Pediatric brain tumors

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.

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.

Postoperative speech impairment and cranial nerve deficits after secondary surgery of posterior fossa tumours in childhood: a prospective European multicentre study

PURPOSE

Brain tumours constitute 25% of childhood neoplasms, and half of them are in the posterior fossa. Surgery is a fundamental component of therapy, because gross total resection is associated with a higher progression-free survival. Patients with residual tumour, progression of residual tumour or disease recurrence commonly require secondary surgery. We prospectively investigated the risk of postoperative speech impairment (POSI) and cranial nerve dysfunction (CND) following primary and secondary resection for posterior cranial fossa tumours.

METHODS

In the Nordic-European study of the cerebellar mutism syndrome, we prospectively included children undergoing posterior fossa tumour resection or open biopsy in one of the 26 participating European centres. Neurological status was assessed preoperatively, and surgical details were noted post-operatively. Patients were followed up 2 weeks, 2 months and 1 year postoperatively. Here, we analyse the risk of postoperative speech impairment (POSI), defined as either mutism or reduced speech, and cranial nerve dysfunction (CND) following secondary, as compared to primary, surgery.

RESULTS

We analysed 426 children undergoing primary and 78 undergoing secondary surgery between 2014 and 2020. The incidence of POSI was significantly lower after secondary (12%) compared with primary (28%, p = 0.0084) surgery. In a multivariate analysis adjusting for tumour histology, the odds ratio for developing POSI after secondary surgery was 0.23, compared with primary surgery (95% confidence interval: 0.08-0.65, p = 0.006). The frequency of postoperative CND did not differ significantly after primary vs. secondary surgery (p = 0.21).

CONCLUSION

Children have a lower risk of POSI after secondary than after primary surgery for posterior fossa tumours but remain at significant risk of both POSI and CND. The present findings should be taken in account when weighing risks and benefits of secondary surgery for posterior fossa tumours.

Differentiation of paediatric posterior fossa tumours by the multiregional and multiparametric MRI radiomics approach: a study on the selection of optimal multiple sequences and multiregions

OBJECTIVE

To evaluate the diagnostic performance of a radiomics model based on multiregional and multiparametric MRI to classify paediatric posterior fossa tumours (PPFTs), explore the contribution of different MR sequences and tumour subregions in tumour classification, and examine whether contrast-enhanced T₁ weighted (T1C) images have irreplaceable added value.

METHODS

This retrospective study of 136 PPFTs extracted 11,958 multiregional (enhanced, non-enhanced, and total tumour) features from multiparametric MRI (T₁- and T₂ weighted, T1C, fluid-attenuated inversion recovery, and diffusion-weighted images). These features were subjected to fast correlation-based feature selection and classified by a support vector machine based on different tasks. Diagnostic performances of multiregional and multiparametric MRI features, different sequences, and different tumoral regions were evaluated using multiclass and one-vs-rest strategies.

RESULTS

The established model achieved an overall area under the curve (AUC) of 0.977 in the validation cohort. The performance of PPFTs significantly improved after replacing T1C with apparent diffusion coefficient maps added into the plain scan sequences (AUC from 0.812 to 0.917). When oedema features were added to contrast-enhancing tumour volume, the performance did not significantly improve.

CONCLUSION

The radiomics model built by multiregional and multiparametric MRI features allows for the excellent distinction of different PPFTs and provides valuable references for the rational adoption of MR sequences.

ADVANCES IN KNOWLEDGE

This study emphasized that T1C has limited added value in predicting PPFTs and should be cautiously adopted. Selecting optimal MR sequences may help guide clinicians to better allocate acquisition sequences and reduce medical costs.

Advanced Magnetic Resonance Imaging in Pediatric Glioblastomas

The shortly upcoming 5th edition of the World Health Organization Classification of Tumors of the Central Nervous System is bringing extensive changes in the terminology of diffuse high-grade gliomas (DHGGs). Previously "glioblastoma," as a descriptive entity, could have been applied to classify some tumors from the family of pediatric or adult DHGGs. However, now the term "glioblastoma" has been divested and is no longer applied to tumors in the family of pediatric types of DHGGs. As an entity, glioblastoma remains, however, in the family of adult types of diffuse gliomas under the insignia of "glioblastoma, IDH-wildtype." Of note, glioblastomas still can be detected in children when glioblastoma, IDH-wildtype is found in this population, despite being much more common in adults. Despite the separation from the family of pediatric types of DHGGs, what was previously labeled as "pediatric glioblastomas" still remains with novel labels and as new entities. As a result of advances in molecular biology, most of the previously called "pediatric glioblastomas" are now classified in one of the four family members of pediatric types of DHGGs. In this review, the term glioblastoma is still apocryphally employed mainly due to its historical relevance and the paucity of recent literature dealing with the recently described new entities. Therefore, "glioblastoma" is used here as an umbrella term in the attempt to encompass multiple entities such as astrocytoma, IDH-mutant (grade 4); glioblastoma, IDH-wildtype; diffuse hemispheric glioma, H3 G34-mutant; diffuse pediatric-type high-grade glioma, H3-wildtype and IDH-wildtype; and high grade infant-type hemispheric glioma. Glioblastomas are highly aggressive neoplasms. They may arise anywhere in the developing central nervous system, including the spinal cord. Signs and symptoms are non-specific, typically of short duration, and usually derived from increased intracranial pressure or seizure. Localized symptoms may also occur. The standard of care of "pediatric glioblastomas" is not well-established, typically composed of surgery with maximal safe tumor resection. Subsequent chemoradiation is recommended if the patient is older than 3 years. If younger than 3 years, surgery is followed by chemotherapy. In general, "pediatric glioblastomas" also have a poor prognosis despite surgery and adjuvant therapy. Magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of glioblastomas. In addition to the typical conventional MRI features, i.e., highly heterogeneous invasive masses with indistinct borders, mass effect on surrounding structures, and a variable degree of enhancement, the lesions may show restricted diffusion in the solid components, hemorrhage, and increased perfusion, reflecting increased vascularity and angiogenesis. In addition, magnetic resonance spectroscopy has proven helpful in pre- and postsurgical evaluation. Lastly, we will refer to new MRI techniques, which have already been applied in evaluating adult glioblastomas, with promising results, yet not widely utilized in children.

Radiomic Phenotypes Distinguish Atypical Teratoid/Rhabdoid Tumors from Medulloblastoma

BACKGROUND AND PURPOSE

Atypical teratoid/rhabdoid tumors and medulloblastomas have similar imaging and histologic features but distinctly different outcomes. We hypothesized that they could be distinguished by MR imaging-based radiomic phenotypes.

MATERIALS AND METHODS

We retrospectively assembled T2-weighted and gadolinium-enhanced T1-weighted images of 48 posterior fossa atypical teratoid/rhabdoid tumors and 96 match-paired medulloblastomas from 7 institutions. Using a holdout test set, we measured the performance of 6 candidate classifier models using 6 imaging features derived by sparse regression of 900 T2WI and 900 T1WI Imaging Biomarker Standardization Initiative-based radiomics features.

RESULTS

From the originally extracted 1800 total Imaging Biomarker Standardization Initiative-based features, sparse regression consistently reduced the feature set to 1 from T1WI and 5 from T2WI. Among classifier models, logistic regression performed with the highest AUC of 0.86, with sensitivity, specificity, accuracy, and F1 scores of 0.80, 0.82, 0.81, and 0.85, respectively. The top 3 important Imaging Biomarker Standardization Initiative features, by decreasing order of relative contribution, included voxel intensity at the 90th percentile, inverse difference moment normalized, and kurtosis-all from T2WI.

CONCLUSIONS

Six quantitative signatures of image intensity, texture, and morphology distinguish atypical teratoid/rhabdoid tumors from medulloblastomas with high prediction performance across different machine learning strategies. Use of this technique for preoperative diagnosis of atypical teratoid/rhabdoid tumors could significantly inform therapeutic strategies and patient care discussions.

Posterior fossa tumors in children: Radiological tips & tricks in the age of genomic tumor classification and advance MR technology

Imaging plays a major role in the comprehensive assessment of posterior fossa tumor in children (PFTC). The objective is to propose a global method relying on the combined analysis of radiological, clinical and epidemiological criteria, (taking into account the child's age and the topography of the lesion) in order to improve our histological approach in imaging, helping the management and approach for surgeons in providing information to the patients' parents. Infratentorial tumors are the most frequent in children, representing mainly medulloblastoma, pilocytic astrocytoma and brainstem glioma. Pre-surgical identification of the tumor type and its aggressiveness could be improved by the combined analysis of key imaging features with epidemiologic data.

Decoding Somatic Driver Gene Mutations and Affected Signaling Pathways in Human Medulloblastoma Subgroups

Medulloblastoma is the most common malignant pediatric brain tumor. Prior studies have concentrated their efforts studying the four molecular subgroups: SHH, Wnt, group 3, and group 4. SHH and Wnt are driven by their canonical pathways. Groups 3 and 4 are highly metastatic and associated with aberrations in epigenetic regulators. Recent developments in the field have revealed that these subgroups are not as homogenous as previously believed. The objective of this study is to investigate the involvement of somatic driver gene mutations in these medulloblastoma subgroups. We obtained medulloblastoma data from the Catalogue of Somatic Mutations in Cancer (COSMIC), which contains distinct samples that were not previously studied in a large cohort. We identified somatic driver gene mutations and the signaling pathways affected by these driver genes for medulloblastoma subgroups using bioinformatics tools. We have revealed novel infrequent drivers in these subgroups that contribute to our understanding of tumor heterogeneity in medulloblastoma. Normally SHH signaling is activated in the SHH subgroup, however, we determined gain-of-function mutations in ubiquitin ligase (CUL1) that inhibit Gli-mediated transcription. This suggests a potential hindrance in SHH signaling for some patients. For group 3, gain-of-function in the inhibitor of proinflammatory cytokines (HIVEP3) suggests an immunosuppressive phenotype and thus a more hostile tumor microenvironment. Surprisingly, group 4 tumors possess mutations that may prompt the activation of Wnt signaling through gain-of-function mutations in MUC16 and PCDH9. These infrequent mutations detected in this study could be due to subclonal or spatially restricted alterations. The investigation of aberrant driver gene mutations can lead to the identification of new drug targets and a greater understanding of human medulloblastoma heterogeneity.

A novel GIT2-BRAF fusion in pilocytic astrocytoma

BACKGROUND

KIAA1549-BRAF fusion is the most common genetic event in pilocytic astrocytoma (PA), and leads to activation of the mitogen activated protein kinase (MAPK) signaling pathway. Fusions of BRAF with other partner genes, as well as other genetic alterations not involving BRAF but also leading to MAPK pathway activation have been described rarely.

CASE PRESENTATION

We present a new fusion partner in the low-grade glioma of a 10-year-old male, who presented with headaches and recent episodes of seizures. Magnetic resonance imaging (MRI) demonstrated a right temporal lobe tumor. Histological and immunohistochemical evaluation, and a next generation sequencing assay (Oncopanel, Illumina, 500 genes) including breaKmer analysis for chromosomal rearrangements were performed. Histology was remarkable for a low-grade glioma composed of mildly atypical astrocytes with piloid processes, in a focally microcystic background. Mitoses were not seen; unequivocal Rosenthal fibers or eosinophilic granular bodies were absent. The tumor was positive for OLIG2 and GFAP and negative for BRAF V600E and IDH1 R132H mutant protein immunostains. Oncopanel showed low SOX2 (3q26.33) copy number gain, and no gains at 7q34. There were no significant single nucleotide variants. BreaKmer detected a GIT2-BRAF fusion with loss of BRAF exons 1-8. The integrated diagnosis was low-grade glioma with piloid features, most consistent with pilocytic astrocytoma, WHO grade I.

CONCLUSION

GIT2-BRAF fusion has not been reported in the literature in any tumor. Given that the BRAF sequence deleted is identical to that seen in other fusion events in PA, it most likely acts as tumor driver by activation of the MAPK pathway.

Posterior Fossa Tumors

Pediatric brain tumors are the leading cause of death from solid tumors in childhood. The most common posterior fossa tumors in children are medulloblastoma, atypical teratoid/rhabdoid tumor, cerebellar pilocytic astrocytoma, ependymoma, and brainstem glioma. Location, and imaging findings on computed tomography (CT) and conventional MR (cMR) imaging may provide important clues to the most likely diagnosis. Moreover, information obtained from advanced MR imaging techniques increase diagnostic confidence and help distinguish between different histologic tumor types. Here we discuss the most common posterior fossa tumors in children, including typical imaging findings on CT, cMR imaging, and advanced MR imaging studies.

Pineal Region Masses in Pediatric Patients

A review of pediatric pineal region tumors is provided with emphasis on advanced imaging techniques. The 3 major categories of pineal region tumors include germ cell tumors, pineal parenchymal tumors, and tumors arising from adjacent structures such as tectal astrocytomas. The clinical presentation, biochemical markers, and imaging of these types of tumors are reviewed.

Advanced MRI for Pediatric Brain Tumors with Emphasis on Clinical Benefits

Conventional anatomic brain MRI is often limited in evaluating pediatric brain tumors, the most common solid tumors and a leading cause of death in children. Advanced brain MRI techniques have great potential to improve diagnostic performance in children with brain tumors and overcome diagnostic pitfalls resulting from diverse tumor pathologies as well as nonspecific or overlapped imaging findings. Advanced MRI techniques used for evaluating pediatric brain tumors include diffusion-weighted imaging, diffusion tensor imaging, functional MRI, perfusion imaging, spectroscopy, susceptibility-weighted imaging, and chemical exchange saturation transfer imaging. Because pediatric brain tumors differ from adult counterparts in various aspects, MRI protocols should be designed to achieve maximal clinical benefits in pediatric brain tumors. In this study, we review advanced MRI techniques and interpretation algorithms for pediatric brain tumors.

Improving Care in Pediatric Neuro-oncology Patients: An Overview of the Unique Needs of Children With Brain Tumors

Brain tumors represent the most common solid tumors in childhood, accounting for almost 25% of all childhood cancer, second only to leukemia. Pediatric central nervous system tumors encompass a wide variety of diagnoses, from benign to malignant. Any brain tumor can be associated with significant morbidity, even when low grade, and mortality from pediatric central nervous system tumors is disproportionately high compared to other childhood malignancies. Management of children with central nervous system tumors requires knowledge of the unique aspects of care associated with this particular patient population, beyond general oncology care. Pediatric brain tumor patients have unique needs during treatment, as cancer survivors, and at end of life. A multidisciplinary team approach, including advanced practice nurses with a specialty in neuro-oncology, allows for better supportive care. Knowledge of the unique aspects of care for children with brain tumors, and the appropriate interventions required, allows for improved quality of life.

The diagnostic accuracy of multiparametric MRI to determine pediatric brain tumor grades and types

Childhood brain tumors show great histological variability. The goal of this retrospective study was to assess the diagnostic accuracy of multimodal MR imaging (diffusion, perfusion, MR spectroscopy) in the distinction of pediatric brain tumor grades and types. Seventy-six patients (range 1 month to 18 years) with brain tumors underwent multimodal MR imaging. Tumors were categorized by grade (I-IV) and by histological type (A-H). Multivariate statistical analysis was performed to evaluate the diagnostic accuracy of single and combined MR modalities, and of single imaging parameters to distinguish the different groups. The highest diagnostic accuracy for tumor grading was obtained with diffusion-perfusion (73.24%) and for tumor typing with diffusion-perfusion-MR spectroscopy (55.76%). The best diagnostic accuracy was obtained for tumor grading in I and IV and for tumor typing in embryonal tumor and pilocytic astrocytoma. Poor accuracy was seen in other grades and types. ADC and rADC were the best parameters for tumor grading and typing followed by choline level with an intermediate echo time, CBV for grading and Tmax for typing. Multiparametric MR imaging can be accurate in determining tumor grades (primarily grades I and IV) and types (mainly pilocytic astrocytomas and embryonal tumors) in children.

Diagnostic and prognostic value of 18F-DOPA PET and 1H-MR spectroscopy in pediatric supratentorial infiltrative gliomas: a comparative study

BACKGROUND

(1)H-MR spectroscopy (MRS) and (18)F-dihydroxyphenylalanine (DOPA) PET are noninvasive imaging techniques able to assess metabolic features of brain tumors. The aim of this study was to compare diagnostic and prognostic information gathered by (18)F-DOPA PET and (1)H-MRS in children with supratentorial infiltrative gliomas or nonneoplastic brain lesions suspected to be gliomas.

METHODS

We retrospectively analyzed 27 pediatric patients with supratentorial infiltrative brain lesions on conventional MRI (21 gliomas and 6 nonneoplastic lesions) who underwent (18)F-DOPA PET and (1)H-MRS within 2 weeks of each other. (1)H-MRS data (choline/N-acetylaspartate, choline-to-creatine ratios, and presence of lactate) and (18)F-DOPA uptake parameters (lesion-to-normal tissue and lesion-to-striatum ratios) were compared and correlated with histology, WHO tumor grade, and patient outcome.

RESULTS

(1)H-MRS and (18)F-DOPA PET data were positively correlated. Sensitivity, specificity, and accuracy in distinguishing gliomas from nonneoplastic lesions were 95%, 83%, and 93% for (1)H-MRS and 76%, 83%, and 78% for (18)F-DOPA PET, respectively. No statistically significant differences were found between the 2 techniques (P > .05). Significant differences regarding (18)F-DOPA uptake and (1)H-MRS ratios were found between low-grade and high-grade gliomas (P≤.001 and P≤.04, respectively). On multivariate analysis, (18)F-DOPA uptake independently correlated with progression-free survival (P≤.05) and overall survival (P = .04), whereas (1)H-MRS did not show significant association with outcome.

CONCLUSIONS

(1)H-MRS and (18)F-DOPA PET provide useful complementary information for evaluating the metabolism of pediatric brain lesions. (1)H-MRS represents the method of first choice for differentiating brain gliomas from nonneoplastic lesions.(18)F-DOPA uptake better discriminates low-grade from high-grade gliomas and is an independent predictor of outcome.

Pediatric brain tumors

Among all causes of death in children from solid tumors, pediatric brain tumors are the most common. This article includes an overview of a subset of infratentorial and supratentorial tumors with a focus on tumor imaging features and molecular advances and treatments of these tumors. Key to understanding the imaging features of brain tumors is a firm grasp of other disease processes that can mimic tumor on imaging. We also review imaging features of a common subset of tumor mimics.