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

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.

The role of apparent diffusion coefficient histogram metrics for differentiating pediatric medulloblastoma histological variants and molecular groups

BACKGROUND

Medulloblastoma, a high-grade embryonal tumor, is the most common primary brain malignancy in the pediatric population. Molecular medulloblastoma groups have documented clinically and biologically relevant characteristics. Several authors have attempted to differentiate medulloblastoma molecular groups and histology variants using diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) maps. However, literature on the use of ADC histogram analysis in medulloblastomas is still scarce.

OBJECTIVE

This study presents data from a sizable group of pediatric patients with medulloblastoma from a single institution to determine the performance of ADC histogram metrics for differentiating medulloblastoma variants and groups based on both histological and molecular features.

MATERIALS AND METHODS

In this retrospective study, we evaluated the distribution of absolute and normalized ADC values of medulloblastomas. Tumors were manually segmented and diffusivity metrics calculated on a pixel-by-pixel basis. We calculated a variety of first-order histogram metrics from the ADC maps, including entropy, minimum, 10th percentile, 90th percentile, maximum, mean, median, skewness and kurtosis, to differentiate molecular and histological variants. ADC values of the tumors were also normalized to the bilateral cerebellar cortex and thalami. We used the Kruskal-Wallis and Mann-Whitney U tests to evaluate differences between the groups. We carried out receiver operating characteristic (ROC) curve analysis to evaluate the areas under the curves and to determine the cut-off values for differentiating tumor groups.

RESULTS

We found 65 children with confirmed histopathological diagnosis of medulloblastoma. Mean age was 8.3 ± 5.8 years, and 60% (n = 39) were male. One child was excluded because histopathological variant could not be determined. In terms of medulloblastoma variants, tumors were classified as classic (n = 47), desmoplastic/nodular (n = 9), large/cell anaplastic (n = 6) or as having extensive nodularity (n = 2). Seven other children were excluded from the study because of incomplete imaging or equivocal molecular diagnosis. Regarding medulloblastoma molecular groups, there were: wingless (WNT) group (n = 7), sonic hedgehog (SHH) group (n = 14) and non-WNT/non-SHH (n = 36). Our results showed significant differences among the molecular groups in terms of the median (P = 0.002), mean (P = 0.003) and 90th percentile (P = 0.002) ADC histogram metrics. No significant differences among the various medulloblastoma histological variants were found.

CONCLUSION

ADC histogram analysis can be implemented as a complementary tool in the preoperative evaluation of medulloblastoma in children. This technique can provide valuable information for differentiating among medulloblastoma molecular groups. ADC histogram metrics can help predict medulloblastoma molecular classification preoperatively.

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.

Posterior fossa extra-axial variations of medulloblastoma: a pictorial review as a primer for radiologists

Manifestations of an atypical variant of medulloblastoma of the posterior fossa in extra-axial locations have been reported, and key questions concerning its interpretation have been raised previously. This review illustrated the clinico-radiological and histopathological features of the posterior fossa extra-axial medulloblastoma and described possible management strategies. We thoroughly reviewed all atypical anatomical locations of medulloblastoma reported within the posterior fossa and extra-axial spaces. The main characteristics of diagnostic imaging and histopathological results, primarily the distinctive radiopathological characteristics, were summarized to distinguish between intra- and extra-axial medulloblastoma, or pathologies mimicking this tumor. Most cases of posterior fossa extra-axial medulloblastoma have been reported in the cerebellopontine angle, followed by the tentorial and lateral cerebellar locations. The dural tail sign, which is commonly observed in meningioma, is rarely seen in intra- or extra-axial medulloblastoma and might be associated with other benign or malignant lesions. In addition to magnetic resonance imaging, the proposed new imaging techniques, including advances in modern neuroimaging modalities, were discussed, as potentially efficient modalities for characterizing extra-axial medulloblastoma. Radionuclide imaging and magnetic resonance perfusion imaging are practical alternatives to limit the number of differential diagnoses. We believe that medulloblastoma cases are likely under-reported because of publication bias and frequent tumors in unusual locations. Addressing these issues would help establish a more accurate understanding of this entity.

Advancements in Neuroimaging to Unravel Biological and Molecular Features of Brain Tumors

Simple Summary

Advanced neuroimaging is gaining increasing relevance for the characterization and the molecular profiling of brain tumor tissue. On one hand, for some tumor types, the most widespread advanced techniques, investigating diffusion and perfusion features, have been proven clinically feasible and rather robust for diagnosis and prognosis stratification. In addition, 2-hydroxyglutarate spectroscopy, for the first time, offers the possibility to directly measure a crucial molecular marker. On the other hand, numerous innovative approaches have been explored for a refined evaluation of tumor microenvironments, particularly assessing microstructural and microvascular properties, and the potential applications of these techniques are vast and still to be fully explored.

Abstract

In recent years, the clinical assessment of primary brain tumors has been increasingly dependent on advanced magnetic resonance imaging (MRI) techniques in order to infer tumor pathophysiological characteristics, such as hemodynamics, metabolism, and microstructure. Quantitative radiomic data extracted from advanced MRI have risen as potential in vivo noninvasive biomarkers for predicting tumor grades and molecular subtypes, opening the era of “molecular imaging” and radiogenomics. This review presents the most relevant advancements in quantitative neuroimaging of advanced MRI techniques, by means of radiomics analysis, applied to primary brain tumors, including lower-grade glioma and glioblastoma, with a special focus on peculiar oncologic entities of current interest. Novel findings from diffusion MRI (dMRI), perfusion-weighted imaging (PWI), and MR spectroscopy (MRS) are hereby sifted in order to evaluate the role of quantitative imaging in neuro-oncology as a tool for predicting molecular profiles, stratifying prognosis, and characterizing tumor tissue microenvironments. Furthermore, innovative technological approaches are briefly addressed, including artificial intelligence contributions and ultra-high-field imaging new techniques. Lastly, after providing an overview of the advancements, we illustrate current clinical applications and future perspectives.

Advanced MRI Findings in Medulloblastomas: Relationship to Genetic Subtypes, Histopathology, and Immunohistochemistry

BACKGROUND AND PURPOSE

For diagnosis of medulloblastoma, the updated World Health Organization classification now demands for genetic typing, defining more precisely the tumor biology, therapy, and prognosis. We investigated potential associations between magnetic resonance imaging (MRI) parameters including apparent diffusion coefficient (ADC) and neuropathologic features of medulloblastoma, focusing on genetic subtypes.

METHODS

This study was a retrospective single-center analysis of 32 patients (eight females, median age = 9 years [range, 1-57], mean 12.6 ± 11.3) from 2012 to 2019. Genetic subtypes (wingless [WNT]; sonic hedgehog [SHH]; non-WNT/non-SHH), histopathology, immunohistochemistry (p53, Ki67), and the following MRI parameters were correlated: tumor volume, location (midline, pontocerebellar, and cerebellar hemisphere), edema, hydrocephalus, metastatic disease (presence/absence and each), contrast-enhancement (minor, moderate, and distinct), cysts (none, small, and large), hemorrhage (none, minor, and major), and ADC_mean . The ADC_mean was calculated using manually set regions of interest within the solid tumor. Statistics comprised univariate and multivariate testing.

RESULTS

Out of 32 tumors, three tumors were WNT activated (9.4%), 13 (40.6%) SHH activated, and 16 (50.0%) non-WNT/non-SHH. Hemispherical location (n = 7/8, P = .003) and presence of edema (8/8; P < .001, specificity 100%, positive predictive value 100%) were significantly associated with SHH activation. The combined parameter "no edema + no metastatic disease + cysts" significantly discriminated WNT-activated from SHH-activated medulloblastoma (P = .036). ADC_mean (10^-6 mm² /s) was 484 for WNT-activated, 566 for SHH-activated, and 624 for non-WNT/non-SHH subtypes (P = .080). A significant negative correlation was found between ADC_mean and Ki67 (r = -.364, P = .040).

CONCLUSION

MRI analysis enabled noninvasive differentiation of SHH-activated medulloblastoma. ADC alone was not reliable for genetic characterization, but associated with tumor proliferation rate.

Apparent Diffusion Coefficient to Evaluate Adult Intracranial Ependymomas: Relationship to Ki-67 Proliferation Index

BACKGROUND AND PURPOSE

There are important differences in the treatment and prognosis of adult intracranial low-grade ependymomas (grade II) versus anaplastic ependymomas (grade III). We evaluated the value of the apparent diffusion coefficient (ADC) for differentiating these two tumors and further investigated the relationship between ADC values and the Ki-67 proliferation index.

METHODS

Clinical and preoperative magnetic resonance imaging data of 35 cases of adult intracranial ependymomas were retrospectively analyzed, including 20 low-grade ependymomas and 15 anaplastic ependymomas. The minimum ADC (ADCmin), average ADC (ADCmean), and normalized ADC (nADC) were compared between the two groups. Receiver operating characteristic curves were drawn to evaluate the differentiating accuracy of ADC values. The Ki-67 proliferation index of the solid tumor components was also measured to explore its relationship with ADC values.

RESULTS

The ADCmin (.89 ± .17 vs. .66 ± .09 × 10^-3  mm² /second), ADCmean (.98 ± .21 vs. .72 ± .11 × 10^-3 mm² /second), and nADC (1.38 ± .31 vs. 1.02 ± .18 × 10^-3  mm² /second) were significantly higher in adult intracranial low-grade ependymomas than anaplastic ependymomas cases (all P < .05). ADCmean best distinguished the two groups, with an area under the curve value of .900. Using .716 × 10^-3  mm² /second as the optimal threshold, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the two groups were 66.7%, 100%, 85.7%, 100%, and 80%, respectively. ADCmin (r = -.490), ADCmean (r = -.449), and nADC (r = -.425) showed significant negative correlations with the Ki-67 proliferation index (all P < .05).

CONCLUSIONS

ADC values can differentiate adult intracranial low-grade ependymomas and anaplastic ependymomas, which could improve the preoperative diagnostic accuracy of these two tumors and guide their treatment.