SEOM-GEINO clinical guidelines for high-grade gliomas of adulthood (2022)

High costs, low quality of life, reduced survival, and room for improving treatment: an analysis of burden and unmet needs in glioma

Gliomas are a group of heterogeneous tumors that account for substantial morbidity, mortality, and costs to patients and healthcare systems globally. Survival varies considerably by grade, histology, biomarkers, and genetic alterations such as IDH mutations and MGMT promoter methylation, and treatment, but is poor for some grades and histologies, with many patients with glioblastoma surviving less than a year from diagnosis. The present review provides an introduction to glioma, including its classification, epidemiology, economic and humanistic burden, as well as treatment options. Another focus is on treatment recommendations for IDH-mutant astrocytoma, IDH-mutant oligodendroglioma, and glioblastoma, which were synthesized from recent guidelines. While recommendations are nuanced and reflect the complexity of the disease, maximum safe resection is typically the first step in treatment, followed by radiotherapy and/or chemotherapy using temozolomide or procarbazine, lomustine, and vincristine. Immunotherapies and targeted therapies currently have only a limited role due to disappointing clinical trial results, including in recurrent glioblastoma, for which the nitrosourea lomustine remains the de facto standard of care. The lack of treatment options is compounded by frequently suboptimal clinical practice, in which patients do not receive adequate therapy after resection, including delayed, shortened, or discontinued radiotherapy and chemotherapy courses due to treatment side effects. These unmet needs will require significant efforts to address, including a continued search for novel treatment options, increased awareness of clinical guidelines, improved toxicity management for chemotherapy, and the generation of additional and more robust clinical and health economic evidence.

Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology

Machine Learning is entering a phase of maturity, but its medical applications still lag behind in terms of practical use. The field of oncological radiology (and neuro-oncology in particular) is at the forefront of these developments, now boosted by the success of Deep-Learning methods for the analysis of medical images. This paper reviews in detail some of the most recent advances in the use of Deep Learning in this field, from the broader topic of the development of Machine-Learning-based analytical pipelines to specific instantiations of the use of Deep Learning in neuro-oncology; the latter including its use in the groundbreaking field of ultra-low field magnetic resonance imaging.