A deep learning model for differentiating paediatric intracranial germ cell tumour subtypes and predicting survival with MRI: a multicentre prospective study.

BACKGROUND: The pretherapeutic differentiation of subtypes of primary intracranial germ cell tumours (iGCTs), including germinomas (GEs) and nongerminomatous germ cell tumours (NGGCTs), is essential for clinical practice because of distinct treatment strategies and prognostic profiles of these diseases. This study aimed to develop a deep learning model, iGNet, to assist in the differentiation and prognostication of iGCT subtypes by employing pretherapeutic MR T2-weighted imaging. METHODS: The iGNet model, which is based on the nnUNet architecture, was developed using a retrospective dataset of 280 pathologically confirmed iGCT patients. The training dataset included 83 GEs and 117 NGGCTs, while the retrospective internal test dataset included 31 GEs and 49 NGGCTs. The model's diagnostic performance was then assessed with the area under the receiver operating characteristic curve (AUC) in a prospective internal dataset (n = 22) and two external datasets (n = 22 and 20). Next, we compared the diagnostic performance of six neuroradiologists with or without the assistance of iGNet. Finally, the predictive ability of the output of iGNet for progression-free and overall survival was assessed and compared to that of the pathological diagnosis. RESULTS: iGNet achieved high diagnostic performance, with AUCs between 0.869 and 0.950 across the four test datasets. With the assistance of iGNet, the six neuroradiologists' diagnostic AUCs (averages of the four test datasets) increased by 9.22% to 17.90%. There was no significant difference between the output of iGNet and the results of pathological diagnosis in predicting progression-free and overall survival (P = .889). CONCLUSIONS: By leveraging pretherapeutic MR imaging data, iGNet accurately differentiates iGCT subtypes, facilitating prognostic evaluation and increasing the potential for tailored treatment.

Whole-exome sequencing has revealed novel genetic characteristics in intracranial germ cell tumours in the Chinese.

AIMS: Intracranial germ cell tumour (IGCT) is a type of rare central nervous system tumour that mainly occurs in children and adolescents, with great variation in its incidence rate and molecular characteristics in patients from different populations. The genetic alterations of IGCT in the Chinese population are still unknown. METHODS AND RESULTS: In this study, 47 patients were enrolled and their tumour specimens were analysed by whole-exome sequencing (WES). We found that KIT was the most significantly mutated gene (15/47, 32%), which mainly occurred in the germinoma group (13/20, 65%), and less frequently in NGGCT (2/27, 7%). Copy number variations (CNVs) of FGF6 and TFE3 only appeared in NGGCT patients (P = 0.003 and 0.032, respectively), while CNVs of CXCR4, RAC2, PDGFA, and FEV only appeared in germinoma patients (P = 0.004 of CXCR4 and P = 0.027 for the last three genes). Compared with a previous Japanese cohort, the somatic mutation rates of RELN and SYNE1 were higher in the Chinese. Prognostic analysis showed that the NF1 mutation was associated with shorter overall survival and progression-free survival in IGCT patients. Clonal evolution analysis revealed an early branched evolutionary pattern in two IGCT patients who underwent changes in the histological subtype or degree of differentiation during disease surveillance. CONCLUSION: This study indicated that Chinese IGCT patients may have distinct genetic characteristics and identified several possible genetic alterations that have the potential to become prognostic biomarkers of NGGCT patients.

Non-invasive differential diagnosis of teratomas from other intracranial germ cell tumours using MRI-based fractal and radiomic analyses.

OBJECTIVES: The histologic subtype of intracranial germ cell tumours (IGCTs) is an important factor in deciding the treatment strategy, especially for teratomas. In this study, we aimed to non-invasively diagnose teratomas based on fractal and radiomic features. MATERIALS AND METHODS: This retrospective study included 330 IGCT patients, including a discovery set (n = 296) and an independent validation set (n = 34). Fractal and radiomic features were extracted from T1-weighted, T2-weighted, and post-contrast T1-weighted images. Five classifiers, including logistic regression, random forests, support vector machines, K-nearest neighbours, and XGBoost, were compared for our task. Based on the optimal classifier, we compared the performance of clinical, fractal, and radiomic models and the model combining these features in predicting teratomas. RESULTS: Among the diagnostic models, the fractal and radiomic models performed better than the clinical model. The final model that combined all the features showed the best performance, with an area under the curve, precision, sensitivity, and specificity of 0.946 [95% confidence interval (CI): 0.882-0.994], 95.65% (95% CI: 88.64-100%), 88.00% (95% CI: 77.78-96.36%), and 91.67% (95% CI: 78.26-100%), respectively, in the test set of the discovery set, and 0.944 (95% CI: 0.855-1.000), 85.71% (95% CI: 68.18-100%), 94.74% (95% CI: 83.33-100%), and 80.00% (95% CI: 58.33-100%), respectively, in the independent validation set. SHapley Additive exPlanations indicated that two fractal features, two radiomic features, and age were the top five features highly associated with the presence of teratomas. CONCLUSION: The predictive model including image and clinical features could help guide treatment strategies for IGCTs. CLINICAL RELEVANCE STATEMENT: Our machine learning model including image and clinical features can non-invasively predict teratoma components, which could help guide treatment strategies for intracranial germ cell tumours (IGCT). KEY POINTS: • Fractals and radiomics can quantitatively evaluate imaging characteristics of intracranial germ cell tumours. • Model combing imaging and clinical features had the best predictive performance. • The diagnostic model could guide treatment strategies for intracranial germ cell tumours.

Depression, anxiety and health-related quality of life in paediatric intracranial germ cell tumor survivors.

BACKGROUND: Little is known about depression and anxiety among paediatric intracranial germ cell tumour (iGCT) survivors. We aimed to evaluate the risk factors associated with depression, anxiety and health-related quality of life (HRQoL) in paediatric iGCT survivors. METHODS: We recruited 200 iGCT patients (and their parents) from Beijing Tiantan Hospital and assessed their HRQoL using the Paediatric Quality of Life Inventory (PedsQL) 4.0 Generic Core Scales. The Children's Depression Inventory, Screen for Child Anxiety Related Emotional Disorders, and Symptom Checklist 90 were used to evaluate depression and anxiety. The results were analysed based on disease recurrence, tumour location and treatment strategies. RESULTS: Survivors with recurrent tumours had worse HRQoL scores than those with non-recurrent tumours. Patients with tumours involving both the suprasellar and basal ganglia regions had the worst HRQoL scores. A large proportion of survivors had depression or anxiety. Both depression and anxiety scores were highly correlated with the HRQoL emotional functioning scores. The parent proxy-reports (PPR) and child self-reports were highly correlated in all domains. CONCLUSIONS: This study demonstrated the clinical factors affecting paediatric iGCT survivors' depression, anxiety, and HRQoL. Therefore, psychological interventions should be implemented. It also suggests that the PedsQL PPR would be helpful for routine screening.

Radiological Latency in Pineal Germinoma: A Case Report and Literature Review.

Suprasellar germinomas can present with non-diagnostic, or even normal results on imaging. The spectrum of reported cases ranges from normal imaging, thickened pituitary stalks, to discrete tumour growths. This similar phenomenon is less commonly seen in the pineal region, or bifocal germinomas, and the literature is sparse with only a few case series or reports mentioning a similar presentation of signs and symptoms preceding radiological evidence of diagnosis. We report a case of pineal germinoma presenting with dorsal midbrain syndrome with no evidence of tumour growth on initial imaging despite symptoms. For patients presenting with this clinical radiological latent period, follow-up imaging is useful to identify interval development of germinomas. This applies to patients with dorsal midbrain syndrome, or even other unexplained ophthalmoplegia, as the initial sign of pineal region germinoma, despite normal imaging.

Evaluation of treatment response using integrated 18F-labeled choline positron emission tomography/magnetic resonance imaging in adolescents with intracranial non-germinomatous germ cell tumours.

The efficacy of hybrid 18F-Fluroethyl-Choline (FEC) positron emission tomography (PET)/magnetic resonance imaging (MRI) was investigated as an imaging modality for diagnosis and assessment of treatment response and remission status in four patients with proven or suspected intracranial non-germinomatous germ cell tumours (NGGCT). In two patients faint or absent choline avidity correlated with negative histology, whereas in other two patients, persistent choline avidity in the residual mass was suggestive of presence of viable tumour, subsequently confirmed histologically. We conclude that FEC-PET/MRI may be an effective imaging tool in detecting viable residual tumour in patients with intracranial NGGCT post treatment.

Hedgehog signalling network gene status analysis in paediatric intracranial germ cell tumours.

INTRODUCTION: Germ cell tumours (GCTs) in the children comprise a group of tumours that originate from primordial germ cells but their pathogenesis is not clear. Intracranial GCTs represent a special subset of these paediatric neoplasms. Hedgehog (Hh) pathway gene status in GCTs is generally unexplored, while Hh signalling is involved in germ cell biology. MATERIAL AND METHODS: Comparative genomic profiling analysis with a microarray-comparative genomic hybridization (CGH) + single nucleotide polymorphism (SNP) technique in a group of intracranial paediatric GCTs was performed. The analysis included evaluation of genes being ligands, receptors, regulators, effectors, and targets of Hh signalling. RESULTS: Chromosomal aberrations were found in 62% of examined tumours, showing their heterogeneity. A number of private genomic imbalances were observed, but only a few recurrent ones. The most common numerical changes were trisomies 19, 21 and monosomies 13, 18 while the most frequent structural aberration was gain/amplification of the chromosome 12p. The analysis of the gene status of Hh network elements showed imbalances in a proportion of tumours. PTCH1, GLI2, IHH and ZIC2 gene aberrations occurred most frequently. Moreover, six tumours had various copy gains or losses of several other genes involved in the pathway, including HHIP, GLI1, GLI3, DHH, SHH, SMO, PTCH2, and several genes from the WNT group. Interestingly, four cases showed losses of pathway repressors, with parallel gains of activators in two of them. Correlations with patho-clinical tumour features were not found, most probably due to the heterogeneity of the examined limited group. CONCLUSIONS: Our results show few genomic alterations related to the Hh signalling pathway genes in paediatric intracranial GCTs. Further analysis of Hedgehog pathway alterations can potentially disclose its biological significance and define new prognostic factors and/or therapeutic targets for high-risk patients.

Current Management of Intracranial Germ Cell Tumours.

Intracranial germ cell tumours (icGCTs) are uncommon tumours occurring in children and young adults. They are usually segregated into germinomas and non-germinomatous tumours (NGGCTs) in most classifications. Germinomas are highly curable tumours with multimodality treatment, but NGGCTs are associated with poorer survival outcomes. There are some differences in the approach to the management of icGCTs globally. Current research generally focuses on reducing treatment intensity, particularly the dose and volume of radiotherapy, in order to minimise the risks of late sequelae while maintaining high cure rates in icGCTs.