Background: Neuroimaging differentiation of glioblastoma, primary central nervous system lymphoma (PCNSL) and solitary brain metastasis (BM) remains challenging in specific cases showing similar appearances or atypical features. Overall, advanced MRI protocols have high diagnostic reliability, but their limited worldwide availability, coupled with the overlapping of specific neuroimaging features among tumor subgroups, represent significant drawbacks and entail disparities in the planning and management of these oncological patients.Objective: To evaluate the classification performance metrics of a deep learning algorithm trained on T1-weighted gadolinium-enhanced (T1Gd) MRI scans of glioblastomas, atypical PCNSLs and BMs.Materials and Methods: We enrolled 121 patients (glioblastoma: n=47; PCNSL: n=37; BM: n=37) who had undergone preoperative T1Gd-MRI and histopathological confirmation. Each lesion was segmented, and all ROIs were exported in a DICOM dataset. The patient cohort was then split in a training and hold-out test sets following a 70/30 ratio. A Resnet101 model, a deep neural network (DNN), was trained on the training set and validated on the hold-out test set to differentiate glioblastomas, PCNSLs and BMs on T1Gd-MRI scans.Results: The DNN achieved optimal classification performance in distinguishing PCNSLs (AUC: 0.98; 95%CI: 0.95 - 1.00) and glioblastomas (AUC: 0.90; 95%CI: 0.81 - 0.97) and moderate ability in differentiating BMs (AUC: 0.81; 95%CI: 0.70 - 0.95). This performance may allow clinicians to correctly identify patients eligible for lesion biopsy or surgical resection.Conclusion: We trained and internally validated a deep learning model able to reliably differentiate ambiguous cases of PCNSLs, glioblastoma and BMs by means of T1Gd-MRI. The proposed predictive model may provide a low-cost, easily-accessible and high-speed decision-making support for eligibility to diagnostic brain biopsy or maximal tumor resection in atypical cases.

Background: Late neurocognitive sequelae are common among long-term brain tumour survivors, resulting in significantly worse quality of life. Cognitive rehabilitation through specific APP/software for PC/tablets represents an innovative intervention spreading in recent years. In this study, we aim to review the current evidence and trends regarding these innovative approaches. Methods: A systematic literature review was performed. Inclusion criteria were: (i) Studies recruiting patients diagnosed with any brain tumour before 21 years of age; (ii) studies assessing the role of digital interventions on cognitive outcomes. Case reports, case series, reviews, letters, conference proceedings, abstracts, and editorials were excluded. Results: Overall, nine studies were included; 152 patients (67.8% males) with brain tumours underwent a digital intervention. The mean age at diagnosis and the intervention enrolment ranged from 4.9 to 9.4 years and 11.1 to 13.3 years, respectively. The computer-based software interventions employed were: Cogmed, Captain’s Log, Fast ForWord, and Nintendo Wii. Most of these studies assessed the effects of cognitive training on working memory, attention, and performance in daily living activities. Conclusions: The studies suggest that this type of intervention improves cognitive functions, such as working memory, attention, and processing speed. However, some studies revealed only transient positive effects with a significant number of dropouts during follow-up. Trials with greater sample sizes are warranted. Motivating families and children to complete cognitive interventions could significantly improve cognitive outcomes and quality of life.

Object: To investigate those parameters affecting early and follow-up functional outcomes in patients undergoing resection of meningiomas and to design a dedicated predictive score, the Milan Bio(metric)-Surgical Score (MBSS) is hereby presented. Methods: Patients undergoing transcranial surgery for intracranial meningiomas were included. The most significant parameters in the regression analyses were implemented in a patient stratification score and were validated by testing its classification consistency with a clinical–radiological grading scale (CRGS), Milan complexity scale (MCS), and Charlson Comorbidity Index (CCI) scores. Results: The ASA score, Frailty index, skull base and posterior cranial fossa locations, a diameter of >25 mm, and the absence of a brain–tumour interface were predictive of early post-operative deterioration and were collected in MBSS Part A (AUC: 0.965; 95%C.I. 0.890–1.022), while the frailty index, posterior cranial fossa location, a diameter of >25 mm, a edema/tumour volume index of >2, dural sinus invasion, DWI hyperintensity, and the absence of a brain–tumour interface were predictive of a long-term unfavourable outcome and were collected in MBSS Part B (AUC: 0.877; 95%C.I. 0.811–0.942). The score was consistent with CRGS, MCS, and CCI. Conclusion: Patients’ multi-domain evaluation and the implementation of frailty indexes might help predict the perioperative complexity of cases; the functional, clinical, and neurological early outcomes; survival; and overall QoL after surgery.

(1) Background: Neuroimaging differentiation of glioblastoma, primary central nervous system lymphoma (PCNSL) and solitary brain metastasis (BM) represents a diagnostic and therapeutic challenge in neurosurgical practice, expanding the burden of care and exposing patients to additional risks related to further invasive procedures and treatment delays. In addition, atypical cases and overlapping features have not been entirely addressed by modern diagnostic research. The aim of this study was to validate a previously designed and internally validated ResNet101 deep learning model to differentiate glioblastomas, PCNSLs and BMs. (2) Methods: We enrolled 126 patients (glioblastoma: n = 64; PCNSL: n = 27; BM: n = 35) with preoperative T1Gd-MRI scans and histopathological confirmation. Each lesion was segmented, and all regions of interest were exported in a DICOM dataset. A pre-trained ResNet101 deep neural network model implemented in a previous work on 121 patients was externally validated on the current cohort to differentiate glioblastomas, PCNSLs and BMs on T1Gd-MRI scans. (3) Results: The model achieved optimal classification performance in distinguishing PCNSLs (AUC: 0.73; 95%CI: 0.62–0.85), glioblastomas (AUC: 0.78; 95%CI: 0.71–0.87) and moderate to low ability in differentiating BMs (AUC: 0.63; 95%CI: 0.52–0.76). The performance of expert neuro-radiologists on conventional plus advanced MR imaging, assessed by retrospectively reviewing the diagnostic reports of the selected cohort of patients, was found superior in accuracy for BMs (89.69%) and not inferior for PCNSL (82.90%) and glioblastomas (84.09%). (4) Conclusions: We investigated whether the previously published deep learning model was generalizable to an external population recruited at a different institution—this validation confirmed the consistency of the model and laid the groundwork for future clinical applications in brain tumour classification. This artificial intelligence-based model might represent a valuable educational resource and, if largely replicated on prospective data, help physicians differentiate glioblastomas, PCNSL and solitary BMs, especially in settings with limited resources.

Article: A supervised machine learning algorithm predicts intraoperative CSF leak in endoscopic transsphenoidal surgery for pituitary adenomas: model development and prospective validation - Journal of Neurosurgical Sciences 2021 Aug 03 - Minerva Medica - Journals