases requires knowledge of imaging findings. The uncommon and challenging neoplasms with FL involvement considered in this study are exophytic brainstem glioma, primary glioblastoma of the cerebellopontine angle (CPA), primary anaplastic ependymoma of the CPA, choroid plexus papilloma of the FL, solitary FL choroid plexus metastasis, extraskeletal myxoid chondrosarcoma of the jugular foramen, paraganglioma of the jugular foramen, exostosis of the jugular foramen, psammomatous meningioma in the lateral cerebellar medullary cistern, epidermoid tumor of the fourth ventricle, and a hypoglossal schwannoma. These neoplasms may have overlapping clinical and imaging features, but some have relatively distinct imaging features. Knowledge of the key clinical and magnetic resonance imaging features of these unusual lesions with FL involvement is important for radiologists to improve diagnostic ability and to assist the referring physician in the appropriate management of the patient.

Outcome of Childhood Cerebellar Pilocytic Astrocytoma: A Series With 20 Years of Follow Up

Background: Cerebellar pilocytic astrocytoma (PCA) is one of the few CNS tumors that can be cured with gross-total removal (GTR). In this series, we had 39 patients diagnosed with cerebellar PCA, 27 patients (70%) had GTR, and mean follow-up period was 62 months with no tumor recurrence.

Objective: To assess the long-term outcome of childhood cerebellar PCA treated at our institute during the period 2000-2020 and to highlight our surgical protocol.

Methodology: Retrospective review of all patients under 18 years of age who were diagnosed with cerebellar PCA and had surgical excision between 2000 and 2020 at the Medical City of King Saud University.

Results: The study included 39 patients: 17 males and 22 females, the mean age was 8.4 years. Radiologically, the tumor was solid in eight patients, cystic in 15 patients, and mixed components were found in 16 patients. The lesion was located in the right cerebellar hemisphere in 12 patients, left cerebellar hemisphere in five patients, and midline 22 patients. The tumor size ranged from 2 to 7 cm in its greatest diameter, it was <5 cm in 13 patients and >5 cm in 26 patients. Thirty-one patients had preoperative hydrocephalus. GTR of the tumor was achieved in 27 patients and subtotal resection (STR) was done in 12 patients, 18 patients required permanent ventriculoperitoneal (V-P) shunt, and five patients had postoperative radiotherapy. Postoperative complications included infection in two patients, cerebellar mutism in two patients, and significant neurologic disability in four patients. The duration of follow-up ranged from 0 to 240 months (mean follow-up period: 62.0 months). The outcome at 10 years was good in 30 patients, fair in four patients, poor in four patients, and one patient died. Recurrence was documented in nine patients, seven of them had GTR and two had STR.

Conclusion: GTR, if achievable, is curative for childhood cerebellar PCA. Many posterior fossa surgical complications could be avoided with watertight dural closure. Although new dural substitutes are available we prefer using autologous grafts (pericranium). It is easy to harvest pericranial graft from the external ventricular drain (EVD) site. The insertion of EVD synchronously with GTR of the tumor and gradual weaning of EVD could avoid the insertion of V-P shunt.

Dynamic susceptibility contrast and diffusion-weighted MRI in posterior fossa pilocytic astrocytoma and medulloblastoma

BACKGROUND AND PURPOSE

The utility of perfusion MRI in distinguishing between pilocytic astrocytoma (PA) and medulloblastoma (MB) is unclear. This study aimed to evaluate the diagnostic and prognostic performance of dynamic susceptibility contrast (DSC)-MRI parameters and apparent diffusion coefficient (ADC) values between PA and MB.

METHODS

Between January 2012 and August 2021, 49 (median, 7 years [range, 1-28 years]; 28 females) and 35 (median, 8 years [1-24 years]; 12 females) patients with pathologically confirmed PA and MB, respectively, were included. The normalized relative cerebral blood volume and flow (nrCBV and nrCBF) and mean and minimal normalized ADC (nADCmean and nADCmin) values were calculated using volume-of-interest analyses. Diagnostic performance and Pearson's correlation with progression-free survival were also evaluated.

RESULTS

The MB group showed a significantly higher nrCBV and nrCBF (nrCBV: 1.69 [0.93-4.23] vs. 0.95 [range, 0.37-2.28], p = .0032; nrCBF: 1.62 [0.93-3.16] vs. 1.07 [0.46-2.26], p = .0084) and significantly lower nADCmean and nADCmin (nADCmean: 0.97 [0.70-1.68] vs. 2.21 [1.44-2.80], p < .001; nADCmin: 0.50 [0.19-0.89] vs. 1.42 [0.89-2.20], p < .001) than the PA group. All parameters exhibited good diagnostic ability (accuracy >0.80) with nADCmin achieving the highest score (accuracy = 1). A moderate correlation was found between nADCmean and progression-free survival for MB (r = 0.44, p = .0084).

CONCLUSIONS

DSC-MRI parameters and ADC values were useful for distinguishing between PA and MB. A lower ADC indicated an unfavorable MB prognosis, but the DSC-MRI parameters did not correlate with progression-free survival in either group.

Magnetic Resonance Imaging in the Contemporary Management of Medulloblastoma: Current and Emerging Applications

Medulloblastoma, the most common malignant primary brain tumor in children, is now considered to comprise of four distinct molecular subgroups-wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4 medulloblastoma, each associated with distinct developmental origins, unique transcriptional profiles, diverse phenotypes, and variable clinical behavior. Due to its exquisite anatomic resolution, multiparametric nature, and ability to image the entire craniospinal axis, magnetic resonance imaging (MRI) is the preferred and recommended first-line imaging modality for suspected brain tumors including medulloblastoma. Preoperative MRI can reliably differentiate medulloblastoma from other common childhood posterior fossa masses such as ependymoma, pilocytic astrocytoma, and brainstem glioma. On T1-weighted images, medulloblastoma is generally iso- to hypointense, while on T2-weighted images, the densely packed cellular component of the tumor is significantly hypointense and displays restricted diffusion on diffusion-weighted imaging. Following intravenous gadolinium, medulloblastoma shows significant but variable and heterogeneous contrast enhancement. Given the propensity of neuraxial spread in medulloblastoma, sagittal fat-suppressed T1-postcontrast spinal MRI is recommended to rule out leptomeningeal metastases for accurate staging. Following neurosurgical excision, postoperative MRI done within 24-48 h confirms the extent of resection, accurately quantifying residual tumor burden imperative for risk assignment. Post-treatment MRI is needed to assess response and effectiveness of adjuvant radiotherapy and systemic chemotherapy. After completion of planned therapy, surveillance MRI is recommended periodically on follow-up for early detection of recurrence for timely institution of salvage therapy, as well as for monitoring treatment-related late complications. Recent studies suggest that preoperative MRI can reliably identify SHH and Group 4 medulloblastoma but has suboptimal predictive accuracy for WNT and Group 3 tumors. In this review, we focus on the role of MRI in the diagnosis, staging, and quantifying residual disease; post-treatment response assessment; and periodic surveillance, and provide a brief summary on radiogenomics in the contemporary management of medulloblastoma.

Radiomics and radiogenomics in pediatric neuro-oncology: A review

The current era of advanced computing has allowed for the development and implementation of the field of radiomics. In pediatric neuro-oncology, radiomics has been applied in determination of tumor histology, identification of disseminated disease, prognostication, and molecular classification of tumors (ie, radiogenomics). The field also comes with many challenges, such as limitations in study sample sizes, class imbalance, generalizability of the methods, and data harmonization across imaging centers. The aim of this review paper is twofold: first, to summarize existing literature in radiomics of pediatric neuro-oncology; second, to distill the themes and challenges of the field and discuss future directions in both a clinical and technical context.

The impact of magnetic resonance imaging spectroscopy parameters on differentiating between paediatric medulloblastoma and ependymoma

Introduction

The distinction of medulloblastomas and ependymomas plays an important role in the care plans and prognosis of children. We aimed to investigate the role of magnetic resonance spectroscopy (MRS) in the differentiation between medulloblastomas and ependymomas in children.

Materials and methods

The institutional review board approved this prospective study. The brain magnetic resonance imaging protocol including axial multivoxel spectroscopy with a TE of 144 ms was assessed in 49 patients, who were divided into 2 groups: 40 patients with medulloblastomas and 9 patients with ependymomas. Receiver operating characteristic (ROC) curve analysis and the Youden index were utilized to determine the best cut-off, sensitivity, specificity, and area under the curve (AUC) values of the independent spectroscopy parameters.

Results

The choline level (Cho) and the choline/creatine (Cho/Cr) and choline/N-acetyl aspartate (Cho/NAA) ratios of medulloblastomas were significantly higher than those of ependymomas (p < 0.05). A Cho/NAA cut-off value of 1.24 to predict the diagnosis of medulloblastoma yielded the highest AUC and sensitivity of 80.3% and 97.5%, respectively, while a Cho cut-off value of 4.64 produced the highest specificity value of 88.9%.

Conclusions

Our findings suggest that Cho and Cho/NAA derived from MRS could serve as differential factors between paediatric medulloblastomas and ependymomas. Among those, a Cho/NAA cut-off value of 1.24 to predict the diagnosis of medulloblastoma generated the highest accuracy.

Medulloblastoma in an Adult Female Patient: A Rare Presentation

Medulloblastoma (MB) is an aggressive malignant tumor of the posterior fossa of the CNS that mainly affects children younger than 15 years of age. It is uncommon in the adult population compared to children. Any adult patient presenting with cerebellar mass must be evaluated with brain tissue biopsy to rule out MB. Our patient is a 27-year-old female who presented with sudden onset of frontal headache and was diagnosed with MB.

Role of MRI in Differentiating Various Posterior Cranial Fossa Space-Occupying Lesions Using Sensitivity and Specificity: A Prospective Study

BACKGROUND

Any abnormal space-occupying posterior fossa lesion may directly involve the vital structures like the brain stem, cranial nerves, cerebellum, vertebrobasilar artery, and venous sinuses, which makes the surgical approach and total excision very difficult. Hence for these reasons, precise evaluation of posterior fossa lesion with MRI is a must to visualize the vital structures, which helps in planning and safe surgery.  Objective: This study aimed to evaluate the added value of diffusion-weighted imaging and magnetic resonance spectroscopy in the localization, extension, characterization, differentiation of various posterior fossa space-occupying lesions, and correlating with the histopathological result.

MATERIALS AND METHODS

This prospective study comprised of 40 patients who were suspected with posterior fossa space-occupying lesions on basis of clinical features or on CT scan. All patients were evaluated using conventional as well as newer MRI techniques using Siemens 1.5 Tesla MRI scanner (Siemens Medical System, Erlangen, Germany). Diffusion-weighted imaging (DWI) was done in all patients and magnetic resonance spectroscopy (MRS) was done in 27 patients. Based on the MRI findings, various posterior fossa lesions were classified as neoplastic or non-neoplastic. The neoplastic lesions were further classified as benign and malignant. The MRI findings were correlated with histopathological findings or follow-up.

STATISTICAL ANALYSIS

Independent sample t-test was used to compare the mean apparent diffusion coefficient (ADC) values of various posterior fossa space-occupying lesions. Receiver operating characteristic (ROC) curve analysis was done to determine the optimal cut-off mean ADC values and choline/creatinine (Cho/cr) ratios for various benign and malignant posterior fossa tumors.

RESULTS

Of 40 patients with posterior fossa lesions, 23 were males and 17 were females with a mean age of 34.67±1.93[SD] years. Metastases were the most common posterior fossa lesions in our study sample and found in seven patients (17.5%) followed by vestibular schwannomas and brainstem gliomas in five patients (12.5%) each, demyelinating lesion in four patients (10%), tubercular abscess in three patients (7.5%), hemangioblastoma, tuberculoma, arachnoid cyst, epidermoid cyst, pilocytic astrocytoma, low-grade glioma in two patients (5%) each, meningioma, medulloblastoma, pyogenic abscess and high-grade glioma in one patient (2.5%) each. The mean ADC value of benign tumors was higher than that of malignant tumors and this difference was found to be significant (p = 0.019). The cut-off ADC value 1.022 x 10^-3mm²/s had a sensitivity of 78.6% and specificity of 66.7%. MRS played important role in differentiating neoplastic from non-neoplastic lesions and benign from malignant tumors. The cut-off Cho/cr ratio of 1.25 had a sensitivity of 66.7%, specificity of 85.7% to differentiate benign from malignant tumors.

CONCLUSION

Conventional MRI sequences able to diagnose most of the benign-appearing lesions of posterior fossa, however, adding advanced MRI sequences like diffusion-weighted imaging and MR spectroscopy helps us to differentiate and diagnose various posterior fossa lesions even closer to the actual histopathological diagnosis.

Extra-axial tentorial medulloblastoma: a rare presentation of a common posterior fossa tumour

Medulloblastoma is a common paediatric posterior fossa tumour typically presenting as midline intra-axial mass involving the cerebellar vermis and/or roof of fourth ventricle with typical radiological features. These can be extra-axial in extremely rare instances with less than 50 cases reported so far in literature. We present a case of 18-year-old boy presenting with ataxia and headache. MRI showed dural mass (involving the left tentorium cerebellum) with typical imaging features of extra-axial lesion. The patient underwent near total excision of the tumour. Histopathology along with immunohistochemistry revealed the mass to be medulloblastoma. We present this case to highlight rarity of this location for medulloblastoma and the importance of considering this in the differential diagnosis of atypical posterior fossa extra-axial lesions. This can help in performing other relevant preoperative workup similar on the lines of medulloblastoma and planning of relevant management.

Neuroophthalmic Manifestations of Intracranial Tumours in Children

BACKGROUND

All children between 0 and 16 years presenting with brain tumours confirmed by Magnetic Resonance Imaging (MRI) and treated surgically in our institute were included in this study.

OBJECTIVE

The aim of this study is to evaluate the neuroophthalmic and clinical characteristics of intracranial space occupying lesions in children.

METHODS

Neuroophthalmic manifestations along with location of the tumour by contrast-enhanced MRI, type of surgical intervention, and postoperative histopathological diagnosis were evaluated.

RESULTS

In pediatric brain tumours, male preponderance was seen and supratentorial location was more common in general, while in older children, infratentorial tumours were more common than supratentorial tumours. Headache, vomiting, and cerebellar signs were the commonest neurological features. Diminution of vision, diplopia, and strabismus were the commonest ophthalmic symptoms. Papilledema, ophthalmoparesis, and nystagmus were the most frequent ophthalmological signs. Neurological manifestations of seizures, altered sensorium and motor deficits were more frequently seen in supratentorial tumours, while cranial nerve involvement and ataxia were seen in infratentorial tumours. Ophthalmological manifestations including diplopia, strabismus, ophthalmoparesis, and nystagmus were more frequently seen in infratentorial tumours. Astrocytoma was the most frequent histopathological diagnosis followed by medulloblastoma.

CONCLUSION

Diagnosis of pediatric intracranial tumours is complex and requires a multidisciplinary approach for prompt management. An ophthalmologist should have a high index of suspicion for brain tumours especially in patients presenting with common ocular symptoms like diminution of vision, diplopia, and strabismus without any neurological symptoms.

Valores del coeficiente de difusión aparente en el diagnóstico diferencial de los tumores de fosa posterior en población pediátrica de Colombia

Introducción. Los tumores de la fosa posterior son frecuentes en la población pediátrica y requieren de una adecuada caracterización mediante resonancia magnética (RM) estructural y técnicas avanzadas de RM para lograr un enfoque terapéutico apropiado. Objetivo. Determinar la utilidad de los valores del coeficiente de difusión aparente (ADC cuantitativo) en el diagnóstico diferencial de los tumores de la fosa posterior en población pediátrica de un hospital de referencia en Bogotá D.C., Colombia. Materiales y métodos. Estudio de validez de prueba diagnóstica realizado en 28 pacientes pediátricos diagnosticados con tumor de fosa posterior entre 2017-2019 en la Fundación Hospital de la Misericordia, hospital de IV nivel de complejidad. Se midieron los valores de ADC, los cuales fueron comparados con  el diagnóstico histopatológico como estándar de oro, obteniendo datos de sensibilidad, especificidad, valores predictivos positivos y negativos.. Las diferencias entre medianas fueron determinadas mediante la prueba de Kruskall-Wallis. El valor p entre el valor ADC y el estándar de oro se calculó con la prueba de X2 de Pearson, con un nivel de significancia de p<0.05. Resultados. La edad media fue 83.9 meses (DE=57 meses) y 64.28% fueron niños. El tumor más frecuente fue el meduloblastoma (39.29%). Para el diagnóstico de meduloblastoma se estableció un valor ADC cuantitativo de 0.6210x10-³mm²/s, obteniéndose una sensibilidad y especificidad de 81.82% y 76.47%, respectivamente, y para el diagnóstico de astrocitoma pilocítico, un ADC cuantitativo de 1.03x10-³mm²/s, con una sensibilidad de 66.67% y una especificidad de 89.40%-. Conclusiones. El valor ADC cuantitativo es útil para clasificar y diferenciar los tumores de la fosa posterior en población pediátrica colombiana, mostrando una relación inversamente proporcional con el grado histológico tumoral.

A Diagnostic Algorithm for Posterior Fossa Tumors in Children: A Validation Study

BACKGROUND AND PURPOSE

Primary posterior fossa tumors comprise a large group of neoplasias with variable aggressiveness and short and long-term outcomes. This study aimed to validate the clinical usefulness of a radiologic decision flow chart based on previously published neuroradiologic knowledge for the diagnosis of posterior fossa tumors in children.

MATERIALS AND METHODS

A retrospective study was conducted (from January 2013 to October 2019) at 2 pediatric referral centers, Children's Hospital of Philadelphia, United States, and Great Ormond Street Hospital, United Kingdom. Inclusion criteria were younger than 18 years of age and histologically and molecularly confirmed posterior fossa tumors. Subjects with no available preoperative MR imaging and tumors located primarily in the brain stem were excluded. Imaging characteristics of the tumors were evaluated following a predesigned, step-by-step flow chart. Agreement between readers was tested with the Cohen κ, and each diagnosis was analyzed for accuracy.

RESULTS

A total of 148 cases were included, with a median age of 3.4 years (interquartile range, 2.1-6.1 years), and a male/female ratio of 1.24. The predesigned flow chart facilitated identification of pilocytic astrocytoma, ependymoma, and medulloblastoma sonic hedgehog tumors with high sensitivity and specificity. On the basis of the results, the flow chart was adjusted so that it would also be able to better discriminate atypical teratoid/rhabdoid tumors and medulloblastoma groups 3 or 4 (sensitivity = 75%-79%; specificity = 92%-99%). Moreover, our adjusted flow chart was useful in ruling out ependymoma, pilocytic astrocytomas, and medulloblastoma sonic hedgehog tumors.

CONCLUSIONS

The modified flow chart offers a structured tool to aid in the adjunct diagnosis of pediatric posterior fossa tumors. Our results also establish a useful starting point for prospective clinical studies and for the development of automated algorithms, which may provide precise and adequate diagnostic tools for these tumors in clinical practice.

Neuroimaging of pediatric infratentorial tumors and the value of diffusion-weighted imaging (DWI) in determining tumor grade

BACKGROUND

Diffusion-weighted imaging (DWI) provides information about the cellular density of tumors. This feature is useful in grading and identifying different tumor types.

PURPOSE

To assess the value of diffusion restriction and apparent diffusion coefficient (ADC) values in differentiating pediatric infratentorial tumors.

MATERIAL AND METHODS

This was a retrospective review of the magnetic resonance imaging (MRI) of 82 children (age range 1-16 years) with infratentorial tumors. Histopathological grading after surgical excision/biopsy was categorized as low grade (WHO grades I and II) (n = 31; 29 pilocytic astrocytomas, 2 ependymomas) and high grade (WHO grade III and IV) (n = 51; 40 medulloblastomas, 8 anaplastic ependymomas, 1 anaplastic astrocytoma, 2 atypical rhabdoid teratoid tumors [ATRT]). MRI features and ADC values were compared among tumor types and grades using a two-tailed t test, Mann-Whitney U test for continuous data and Chi-square test for categorical variables.

RESULTS

Diffusion restriction and low ADC value was a feature of high-grade tumors (P<0.001). The mean ADC values of the low-grade and high-grade tumors were 1.567 × 10^-3mm²/s and 0.661 × 10^-3mm²/s, respectively. Using 0.9 × 10^-3mm²/s as the cut-off value, the sensitivity, specificity, positive and negative predictive values for differentiating the grades was 87%, 100%, 100%, and 81.8%, respectively. Significant differences were found between the mean ADC values of the individual tumor types (P<0.05), except between medulloblastoma and ATRT.

CONCLUSION

ADC values and visual assessment of diffusion restriction are useful in tumor grading. The individual tumor types can be identified by an algorithmic approach, using DWI in conjunction with other described MRI features.

Intraoperative consultation in the diagnosis of posterior fossa brain tumors following the 2016 WHO update

OBJECTIVE

Intraoperative crush/squash smear or frozen section consultation is routinely performed at several centers and offers rapid onsite assessment of tumor type and provides invaluable information to the neurosurgeons. The WHO classification of central nervous system neoplasms underwent a paradigm shift in 2016 with the incorporation of molecular data with the morphological features, such that several new entities came to be distinctly defined. With this paper, we present our experience at intraoperative consultation of brain tumors arising in posterior fossa and aim to apprise the pathologists with the spectrum of cytomorphologic appearances that can occur during such consultation and highlight the diagnostic dilemmas and pitfalls encountered in this setting.

METHODS

This is a retrospective observational study illustrating the salient morphological features of commonly encountered brain tumors arising in the posterior fossa (prototype example of each type) reported at our institute over a period of seven years. Both squash smears and rapid snap frozen section were prepared and stained with Toluidine blue and rapid hematoxylin and eosin (H&E) stains.

RESULTS AND CONCLUSIONS

While the majority of tumors at this location comprise of pilocytic astrocytoma, ependymoma, and medulloblastoma, some rare examples may also arise; common differentials must be considered and prudently excluded to arrive at the diagnosis which is crucial in guiding the neurosurgeon. Both squash smears and rapid frozen section should be prepared and complement each other for rapid on-site evaluation.

The diagnostic function of intravoxel incoherent motion for distinguishing between pilocytic astrocytoma and ependymoma

Introduction

Intravoxel incoherent motion (IVIM) imaging concurrently measures diffusion and perfusion parameters and has potential applications for brain tumor classification. However, the effectiveness of IVIM for the differentiation between pilocytic astrocytoma and ependymoma has not been verified. The aim of this study was to determine the potential diagnostic role of IVIM for the distinction between ependymoma and pilocytic astrocytoma.

Methods

Between February 2019 and October 2020, 22 children (15 males and 7 females; median age 4 years) with either ependymoma or pilocytic astrocytoma were recruited for this prospective study. IVIM parameters were fitted using 7 b-values (0–1,500 s/mm²), to develop a bi-exponential model. The diffusivity (D), perfusion fraction (f), and pseudo diffusivity (D*) were measured in both tumors and the adjacent normal-appearing parenchyma. These IVIM parameters were compared using the Mann-Whitney U test. Receiver operating characteristic (ROC) curve analysis was employed to assess diagnostic performance.

Results

The median D values for ependymoma and pilocytic astrocytoma were 0.87 and 1.25 × 10⁻³ mm²/s (p < 0.05), respectively, whereas the f values were 0.11% and 0.15% (p < 0.05). The ratios of the median D values for ependymoma and pilocytic astrocytoma relative to the median D values for the adjacent, normal-appearing parenchyma were 1.45 and 2.10 (p < 0.05), respectively. ROC curve analysis found that the D value had the best diagnostic performance for the differentiation between pilocytic astrocytoma and ependymoma, with an area under the ROC curve of 1.

Conclusion

IVIM is a beneficial, effective, non-invasive, and endogenous-contrast imaging technique. The D value derived from IVIM was the most essential factor for differentiating ependymoma from pilocytic astrocytoma.

Imaging pitfalls in paediatric posterior fossa neoplastic and non-neoplastic lesions

Paediatric posterior fossa lesions can have much overlap in their clinical and radiological presentation. There are, however, a number of key imaging features that can help the reading radiologist to distinguish tumours from important tumour mimics which are often inflammatory or metabolic entities. This pictorial review provides a number of important cases that proved challenging on imaging and illustrates some common pitfalls when interpreting lesions in the posterior fossa in children. Not everything that is abnormal will be a tumour, but often other causes are overlooked and misinterpreted as tumours, leading to great morbidity for that child. This article highlights some lesions that were mistaken as tumours and will introduce the reader to less commonly seen pathologies which are important to consider on a differential list for this location.

Measurement of Apparent Diffusion Coefficient (ADC) Values of Ependymoma and Medulloblastoma Tumors: a Patient-based Study

Background:

Some brain tumors such as ependymoma and Medulloblastoma have similar MR images which may result to undifferentiated them from each other.

Objective:

This study aimed to compare the apparent diffusion coefficient (ADC) of two different cerebellar pediatric tumors, including ependymoma and medulloblastoma which have shown similar clinical images in conventional magnetic resonance imaging (MRI) methods.

Material and Methods:

In this analytical study, thirty six pediatric patients who were suspected to have the mentioned tumors according to their CT image findings were included in this study. The patients were subjected to conventional MRI protocols followed by diffusion weighted imaging (DWI) and ADC values of the tumors were calculated automatically using MRI scanner software.

Results:

The mean (± SD) ADC value for ependymoma (1.2± 0.06 ×10^-3 mm²/s) was significantly higher than medulloblastoma (0.87 ± 0.02 ×10^-3 mm²/s) (p = 0.041). Moreover, the maximum ADC value of ependymoma was considerably different in comparison with medulloblastoma (1.4 ×10^-3 mm²/s and 0.96×10^-3 mm²/s, respectively; p = 0.035). Furthermore, the minimum ADC value of ependymoma was higher compared to medulloblastoma (1.0 ×10^-3 mm²/s and 0.61×10^-3 mm²/s, respectively), but there was not significant (p = 0.067).

Conclusion:

Evaluation of ADC values for ependymoma and medulloblastoma is a reliable method to differentiate these two malignancies. This is due to different ADC values reflected during the evaluation.

Perfusion-weighted techniques in MRI grading of pediatric cerebral tumors: efficiency of dynamic susceptibility contrast and arterial spin labeling

PURPOSE

Dynamic susceptibility contrast (DSC) and arterial spin labeling (ASL) perfusion MRI are applied in pediatric brain tumor grading, but their value for clinical daily practice remains unclear. We explored the ability of ASL and DSC to distinguish low- and high-grade lesions, in an unselected cohort of pediatric cerebral tumors.

METHODS

We retrospectively compared standard perfusion outcomes including blood volume, blood flow, and time parameters from DSC and ASL at 1.5T or 3T MRI scanners of 46 treatment-naive patients by drawing ROI via consensus by two neuroradiologists on the solid portions of every tumor. The discriminant abilities of perfusion parameters were evaluated by receiver operating characteristic (ROC) over the entire cohort and depending on the tumor location and the magnetic field.

RESULTS

ASL and DSC parameters showed overall low to moderate performances to distinguish low- and high-grade tumors (area under the curve: between 0.548 and 0.697). Discriminant abilities were better for tumors located supratentorially (AUC between 0.777 and 0.810) than infratentorially, where none of the metrics reached significance. We observed a better differentiation between low- and high-grade cancers at 3T than at 1.5-T. For infratentorial tumors, time parameters from DSC performed better than the commonly used metrics (AUC ≥ 0.8).

CONCLUSION

DSC and ASL show moderate abilities to distinguish low- and high-grade brain tumors in an unselected cohort. Absolute value of K2, TMAX, tMIP, and normalized value of TMAX of the DSC appear as an alternative to conventional parameters for infratentorial tumors. Three Tesla evaluation should be favored over 1.5-Tesla.

Brain stem gliomas and current landscape

PURPOSE

CNS malignancies are currently the most common cause of disease related deaths in children. Although brainstem gliomas are invariably fatal cancers in children, clinical studies against this disease are limited. This review is to lead to a succinct collection of knowledge of known biological mechanisms of this disease and discuss available therapeutics.

METHODS

A hallmark of brainstem gliomas are mutations in the histone H3.3 with the majority of cases expressing the mutation K27M on histone 3.3. Recent studies using whole genome sequencing have revealed other mutations associated with disease. Current standard clinical practice may merely involve radiation and/or chemotherapy with little hope for long term survival. Here we discuss the potential of new therapies.

CONCLUSION

Despite the lack of treatment options using frequently practiced clinical techniques, immunotherapeutic strategies have recently been developed to target brainstem gliomas. To target brainstem gliomas, investigators are evaluating the use of broad non-targeted therapy with immune checkpoint inhibitors. Alternatively, others have begun to explore adoptive T cell strategies against these fatal malignancies.

Survival after therapy for pediatric ependymoma in a tertiary care center in Saudi Arabia

BACKGROUND

There is limited data from Saudi Arabia on the demographic characteristics, outcomes and effectiveness of different treatment modalities in children with intracranial ependymoma.

OBJECTIVE

Study the characteristics of pediatric ependymoma and outcomes of treatment modalities in Saudi Arabia.

DESIGN

Retrospective.

SETTING

Tertiary care center.

PATIENTS AND METHODS

Children with intracranial ependymoma who were younger than 14 years of age and treated between 2006 and 2015 were included in the study. Patients with prior radiation, chemo-therapy, or surgical resection at other centers were excluded.

MAIN OUTCOME MEASURES

Kaplan-Meier survival curves were used to estimate the event-free (EFS) and overall survival (OS) rates of the patients.

SAMPLE SIZE

22.

RESULTS

Of the 22 children, 4 (18.2%) were less than three years old. All intracranial ependymomas had upfront surgical resection of the primary tumor. Gross total resection was achievable in 9 (42.9%) cases and subtotal resection in another 9 (42.9%). Near-total resection was done in 3 (14.3%) cases. Median time from surgery to start of radiotherapy was 62 days. RT was given to 17 (77.3%) patients. Both mean and median RT dose was 55.8 Gy. Only 5 (22.7%) of the children received chemotherapy. The median duration of follow-up was 5.38 years and the median time for EFS was 2.27 years. The cumulative OS rate of the study was 44.5%. The cumulative EFS survival rate of the study was 18.6%. Among demographic, pathological, radiological features, none had a statistically significant effect on the survival.

CONCLUSIONS

The outcomes are comparable to those reported by international investigators for similar populations. Further improvements can be achieved by avoiding delays in radiation therapy and adding molecular staging.

LIMITATIONS

The limited number of cases, retrospective nature, lack of molecular biology and size of the tumors.

CONFLICT OF INTEREST

None.

The Role of Apparent Diffusion Coefficient in the Differentiation between Cerebellar Medulloblastoma and Brainstem Glioma

For certain clinical circumstances, the differentiation between cerebellar medulloblastoma and brainstem glioma is essential. We aimed to evaluate the role played by the apparent diffusion coefficient (ADC) values in the differentiation between cerebellar medulloblastomas and brainstem gliomas in children. The institutional review board approved this prospective study. Brain magnetic resonance imaging (MRI), including diffusion-weighted imaging (DWI) and ADC, was assessed in 32 patients (median age: 7.0 years), divided into two groups, a medulloblastoma group (group 1, n = 22) and a brainstem glioma group (group 2, n = 10). The Mann-Whitney U test was utilized to compare tumor ADCmax, ADCmin, ADCmean, and ADCsd values, and their ratios with the parenchyma values between the two groups. Receiver operating characteristic (ROC) curve analysis and the Youden index were used to calculate the cut-off value, along with the area under the curve (AUC), sensitivity, and specificity. The median ADCmax, ADCmin, and ADCmean values were significantly higher in group 2 than in group 1 (p < 0.05). The median ratios of ADCmin and ADCmean to the parenchyma were significantly higher in group 2 than in group 1 (p < 0.05). The ROC analysis showed that the AUC for the ADCmean ratio was the highest among these parameters, at 98.2%. The ADCmean tumor to parenchyma ratio was a significant and effective parameter for the differentiation between pediatric medulloblastomas and brainstem gliomas.

The Effects of Applying Apparent Diffusion Coefficient Parameters on the Differentiation between Fourth Ventricular Ependymoma and Diffuse Intrinsic Pontine Glioma

Distinguishing the fourth ventricular ependymoma from diffuse intrinsic pontine glioma (DIPG) is essential to improve the treatment strategy between these two tumor types. We attempted to evaluate the effects of applying apparent diffusion coefficient (ADC) values to the distinction between pediatric fourth ventricular ependymomas and DIPGs. Brain magnetic resonance imaging, including diffusion-weighted imaging and ADC, was assessed in 26 patients, who were divided into two groups: group 1 included 8 patients with fourth ventricular ependymoma and group 2 included 18 patients with DIPG. The Mann–Whitney U test was utilized to compare tumoral maximum (ADCmax), minimum ADC (ADCmin), mean ADC (ADCmean), and standard deviation (ADCsd) values, and the ratios between the tumor and parenchyma values for each of these parameters (rADCmax, rADCmin, rADCmean, and rADCsd, respectively) between the two groups. Cutoff values were calculated based on receiver operating characteristic curve analysis and the Youden index, and the area under the curve (AUC), sensitivity, and specificity were determined. The median ADCmax, ADCmin, ADCmean, rADCmax, rADCmin, and rADCmean values were significantly lower in group 1 than in group 2 (p < 0.05). For the differential diagnosis of ependymomas and DIPGs, a cutoff ADCmean value of 1.02 × 10−3 mm2/s was determined, which produced a sensitivity of 100%, a specificity of 88.9%, and an AUC of 95.8%. ADC parameters should be considered when performing a differential diagnosis between fourth ventricular ependymomas and DIPGs. Based on our findings, a cutoff ADCmean value of 1.02 × 10−3 mm2/s was the most significant and effective parameter for this purpose.

Pediatric posterior fossa tumors outcomes: Experience in a tertiary care center in the Middle East

BACKGROUND

Among all childhood cancers, brain tumors are second only to leukemia in incidence and are the most common solid pediatric tumors. More than 60 % of pediatric brain tumors are infra-tentorial. The first-line treatment for most infra-tentorial tumors in pediatric patients is surgical resection, with the goal of gross-total resection, relief of symptoms and hydrocephalus, and increased survival. The proximity to the fourth ventricle, and therefore, the cerebrospinal fluid (CSF) pathways, predisposes children with posterior fossa tumors to the development of obstructive hydrocephalus and multiple other co-morbidities pre and post-surgery.

OBJECTIVES

This study aims to present our series of pediatric posterior fossa tumor surgeries in the Neurosurgical Department at the American University of Beirut Medical Center(AUBMC) and perform internal quality control for our single-institution consecutive series as one of the largest referral and tertiary care centers in the region. The second purpose of this retrospective study is to weigh the risks of surgery against the presumed advantages and to have specific knowledge about the complication rates, especially those related to the CSF pathway, comparing our results to those in the literature.

METHODS

All pediatric patients (< 18 years of age), referred to our center from different regions in the middle east, and surgically treated for a posterior fossa tumor from June 2006 to June 2018 at the American University of Beirut Medical Center were included. A thorough review of all medical charts was performed to validate all the database records.

RESULTS

The patient sample consisted of 64 patients having a mean age of 6.19 ± 4.42 years and 59.37 % of whom were males. The most common tumor pathology was pilocytic astrocytoma (40.62 %) followed by medulloblastoma (35.93 %) and ependymoma. The most common type of tumor that was seen in patients that developed mutism postoperatively (n = 6, 9.37 %) was medulloblastoma (n = 4, 66.66 %). In this patient sample, 12.28 % (n = 7) of the patients developed hydrocephalus postoperatively.Midline tumors were more associated with the development of mutism(OR = 4.632, p = 0.306) and hydrocephalus (OR = 5.056, p = 0.135) postoperatively, albeit not statistically significantly.The presence of a preoperative shunt was shown to be protective against the development of CSF leak (OR = 0.636, p = 0.767), as none of the patients that came in with CSF diversion developed a CSF leak after their surgery.

CONCLUSION

This study from a single center experience accompanied by a thorough literature review sheds light on the complications frequently encountered after posterior fossa tumor surgery in children. These included transient cerebellar mutism, CSF leak, and hydrocephalus as seen in some of our patients. Our findings highlight the need for prospective studies with well-defined protocols directed at assessing novel ways and approaches to minimize the risk of these complications.

Automatic Machine Learning to Differentiate Pediatric Posterior Fossa Tumors on Routine MR Imaging

BACKGROUND AND PURPOSE

Differentiating the types of pediatric posterior fossa tumors on routine imaging may help in preoperative evaluation and guide surgical resection planning. However, qualitative radiologic MR imaging review has limited performance. This study aimed to compare different machine learning approaches to classify pediatric posterior fossa tumors on routine MR imaging.

MATERIALS AND METHODS

This retrospective study included preoperative MR imaging of 288 patients with pediatric posterior fossa tumors, including medulloblastoma (n = 111), ependymoma (n = 70), and pilocytic astrocytoma (n = 107). Radiomics features were extracted from T2-weighted images, contrast-enhanced T1-weighted images, and ADC maps. Models generated by standard manual optimization by a machine learning expert were compared with automatic machine learning via the Tree-Based Pipeline Optimization Tool for performance evaluation.

RESULTS

For 3-way classification, the radiomics model by automatic machine learning with the Tree-Based Pipeline Optimization Tool achieved a test micro-averaged area under the curve of 0.91 with an accuracy of 0.83, while the most optimized model based on the feature-selection method χ2 score and the Generalized Linear Model classifier achieved a test micro-averaged area under the curve of 0.92 with an accuracy of 0.74. Tree-Based Pipeline Optimization Tool models achieved significantly higher accuracy than average qualitative expert MR imaging review (0.83 versus 0.54, P < .001). For binary classification, Tree-Based Pipeline Optimization Tool models achieved an area under the curve of 0.94 with an accuracy of 0.85 for medulloblastoma versus nonmedulloblastoma, an area under the curve of 0.84 with an accuracy of 0.80 for ependymoma versus nonependymoma, and an area under the curve of 0.94 with an accuracy of 0.88 for pilocytic astrocytoma versus non-pilocytic astrocytoma.

CONCLUSIONS

Automatic machine learning based on routine MR imaging classified pediatric posterior fossa tumors with high accuracy compared with manual expert pipeline optimization and qualitative expert MR imaging review.

The effect of semi-quantitative T1-perfusion parameters for the differentiation between pediatric medulloblastoma and ependymoma

Background

The differentiation between medulloblastomas and ependymomas plays an important role in treatment planning and prognosis for children. This study aims to investigate the role of T1-perfusion parameters during the differentiation between medulloblastomas and ependymomas in children. The institutional review board approved this prospective study. The brain magnetic resonance imaging (MRI) protocol, including axial T1-perfusion, was assessed in 26 patients, divided into a medulloblastoma group (group 1, n = 22) and an ependymoma group (group 2, n = 4). The quantified region of interest (ROI) values for tumors and the tumor to parenchyma ratios were collected and compared between the two groups. Receiver operating characteristic (ROC) curve analysis and the Youden index were utilized to identify the best cut-off, sensitivity, specificity, and area under the curve (AUC) values for the independent T1-perfusion parameters.

Results

The relative enhancement, maximum enhancement, maximum relative enhancement, time to peak, and AUC values for medulloblastomas were significantly higher than those for ependymomas (p < 0.05). Furthermore, the maximum enhancement and maximum relative enhancement for medulloblastoma to parenchyma ratios were also significantly higher than those for ependymomas. A cut-off maximum enhancement value of 100.25 was identified as sufficient to discriminate between medulloblastoma and ependymoma and resulted in a sensitivity of 90.9%, a specificity of 100%, and an AUC of 94.3%.

Conclusion

A cut-off maximum enhancement value of 100.25 derived from T1-perfusion was able to discriminate between medulloblastoma and ependymoma, with high sensitivity, specificity, and accuracy values.

Pediatric Posterior Fossa Medulloblastoma: The Role of Diffusion Imaging in Identifying Molecular Groups

BACKGROUND AND PURPOSE

The molecular groups WNT activated (WNT), Sonic hedgehog activated (SHH), group 3, and group 4 are biologically and clinically distinct forms of medulloblastoma. We evaluated apparent diffusion coefficient (ADC) values' utility in differentiating/predicting medulloblastoma groups at the initial diagnostic imaging evaluation and prior to surgery.

METHODS

We retrospectively measured the ADC values of the enhancing, solid portion of the tumor (EST) and of the whole tumor (WT) and performed Kruskal-Wallis testing to compare the absolute tumor ADC values and cerebellar and thalamic ratios of three medulloblastoma groups (WNT, SHH, and group 3/group 4 combined).

RESULTS

Ninety-three children (65 males) were included. Fifty-seven children had group 3/group 4, 27 had SHH, and 9 had WNT medulloblastomas. The median absolute ADC values in the EST and WT were .719 × 10^-3 and .864 × 10^-3 mm² /s for group 3/group 4; .660 × 10^-3 and .965 × 10^-3 mm² /s for SHH; and .594 × 10^-3 and .728 × 10^-3 mm² /s for WNT medulloblastomas (P = .02 and .13). The median ratio of ADC values in the EST or the WT to normal cerebellar tissue was highest for group 3/group 4 and lowest for WNT medulloblastomas (P = .03 and .09), with similar results in pairwise comparisons of the corresponding thalamic ADC values (P = .02 and .06).

CONCLUSION

ADC analysis of a tumor's contrast-enhancing solid portion may aid preoperative molecular classification/prediction of pediatric medulloblastomas and may facilitate optimal surgical treatment planning, reducing surgery-induced morbidity.

Diagnostic accuracy of apparent diffusion coefficient ratio in distinguishing common pediatric CNS posterior fossa tumors

Background

Pilocytic astrocytoma, medulloblastoma, and ependymoma are the most common pediatric CNS tumors seen at posterior cranial fossa and final diagnosis obtained by histopathology after surgical excision. Routine MRI study gives an idea about site and extension of the tumors but provide a little information about type and grade of tumors. ADC ratio had high sensitivity and specificity in differentiation between these tumors as regard type and grade according to tumor cellularity.

Patients and methods

Prospective study conducted on thirty pediatric patients (11 males and 19 females) with CNS posterior fossa masses, their ages ranged from 2 to 17 years (mean age of 8.7 years), conventional MRI, DWI, ADC value, and ADC ratio were done for all patients.

Results

ADC values were significantly different between pilocytic astrocytomas (1.43 ± 0.28 × 10−3) and medulloblastomas (0.71 ± 0. 21 × 10−3) with a P value < 0.001, also there was a significant difference when comparing medulloblastomas (0.71 ± 0.21 × 10−3) with ependymomas (1.04 × 10−3 ± 0.21) with a P value < 0.001. ADC ratio at a cutoff > 1.7 showed significant good power of discrimination of astrocytoma (AUC = 0.85) from ependymoma with 87.5% sensitivity and 93.3% specificity. Similarly, at cutoff ≤ 1.6-> 1.2 was a significant good predictor of ependymoma (AUC = 0.85) with 87.8% sensitivity and 99.5% specificity. While, ADC ratio ≤ 1.2 was significant excellent discriminator of medulloblastoma (AUC = 0.99) with 100% sensitivity and 90% specificity.

Conclusion

ADC ratio is a simple way used in distinguishing juvenile pilocytic astrocytoma, ependymoma, and medulloblastoma, which are the most frequent pediatric posterior fossa tumors. Cutoff ADC ratio of more than 1.7 characteristic of JPA with 87.5% sensitivity and 93.3% specificity, ADC ratio less than 1.1 characteristic of medulloblastoma with 100% sensitivity and 90% specificity. ADC ratios more than 1.1 and less than 1.7 characteristic of ependymoma with 87.8% sensitivity and 99.5% specificity. We recommended ADC ratio as a routine study in evaluation of pediatric CNS posterior fossa tumors.

Ependymoma and pilocytic astrocytoma: Differentiation using radiomics approach based on machine learning

Mandatory accurate and specific diagnosis demands have brought about increased challenges for radiologists in pediatric posterior fossa tumor prediction and prognosis. With the development of high-performance computing and machine learning technologies, radiomics provides increasing opportunities for clinical decision-making. Several studies have applied radiomics as a decision support tool in intracranial tumors differentiation. Here we seek to achieve preoperative differentiation between ependymoma (EP) and pilocytic astrocytoma (PA) using radiomics analysis method based on machine learning. A total of 135 Magnetic Resonance Imaging (MRI) slices are divided into training sets and validation sets. Three kinds of radiomics features, including Gabor transform, texture and wavelet transform based ones are used to obtain 300 multimodal features. Kruskal-Wallis test score (KWT) and support vector machines (SVM) are applied for feature selection and tumor differentiation. The performance is investigated via accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. Results show that the accuracy, sensitivity, specificity, and AUC of the selected feature set are 0.8775, 0.9292, 0.8000, and 0.8646 respectively, having no significantdifferencescomparedwiththe overall feature set. For different types of features, texture features yield the best differentiation performance and the significance analysis results are consistent with this. Our study demonstrates texture features perform better than the other features. The radiomics approach based on machine learning is efficient for pediatric posterior fossa tumors differentiation and could enhance the application of radiomics methods for assisted clinical diagnosis.