Radiomic Signatures of Posterior Fossa Ependymoma: Molecular Subgroups and Risk Profiles

Imaging features to distinguish posterior fossa ependymoma subgroups

OBJECTIVES

Posterior fossa ependymoma group A (EPN_PFA) and group B (EPN_PFB) can be distinguished by their DNA methylation and give rise to different prognoses. We compared the MRI characteristics of EPN_PFA and EPN_PFB at presentation.

METHODS

Preoperative imaging of 68 patients with posterior fossa ependymoma from two centers was reviewed by three independent readers, blinded for histomolecular grouping. Location, tumor extension, tumor volume, hydrocephalus, calcifications, tissue component, enhancement or diffusion signal, and histopathological data (cellular density, calcifications, necrosis, mitoses, vascularization, and microvascular proliferation) were compared between the groups. Categorical data were compared between groups using Fisher's exact tests, and quantitative data using Mann-Whitney tests. We performed a Benjamini-Hochberg correction of the p values to account for multiple tests.

RESULTS

Fifty-six patients were categorized as EPN_PFA and 12 as EPN_PFB, with median ages of 2 and 20 years, respectively (p = 0.0008). The median EPN_PFA tumoral volume was larger (57 vs 29 cm3, p = 0.003), with more pronounced hydrocephalus (p = 0.002). EPN_PFA showed an exclusive central position within the 4th ventricle in 61% of patients vs 92% for EPN_PFB (p = 0.01). Intratumor calcifications were found in 93% of EPN_PFA vs 40% of EPN_PFB (p = 0.001). Invasion of the posterior fossa foramina was mostly found for EPN_PFA, particularly the foramina of Luschka (p = 0.0008). EPN_PFA showed whole and homogeneous tumor enhancement in 5% vs 75% of EPN_PFB (p = 0.0008). All mainly cystic tumors were EPN_PFB (p = 0.002). The minimal and maximal relative ADC was slightly lower in EPN_PFA (p = 0.02 and p = 0.01, respectively).

CONCLUSION

Morphological characteristics from imaging differ between posterior fossa ependymoma subtypes and may help to distinguish them preoperatively.

CLINICAL RELEVANCE STATEMENT

This study provides a tool to differentiate between group A and group B ependymomas, which will ultimately allow the therapeutic strategy to be adapted in the early stages of patient management.

KEY POINTS

• Posterior fossa ependymoma subtypes often have different imaging characteristics. • Posterior fossa ependymomas group A are commonly median or lateral tissular calcified masses, with incomplete enhancement, affecting young children and responsible for pronounced hydrocephalus and invasion of the posterior fossa foramina. • Posterior fossa ependymomas group B are commonly median non-calcified masses of adolescents and adults, predominantly cystic, and minimally invasive, with total and homogeneous enhancement.

A Fully Automated Deep-Learning Model for Predicting the Molecular Subtypes of Posterior Fossa Ependymomas Using T2-Weighted Images

PURPOSE

We aimed to develop and validate a deep learning (DL) model to automatically segment posterior fossa ependymoma (PF-EPN) and predict its molecular subtypes [Group A (PFA) and Group B (PFB)] from preoperative MR images.

EXPERIMENTAL DESIGN

We retrospectively identified 227 PF-EPNs (development and internal test sets) with available preoperative T2-weighted (T2w) MR images and molecular status to develop and test a 3D nnU-Net (referred to as T2-nnU-Net) for tumor segmentation and molecular subtype prediction. The network was externally tested using an external independent set [n = 40; subset-1 (n = 31) and subset-2 (n =9)] and prospectively enrolled cases [prospective validation set (n = 27)]. The Dice similarity coefficient was used to evaluate the segmentation performance. Receiver operating characteristic analysis for molecular subtype prediction was performed.

RESULTS

For tumor segmentation, the T2-nnU-Net achieved a Dice score of 0.94 ± 0.02 in the internal test set. For molecular subtype prediction, the T2-nnU-Net achieved an AUC of 0.93 and accuracy of 0.89 in the internal test set, an AUC of 0.99 and accuracy of 0.93 in the external test set. In the prospective validation set, the model achieved an AUC of 0.93 and an accuracy of 0.89. The predictive performance of T2-nnU-Net was superior or comparable to that of demographic and multiple radiologic features (AUCs ranging from 0.87 to 0.95).

CONCLUSIONS

A fully automated DL model was developed and validated to accurately segment PF-EPNs and predict molecular subtypes using only T2w MR images, which could help in clinical decision-making.

"Soap bubble" sign as an imaging marker for posterior fossa ependymoma Group B

PURPOSE

To investigate the predictive value of the "soap bubble" sign on molecular subtypes (Group A [PFA] and Group B [PFB]) of posterior fossa ependymomas (PF-EPNs).

METHODS

MRI scans of 227 PF-EPNs (internal retrospective discovery set) were evaluated by two independent neuroradiologists to assess the "soap bubble" sign, which was defined as clusters of cysts of various sizes that look like "soap bubbles" on T2-weighted images. Two independent cohorts (external validation set [n = 31] and prospective validation set [n = 27]) were collected to validate the "soap bubble" sign.

RESULTS

Across three datasets, the "soap bubble" sign was observed in 21 PFB cases (7.4% [21/285] of PF-EPNs and 12.9% [21/163] of PFB); none in PFA. Analysis of the internal retrospective discovery set demonstrated substantial interrater agreement (1st Rating: κ = 0.71 [0.53-0.90], 2nd Rating: κ = 0.83 [0.68-0.98]) and intrarater agreement (Rater 1: κ = 0.73 [0.55-0.91], Rater 2: κ = 0.74 [0.55-0.92]) for the "soap bubble" sign; all 13 cases positive for the "soap bubble" sign were PFB (p = 0.002; positive predictive value [PPV] = 100%, negative predictive value [NPV] = 44%, sensitivity = 10%, specificity = 100%). The findings from the external validation set and the prospective validation set were similar, all cases positive for the "soap bubble" sign were PFB (p < 0.001; PPV = 100%).

CONCLUSION

The "soap bubble" sign represents a highly specific imaging marker for the PFB molecular subtype of PF-EPNs.

Current state of radiomics in pediatric neuro-oncology practice: a systematic review

BACKGROUND

Radiomics is the process of converting radiological images into high-dimensional data that may be used to create machine learning models capable of predicting clinical outcomes, such as disease progression, treatment response and survival. Pediatric central nervous system (CNS) tumors differ from adult CNS tumors in terms of their tissue morphology, molecular subtype and textural features. We set out to appraise the current impact of this technology in clinical pediatric neuro-oncology practice.

OBJECTIVES

The aims of the study were to assess radiomics' current impact and potential utility in pediatric neuro-oncology practice; to evaluate the accuracy of radiomics-based machine learning models and compare this to the current standard which is stereotactic brain biopsy; and finally, to identify the current limitations of radiomics applications in pediatric neuro-oncology.

MATERIALS AND METHODS

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards, a systematic review of the literature was carried out with protocol number CRD42022372485 in the prospective register of systematic reviews (PROSPERO). We performed a systematic literature search via PubMed, Embase, Web of Science and Google Scholar. Studies involving CNS tumors, studies that utilized radiomics and studies involving pediatric patients (age<18 years) were included. Several parameters were collected including imaging modality, sample size, image segmentation technique, machine learning model used, tumor type, radiomics utility, model accuracy, radiomics quality score and reported limitations.

RESULTS

The study included a total of 17 articles that underwent full-text review, after excluding duplicates, conference abstracts and studies that did not meet the inclusion criteria. The most commonly used machine learning models were support vector machines (n=7) and random forests (n=6), with an area under the curve (AUC) range of 0.60-0.94. The included studies investigated several pediatric CNS tumors, with ependymoma and medulloblastoma being the most frequently studied. Radiomics was primarily used for lesion identification, molecular subtyping, survival prognostication and metastasis prediction in pediatric neuro-oncology. The low sample size of studies was a commonly reported limitation.

CONCLUSION

The current state of radiomics in pediatric neuro-oncology is promising, in terms of distinguishing between tumor types; however, its utility in response assessment requires further evaluation which, given the relatively low number of pediatric tumors, calls for multicenter collaboration.

Cellular Therapy for Children with Central Nervous System Tumors: Mining and Mapping the Correlative Data

PURPOSE OF REVIEW

Correlative studies should leverage clinical trial frameworks to conduct biospecimen analyses that provide insight into the bioactivity of the intervention and facilitate iteration toward future trials that further improve patient outcomes. In pediatric cellular immunotherapy trials, correlative studies enable deeper understanding of T cell mobilization, durability of immune activation, patterns of toxicity, and early detection of treatment response. Here, we review the correlative science in adoptive cell therapy (ACT) for childhood central nervous system (CNS) tumors, with a focus on existing chimeric antigen receptor (CAR) and T cell receptor (TCR)-expressing T cell therapies.

RECENT FINDINGS

We highlight long-standing and more recently understood challenges for effective alignment of correlative data and offer practical considerations for current and future approaches to multi-omic analysis of serial tumor, serum, and cerebrospinal fluid (CSF) biospecimens. We highlight the preliminary success in collecting serial cytokine and proteomics from patients with CNS tumors on ACT clinical trials.

Promoting the application of pediatric radiomics via an integrated medical engineering approach

Radiomics is widely used in adult tumors but has been rarely applied to the field of pediatrics. Promoting the application of radiomics in pediatric diseases, especially in the early diagnosis and stratified treatment of tumors, is of great value to the realization of the WHO 2030 “Global Initiative for Childhood Cancer.” This paper discusses the general characteristics of radiomics, the particularity of its application to pediatric diseases, and the current status and prospects of pediatric radiomics. Radiomics is a data‐driven science, and the combination of medicine and engineering plays a decisive role in improving data quality, data diversity, and sample size. Compared with adult radiomics, pediatric radiomics is significantly different in data type, disease spectrum, disease staging, and progression. Some progress has been made in the identification, classification, stratification, survival prediction, and prognosis of tumor diseases. In the future, big data applications from multiple centers and cross‐talent training should be strengthened to improve the benefits for clinical workers and children.

Changes to pediatric brain tumors in 2021 World Health Organization classification of tumors of the central nervous system

New tumor types are continuously being described with advances in molecular testing and genomic analysis resulting in better prognostics, new targeted therapy options and improved patient outcomes. As a result of these advances, pathological classification of tumors is periodically updated with new editions of the World Health Organization (WHO) Classification of Tumors books. In 2021, WHO Classification of Tumors of the Central Nervous System, 5^th edition (CNS5), was published with major changes in pediatric brain tumors officially recognized including pediatric gliomas being separated from adult gliomas, ependymomas being categorized based on anatomical compartment and many new tumor types, most of them seen in children. Additional general changes, such as tumor grading now being done within tumor types rather than across entities and changes in definition of glioblastoma, are also relevant to pediatric neuro-oncology practice. The purpose of this manuscript is to highlight the major changes in pediatric brain tumors in CNS5 most relevant to radiologists. Additionally, brief descriptions of newly recognized entities will be presented with a focus on imaging findings.