The precise initial characterization of contrast-enhancing brain tumors has significant consequences for clinical outcomes. Various novel neuroimaging methods have been developed to increase the specificity of conventional magnetic resonance imaging (cMRI) but also the increased complexity of data analysis. Artificial intelligence offers new options to manage this challenge in clinical settings. Here, we investigated whether multiclass machine learning (ML) algorithms applied to a high-dimensional panel of radiomic features from advanced MRI (advMRI) and physiological MRI (phyMRI; thus, radiophysiomics) could reliably classify contrast-enhancing brain tumors. The recently developed phyMRI technique enables the quantitative assessment of microvascular architecture, neovascularization, oxygen metabolism, and tissue hypoxia. A training cohort of 167 patients suffering from one of the five most common brain tumor entities (glioblastoma, anaplastic glioma, meningioma, primary CNS lymphoma, or brain metastasis), combined with nine common ML algorithms, was used to develop overall 135 classifiers. Multiclass classification performance was investigated using tenfold cross-validation and an independent test cohort. Adaptive boosting and random forest in combination with advMRI and phyMRI data were superior to human reading in accuracy (0.875 vs. 0.850), precision (0.862 vs. 0.798), F-score (0.774 vs. 0.740), AUROC (0.886 vs. 0.813), and classification error (5 vs. 6). The radiologists, however, showed a higher sensitivity (0.767 vs. 0.750) and specificity (0.925 vs. 0.902). We demonstrated that ML-based radiophysiomics could be helpful in the clinical routine diagnosis of contrast-enhancing brain tumors; however, a high expenditure of time and work for data preprocessing requires the inclusion of deep neural networks.

Background: Corticosteroid therapy (CST) prior to biopsy may hinder histopathological diagnosis in primary central nervous system lymphoma (PCNSL). Therefore, preoperative CST in patients with suspected PCNSL should be avoided if clinically possible. The aim of this study was thus to analyze the difference in the rate of diagnostic surgeries in PCNSL patients with and without preoperative CST. Methods: A multicenter retrospective study including all immunocompetent patients diagnosed with PCNSL between 1/2004 and 9/2018 at four neurosurgical centers in Austria was conducted and the results were compared to literature. Results: A total of 143 patients were included in this study. All patients showed visible contrast enhancement on preoperative MRI. There was no statistically significant difference in the rate of diagnostic surgeries with and without preoperative CST with 97.1% (68/70) and 97.3% (71/73), respectively (p = 1.0). Tapering and pause of CST did not influence the diagnostic rate. Including our study, there are 788 PCNSL patients described in literature with an odds ratio for inconclusive surgeries after CST of 3.3 (CI 1.7–6.4). Conclusions: Preoperative CST should be avoided as it seems to diminish the diagnostic rate of biopsy in PCNSL patients. Yet, if CST has been administered preoperatively and there is still a contrast enhancing lesion to target for biopsy, surgeons should try to keep the diagnostic delay to a minimum as the likelihood for acquiring diagnostic tissue seems sufficiently high.

Purpose: Insufficient control of infiltrative glioblastoma (GBM) cells is a major cause of treatment failure and tumor recurrence. Hence, detailed insights into pathophysiologic changes that precede GBM recurrence are needed to develop more precise neuroimaging modalities for tailored diagnostic monitoring and therapeutic approaches. Experimental Design: Overall, 168 physiologic MRI follow-up examinations of 56 patients with GBM who developed recurrence after standard therapy were retrospectively evaluated, that is, two post–standard-therapeutic follow-ups before and one at radiological recurrence. MRI biomarkers for microvascular architecture and perfusion, neovascularization activity, oxygen metabolism, and hypoxia were determined for brain areas that developed in the further course into recurrence and for the recurrent GBM itself. The temporal pattern of biomarker changes was fitted with locally estimated scatterplot smoothing functions and analyzed for pathophysiologic changes preceding radiological GBM recurrence. Results: Our MRI approach demonstrated early pathophysiologic changes prior to radiological GBM recurrence in all patients. Analysis of the time courses revealed a model for the pathophysiology of GBM recurrence: 190 days prior to radiological recurrence, vascular cooption by GBM cells induced vessel regression, detected as decreasing vessel density/perfusion and increasing hypoxia. Seventy days later, neovascularization activity was upregulated, which reincreased vessel density and perfusion. Hypoxia, however, continued to intensify for 30 days and peaked 90 days before radiological recurrence. Conclusions: Hypoxia may represent an early sign for GBM recurrence. This might become useful in the development of new combined diagnostic–therapeutic approaches for tailored clinical management of recurrent GBM. Further preclinical and in-human studies are required for validation and evaluation.

In this study, we assessed the prognostic relevance of temporal muscle thickness (TMT), likely reflecting patient’s frailty, in patients with primary central nervous system lymphoma (PCNSL). In 128 newly diagnosed PCNSL patients TMT was analyzed on cranial magnetic resonance images. Predefined sex-specific TMT cutoff values were used to categorize the patient cohort. Survival analyses, using a log-rank test as well as Cox models adjusted for further prognostic parameters, were performed. The risk of death was significantly increased for PCNSL patients with reduced muscle thickness (hazard ratio of 3.189, 95% CI: 2–097–4.848, p < 0.001). Importantly, the results confirmed that TMT could be used as an independent prognostic marker upon multivariate Cox modeling (hazard ratio of 2.504, 95% CI: 1.608–3.911, p < 0.001) adjusting for sex, age at time of diagnosis, deep brain involvement of the PCNSL lesions, Eastern Cooperative Oncology Group (ECOG) performance status, and methotrexate-based chemotherapy. A TMT value below the sex-related cutoff value at the time of diagnosis is an independent adverse marker in patients with PCNSL. Thus, our results suggest the systematic inclusion of TMT in further translational and clinical studies designed to help validate its role as a prognostic biomarker.

Glioblastoma (GB) and brain metastasis (BM) are the most frequent types of brain tumors in adults. Their therapeutic management is quite different and a quick and reliable initial characterization has a significant impact on clinical outcomes. However, the differentiation of GB and BM remains a major challenge in today’s clinical neurooncology due to their very similar appearance in conventional magnetic resonance imaging (MRI). Novel metabolic neuroimaging has proven useful for improving diagnostic performance but requires artificial intelligence for implementation in clinical routines. Here; we investigated whether the combination of radiomic features from MR-based oxygen metabolism (“oxygen metabolic radiomics”) and deep convolutional neural networks (CNNs) can support reliably pre-therapeutic differentiation of GB and BM in a clinical setting. A self-developed one-dimensional CNN combined with radiomic features from the cerebral metabolic rate of oxygen (CMRO₂) was clearly superior to human reading in all parameters for classification performance. The radiomic features for tissue oxygen saturation (mitoPO₂; i.e., tissue hypoxia) also showed better diagnostic performance compared to the radiologists. Interestingly, both the mean and median values for quantitative CMRO₂ and mitoPO₂ values did not differ significantly between GB and BM. This demonstrates that the combination of radiomic features and DL algorithms is more efficient for class differentiation than the comparison of mean or median values. Oxygen metabolic radiomics and deep neural networks provide insights into brain tumor phenotype that may have important diagnostic implications and helpful in clinical routine diagnosis.

Primary central nervous system lymphomas (PCNSL) are rare CNS tumors that harbor a conspicuously longer diagnostic delay compared to other malignant brain tumors. The gold standard for diagnosis is stereotactic biopsy to acquire tissue for histopathological analysis and therefore neurosurgery plays a central role when reducing the diagnostic period is mandated. However, histopathological diagnosis could be complicated if the patient was preoperatively exposed to corticosteroids. Besides the histopathological result, diagnosis of a PCNSL also requires full diagnostic workup to exclude cerebral metastatic disease of a systemic lymphoma. Most reviews of PCNSL discuss recent advancements in systemic treatment options from an (neuro-)oncologic viewpoint, whereas our intention was to discuss the optimization of the diagnostic period and therefore describe current standards of imaging, summarizing the diagnostic workup, discussing the surgical workup and future diagnostic prospects as well as the influence of preoperative corticosteroid therapy to reduce the diagnostic delay of PCNSL patients.