Search

Purpose: MRI-based radiomics models can predict genetic markers in pediatric low-grade glioma (pLGG). These models usually require tumour segmentation, which is tedious and time consuming if done manually. We propose a deep learning (DL) model to automate tumour segmentation and build an end-to-end radiomics-based pipeline for pLGG classification. Methods: The proposed architecture is a 2-step U-Net based DL network. The first U-Net is trained on downsampled images to locate the tumour. The second U-Net is trained using image patches centred around the located tumour to produce more refined segmentations. The segmented tumour is then fed into a radiomics-based model to predict the genetic marker of the tumour. Results: Our segmentation model achieved a correlation value of over 80% for all volume-related radiomic features and an average Dice score of.795 in test cases. Feeding the auto-segmentation results into a radiomics model resulted in a mean area under the ROC curve (AUC) of.843, with 95% confidence interval (CI) [.78-.906] and.730, with 95% CI [.671-.789] on the test set for 2-class (BRAF V600E mutation BRAF fusion) and 3-class (BRAF V600E mutation BRAF fusion and Other) classification, respectively. This result was comparable to the AUC of.874, 95% CI [.829-.919] and.758, 95% CI [.724-.792] for the radiomics model trained and tested on the manual segmentations in 2-class and 3-class classification scenarios, respectively. Conclusion: The proposed end-to-end pipeline for pLGG segmentation and classification produced results comparable to manual segmentation when it was used for a radiomics-based genetic marker prediction model. [ABSTRACT FROM AUTHOR]

The use of targeted agents in the treatment of pediatric low-grade gliomas (pLGGs) relies on the determination of molecular status. It has been shown that genetic alterations in pLGG can be identified non-invasively using MRI-based radiomic features or convolutional neural networks (CNNs). We aimed to build and assess a combined radiomics and CNN non-invasive pLGG molecular status identification model. This retrospective study used the tumor regions, manually segmented from T2-FLAIR MR images, of 336 patients treated for pLGG between 1999 and 2018. We designed a CNN and Random Forest radiomics model, along with a model relying on a combination of CNN and radiomic features, to predict the genetic status of pLGG. Additionally, we investigated whether CNNs could predict radiomic feature values from MR images. The combined model (mean AUC: 0.824) outperformed the radiomics model (0.802) and CNN (0.764). The differences in model performance were statistically significant (p-values < 0.05). The CNN was able to learn predictive radiomic features such as surface-to-volume ratio (average correlation: 0.864), and difference matrix dependence non-uniformity normalized (0.924) well but was unable to learn others such as run-length matrix variance (− 0.017) and non-uniformity normalized (− 0.042). Our results show that a model relying on both CNN and radiomic-based features performs better than either approach separately in differentiating the genetic status of pLGGs, and that CNNs are unable to express all handcrafted features. [ABSTRACT FROM AUTHOR]

Intoduction: Diffuse leptomeningeal glioneuronal tumors (DLGNTs) pose a rare and challenging entity within pediatric central nervous system neoplasms. Despite their rarity, DLGNTs exhibit complex clinical presentations and unique molecular characteristics, necessitating a deeper understanding of their diagnostic and therapeutic nuances. Methods: This review synthesizes contemporary literature on DLGNT, encompassing epidemiology, clinical manifestations, pathological features, treatment strategies, prognostic markers, and future research directions. To compile the existing body of knowledge on DLGNT, a comprehensive search of relevant databases was conducted. Results: DLGNT primarily affects pediatric populations but can manifest across all age groups. Its diagnosis is confounded by nonspecific clinical presentations and overlapping radiological features with other CNS neoplasms. Magnetic resonance imaging (MRI) serves as a cornerstone for DLGNT diagnosis, revealing characteristic leptomeningeal enhancement and intraparenchymal involvement. Histologically, DLGNT presents with low to moderate cellularity and exhibits molecular alterations in the MAPK/ERK signalling pathway. Optimal management of DLGNT necessitates a multidisciplinary approach encompassing surgical resection, chemotherapy, radiotherapy, and emerging targeted therapies directed against specific genetic alterations. Prognostication remains challenging, with factors such as age at diagnosis, histological subtypes, and genetic alterations influencing disease progression and treatment response. Long-term survival data are limited, underscoring the need for collaborative research efforts. Conclusion: Advancements in molecular profiling, targeted therapies, and international collaborations hold promise for improving DLGNT outcomes. Harnessing the collective expertise of clinicians, researchers, and patient advocates, can advance the field of DLGNT research and optimize patient care paradigms. [ABSTRACT FROM AUTHOR]

Objectives: Currently, the BRAF status of pediatric low-grade glioma (pLGG) patients is determined through a biopsy. We established a nomogram to predict BRAF status non-invasively using clinical and radiomic factors. Additionally, we assessed an advanced thresholding method to provide only high-confidence predictions for the molecular subtype. Finally, we tested whether radiomic features provide additional predictive information for this classification task, beyond that which is embedded in the location of the tumor. Methods: Random forest (RF) models were trained on radiomic and clinical features both separately and together, to evaluate the utility of each feature set. Instead of using the traditional single threshold technique to convert the model outputs to class predictions, we implemented a double threshold mechanism that accounted for uncertainty. Additionally, a linear model was trained and depicted graphically as a nomogram. Results: The combined RF (AUC: 0.925) outperformed the RFs trained on radiomic (AUC: 0.863) or clinical (AUC: 0.889) features alone. The linear model had a comparable AUC (0.916), despite its lower complexity. Traditional thresholding produced an accuracy of 84.5%, while the double threshold approach yielded 92.2% accuracy on the 80.7% of patients with the highest confidence predictions. Conclusion: Models that included radiomic features outperformed, underscoring their importance for the prediction of BRAF status. A linear model performed similarly to RF but with the added benefit that it can be visualized as a nomogram, improving the explainability of the model. The double threshold technique was able to identify uncertain predictions, enhancing the clinical utility of the model. Clinical relevance statement: Radiomic features and tumor location are both predictive of BRAF status in pLGG patients. We show that they contain complementary information and depict the optimal model as a nomogram, which can be used as a non-invasive alternative to biopsy. Key Points: • Radiomic features provide additional predictive information for the determination of the molecular subtype of pediatric low-grade gliomas patients, beyond what is embedded in the location of the tumor, which has an established relationship with genetic status. • An advanced thresholding method can help to distinguish cases where machine learning models have a high chance of being (in)correct, improving the utility of these models. • A simple linear model performs similarly to a more powerful random forest model at classifying the molecular subtype of pediatric low-grade gliomas but has the added benefit that it can be converted into a nomogram, which may facilitate clinical implementation by improving the explainability of the model. [ABSTRACT FROM AUTHOR]

Hippocampal sclerosis (HS) is a common surgical substrate in adult epilepsy surgery cohorts but variably reported in various pediatric cohorts. We aimed to study the epilepsy phenotype, radiological and pathological variability, seizure and neurocognitive outcomes in children with drug-resistant epilepsy and hippocampal sclerosis (HS) with or without additional subtle signal changes in anterior temporal lobe who underwent surgery. This retrospective study enrolled children with drug-resistant focal epilepsy and hippocampal sclerosis with or without additional subtle T2-Fluid Attenuated Inversion Recovery (FLAR)/Proton Density (PD) signal changes in anterior temporal lobe who underwent anterior temporal lobectomy with amygdalohippocampectomy. Their clinical, EEG, neuropsychological, radiological and pathological data were reviewed and summarized. Thirty-six eligible patients were identified. The mean age at seizure onset was 3.7 years; 25% had daily seizures at time of surgery. Isolated HS was noted in 22 (61.1%) cases and additional subtle signal changes in ipsilateral temporal lobe in 14 (38.9%) cases. Compared to the normative population, the group mean performance in intellectual functioning and most auditory and visual memory tasks were significantly lower than the normative sample. The mean age at surgery was 12.3 years; 22 patients (61.1%) had left hemispheric surgeries. ILAE class 1 outcomes was seen in 28 (77.8%) patients after a mean follow up duration of 2.3 years. Hippocampal sclerosis was noted pathologically in 32 (88.9%) cases; type 2 (54.5%) was predominant subtype where further classification was possible. Additional pathological abnormalities were seen in 11 cases (30.6%); these had had similar rates of seizure freedom as compared to children with isolated hippocampal sclerosis/gliosis (63.6% vs 84%, p=0.21). Significant reliable changes were observed across auditory and visual memory tasks at an individual level post surgery. Favourable seizure outcomes were seen in most children with isolated radiological hippocampal sclerosis. Patients with additional pathological abnormalities had similar rates of seizure freedom as compared to children with isolated hippocampal sclerosis/gliosis. • Subtle anterior temporal signal changes were noted in 38.9% children with hippocampal sclerosis (HS). • 77.8% children became seizure free after anterior temporal lobectomy with amygdalohippocampectomy. • Overall, 30.6% cases had additional pathological abnormalities. • Seizure freedom rates of children with additional pathological abnormalities similar to those with isolated HS. [ABSTRACT FROM AUTHOR]

Pediatric-type low-grade glioma (PLGG) encompasses a heterogeneous group of WHO grade 1 or 2 tumors and is the most common central nervous system tumor found in children. PLGG extends beyond pediatrics, into adolescents and young adults (AYA, ages 15–40). PLGG represents 25% of all gliomas diagnosed in AYA with differences in tumor location and molecular alterations compared to children, resulting in improved outcome for AYAs. Long-term outcome is excellent, though patients may suffer significant morbidity depending on tumor location. There are differences in treatment practices with radiation used to treat PLGG in AYAs more often than in children. Most PLGG in AYA harbor an alteration in the RAS/MAPK pathway, with limited insight into response to targeted therapy in this age group. This review discusses the epidemiology, current therapeutic approaches, and challenges in the management of PLGG in AYA. [ABSTRACT FROM AUTHOR]