Editorial: Current Challenges and Future Perspectives in Neuro-Oncological Imaging

Emma Gangemi^1,2*Paola Feraco³Carlo Augusto Mallio^4,5

• ¹Regina Elena National Cancer Institute, Hospital Physiotherapy Institutes (IRCCS), Rome, Italy
• ²Universita degli Studi di Roma La Sapienza Dipartimento di Neuroscienze Umane, Rome, Italy
• ³Centre for Medical Sciences (CISMed), University of Trento, Trento, Italy, Trento, Italy
• ⁴Fondazione Policlinico Universitario Campus Bio-Medico, Rome, Italy
• ⁵Research Unit of Diagnostic Imaging, Department of Medicine and Surgery, Università Campus Bio-Medico di Roma, Rome, Italy, Rome, Italy

Over 100 distinct types of primary CNS tumors contribute to a variety of histopathological and molecular profiles, each with unique clinical presentations, treatment strategies, and prognostic implications. Recent advancements in molecular diagnostics, along with traditional histology and immunohistochemistry, have enhanced our understanding of the histogenetic classification of these tumors, as reflected in the latest WHO classification (5th edition) of brain tumors [1]. Despite therapeutic advancements, the prognosis for patients with brain tumors, particularly those with high-grade neoplasms, remains poor.The heterogeneity and complexity of these tumors underscore the need for personalized, targeted treatment approaches. Quantitative MRI (qMRI) and Artificial Intelligence (AI) are key tools in modern neuro-oncology, providing advanced diagnostic and prognostic capabilities [2][3][4]. qMRI quantifies diffusion, perfusion, and metabolism, while AI-using Deep Learning and Radiomics-automates tumor analysis and integrates imaging with genetic and clinical data. Together, they improve accuracy, reproducibility, and treatment planning, driving progress in precision medicine for brain tumors [5][6][7]. Automated volumetric assessment reduces interobserver variability and predicts survival more reliably than manual measurements [8,9].The goal of this Research Topic was to review recent advancements in neuro-oncological imaging modalities and their impact on managing brain tumors. By focusing on innovations in diagnosis, cancer staging, prognostication, pre-treatment assessment, and treatment monitoring, we aimed to highlight the enhanced accuracy and effectiveness these tools bring to neuro-oncology, optimizing personalized healthcare strategies. of 17 tumors (seven bilateral and three unilateral) vestibular schwannomas (VS) were segmented using both manual and AI-based methods, and the effect of voxel size on segmentation precision was quantified through volume measurements. Across the dataset, the authors observed a clear inverse relationship between voxel size and segmentation accuracy. Smaller voxel sizes (e.g., 0.5 × 0.5 × 0.8 mm) significantly improved the accuracy and consistency of both manual and AI-based tumor segmentation, while larger voxels reduced precision. AI segmentation was more robust and showed reduced variability than manual methods, especially at lower resolutions. The study concludes that high-resolution MRI and AI-driven segmentation are essential for reliable tumor monitoring and treatment planning in patients with NF2-related vestibular schwannomas.