Use of T2 signal intensity of cerebellar neoplasms in pediatric patients to guide preoperative staging of the neuraxis

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 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.

Factors associated with seizure and cognitive outcomes after epilepsy surgery for low-grade epilepsy-associated neuroepithelial tumors in children

Low-grade epilepsy-associated neuroepithelial tumors (LEATs) are responsible for drug-resistant chronic focal epilepsy, and are the second-most common reason for epilepsy surgery in children. LEATs are extremely responsive to surgical treatment, and therefore epilepsy surgery should be considered as a treatment option for LEATs. However, the optimal time for surgery remains controversial, and surgeries are often delayed. In this review, we reviewed published article on the factors associated with seizure and cognitive outcomes after epilepsy surgery for LEATs in children to help clinicians in their decision whether to pursue epilepsy surgery for LEATs. The achievement of gross total resection may be the most important prognostic factor for seizure freedom. A shorter duration of epilepsy, a younger age at surgery, and extended resection of temporal lobe tumors have also been suggested as favorable prognostic factors in terms of seizure control. Poor cognitive function in children with LEATs is associated with a longer duration of epilepsy and a younger age at seizure onset.

Analysis of T2 signal intensity helps in the differentiation between high and low-grade brain tumours in paediatric patients

PURPOSE

Previous studies hypothesized that the analysis of magnetic resonance intensity of the solid portion in paediatric tumours can provide pre-surgical information about the histopathology. Classically, high signal-intensity in T2weighted (T2w) images identifies low-grade tumours, while anaplasia is characterized by T2 hypointensity. We aimed to investigate if T2w signal intensities can pre-operatively distinguish between low-grade and high-grade brain tumours in paediatric patients.

METHODS

Two raters, blinded to the histological diagnosis, rated the signal intensity of MR images (T2w) from 36 children with newly diagnosed brain tumours, 17 children with low-grade brain tumours and 19 children with high-grade brain tumours were included in this study. Relative T2 values were obtained by dividing the T2w values of the solid portion of the tumour by the T2w values of the vitreous humour.

RESULTS

The best cut-off point to distinguish low and high-grade paediatric brain tumours was 0.8. If the signal intensity was less than or equal to 0.8 the tumour was expected to be a high-grade tumour with a sensitivity of 100%. Prediction of a low-grade tumour was more uncertain with a sensitivity of 70.5%. Overall, 86% of the tumours would have been predicted correctly.

CONCLUSION

Our data suggest that T2w signal intensities of the solid portion of brain tumours in paediatrics can pre-operatively differentiate between low-grade and high-grade tumours. In addition, T2 hypointensity may be helpful in targeting stereotactic biopsy.

Conventional magnetic resonance imaging in the differentiation between high and low-grade brain tumours in paediatric patients

OBJECTIVE

It has been described that hyperintensity in diffusion-weighted imaging (DWI) correlates with high-grade tumours, and high signal-intensity in T2-weighted (T2w) images identifies low-grade tumours. We aimed to investigate the potential of routine conventional MRI sequences, such as DWI and T2-w, to pre-operatively distinguish between low-grade and high-grade brain tumours in paediatric patients.

MATERIAL AND METHODS

Two raters, blinded to the histological diagnosis, rated the aspect and signal intensity of MR images (T2w and DWI) from 37 children with newly diagnosed brain tumours. Histological diagnoses included 18 low-grade and 19 high-grade brain tumours.

RESULTS

The inter-rater agreement was 81-95%. High-grade tumours were never hypointense on DWI and low-grade tumours were usually hyperintense on T2w. Specificity was 100% for low-grade tumours and 90% for high-grade tumours. About 95% of the high-grade tumours and about 70% of the low-grade tumours were correctly diagnosed.

CONCLUSION

The combination of general morphological aspect of the tumours and signals on T2-w and DWI yield a high accuracy of pre-operative differentiation between low-grade and high-grade paediatric tumours.

Canine intracranial gliomas: relationship between magnetic resonance imaging criteria and tumor type and grade

Limited information is available to assist in the ante-mortem prediction of tumor type and grade for dogs with primary brain tumors. The objective of the current study was to identify magnetic resonance imaging (MRI) criteria related to the histopathological type and grade of gliomas in dogs. A convenience sample utilizing client-owned dogs (n=31) with gliomas was used. Medical records of dogs with intracranial lesions admitted to two veterinary referral hospitals were reviewed and cases with a complete brain MRI and definitive histopathological diagnosis were retrieved for analysis. Each MRI was independently interpreted by five investigators who were provided with standardized grading instructions and remained blinded to the histopathological diagnosis. Mild to no contrast enhancement, an absence of cystic structures (single or multiple), and a tumor location other than the thalamo-capsular region were independently associated with grade II tumors compared to higher grade tumors. In comparison to oligodendrogliomas, astrocytomas were independently associated with the presence of moderate to extensive peri-tumoral edema, a lack of ventricular distortion, and an isointense or hyper-intense T1W-signal. When clinical and MRI features indicate that a glioma is most likely, certain MRI criteria can be used to inform the level of suspicion for low tumor grade, particularly poor contrast enhancement. Information obtained from the MRI of such dogs can also assist in predicting an astrocytoma or an oligodendroglioma, but no single imaging characteristic allows for a particular tumor type to be ruled out.

Pediatric cerebellar pilomyxoid-spectrum astrocytomas

OBJECT

Pediatric cerebellar astrocytomas with pilomyxoid features include classic pilomyxoid astrocytomas (PMAs) and intermediate pilomyxoid tumors (IPTs). Since the original description of PMA in 1999, most reports in the literature have described PMAs arising from the hypothalamic/chiasmatic region. To the authors' knowledge, PMAs arising from the posterior fossa have not been discussed in the neurosurgical literature. Intermediate pilomyxoid tumors, or tumors with pathological features of both pilocytic astrocytoma (PA) and PMA, have only recently been described. In this article, the authors present 2 cases that fall within the spectrum of pediatric cerebellar PMA-including a classic PMA and an intermediate pilomyxoid tumor. The authors compare the radiological presentation, surgical results, and postoperative course to findings in a cohort of 15 patients with cerebellar PAs.

METHODS

Between 2003 and 2010, 2 patients with pilomyxoid-spectrum astrocytomas underwent treatment at Vanderbilt Children's Hospital. One was a 22-month-old girl who presented with progressive gait disturbance and falls. The other was a 4-year-old girl who presented with ataxia and generalized weakness. In a retrospective review of pediatric cerebellar neoplasms resected by the senior author during this period, these tumors comprised 4% of cerebellar neoplasms and approximately 10% of cerebellar glial neoplasms.

RESULTS

Both patients were treated with midline suboccipital craniotomy for resection. In both cases, tumor invasion anteriorly into the brainstem prevented gross-total resection. the patient in Case 1 was placed on chemotherapy following pathological diagnosis and later developed definitive evidence of leptomeningeal dissemination (LD) 3 years after the operation. The patient in Case 2 was placed on chemotherapy after exhibiting progressive evidence of local recurrence (findings were negative for LD) 12 months following resection.

CONCLUSIONS

Pediatric patients with cerebellar pilomyxoid-spectrum astrocytomas appear to suffer higher rates of local recurrence and LD than pediatric patients with cerebellar PAs.

Findings on preoperative brain MRI predict histopathology in children with cerebellar neoplasms

BACKGROUND/AIMS

The majority of pediatric patients with cerebellar neoplasms harbor pilocytic astrocytomas (PAs), medulloblastomas, or ependymomas. Knowledge of a preoperative likelihood of histopathology in this group of patients has the potential to influence many aspects of care. Previous studies have demonstrated hyperintensity on diffusion-weighted imaging to correlate with medulloblastomas. Recently, measurement of T(2)-weighted signal intensity (T2SI) was shown to be useful in identification of low-grade cerebellar neoplasms. The goal of this study was to assess whether objective findings on these MRI sequences reliably correlated with the underlying histopathology.

METHODS

We reviewed the radiologic findings of 50 pediatric patients who underwent resection of a cerebellar neoplasm since 2003 at our institution. Region of interest placement was used to calculate the relative diffusion-weighted signal intensity (rDWSI) and relative T2SI (rT2SI) of each neoplasm.

RESULTS

Tukey's multiple comparison test demonstrated medulloblastomas to have significantly higher rDWSIs than PAs/ependymomas, and PAs to have significantly higher rT2SIs than medulloblastomas/ependymomas. A simple method consisting of sequential measurement of rDWSI and rT2SI to predict histopathology was then constructed. Using this method, 39 of 50 (78%) tumors were accurately predicted.

CONCLUSION

Measurement of rDWSI and rT2SI using standard MRI of the brain can be used to predict histopathology with favorable accuracy in pediatric patients with cerebellar tumors.