RESUMEN
PURPOSE: Recurrence for high-grade gliomas is inevitable despite maximal safe resection and adjuvant chemoradiation, and current imaging techniques fall short in predicting future progression. However, we introduce a novel whole-brain magnetic resonance spectroscopy (WB-MRS) protocol that delves into the intricacies of tumor microenvironments, offering a comprehensive understanding of glioma progression to inform expectant surgical and adjuvant intervention. METHODS: We investigated five locoregional tumor metabolites in a post-treatment population and applied machine learning (ML) techniques to analyze key relationships within seven regions of interest: contralateral normal-appearing white matter (NAWM), fluid-attenuated inversion recovery (FLAIR), contrast-enhancing tumor at time of WB-MRS (Tumor), areas of future recurrence (AFR), whole-brain healthy (WBH), non-progressive FLAIR (NPF), and progressive FLAIR (PF). Five supervised ML classification models and a neural network were developed, optimized, trained, tested, and validated. Lastly, a web application was developed to host our novel calculator, the Miami Glioma Prediction Map (MGPM), for open-source interaction. RESULTS: Sixteen patients with histopathological confirmation of high-grade glioma prior to WB-MRS were included in this study, totaling 118,922 whole-brain voxels. ML models successfully differentiated normal-appearing white matter from tumor and future progression. Notably, the highest performing ML model predicted glioma progression within fluid-attenuated inversion recovery (FLAIR) signal in the post-treatment setting (mean AUC = 0.86), with Cho/Cr as the most important feature. CONCLUSIONS: This study marks a significant milestone as the first of its kind to unveil radiographic occult glioma progression in post-treatment gliomas within 8 months of discovery. These findings underscore the utility of ML-based WB-MRS growth predictions, presenting a promising avenue for the guidance of early treatment decision-making. This research represents a crucial advancement in predicting the timing and location of glioblastoma recurrence, which can inform treatment decisions to improve patient outcomes.
RESUMEN
Low-grade gliomas encompass a subgroup of cancerous glial cell growths within the central nervous system and are distinguished by their slow growth and relatively low malignant potential. Despite their less aggressive nature, these tumors can still cause significant neurological symptoms through the compression of surrounding neural and vascular structures and, in some instances, undergo malignant transformation. For these reasons, timely and appropriate evaluation and management of low-grade gliomas is critical. Medical imaging stands as a cornerstone for evaluating patients with low-grade gliomas because of its noninvasive nature and ability to provide a vast amount of information about the underlying lesion. With the growing number of neuroimaging techniques and their capabilities, there is a lack of clear guidance on which techniques to utilize for the assessment of low-grade gliomas and what their respective core use cases should be. In this literature review, the authors discuss in significant depth the available evidence pertaining to the use of advanced neuroimaging techniques in the evaluation and management of low-grade gliomas. Specifically, they review the specificity, sensitivity, accuracy, and use cases of magnetic resonance spectroscopy (MRS), perfusion MR imaging (perfusion MRI), diffusion tensor imaging (DTI), functional MRI (fMRI), positron emission tomography (PET), single-photon emission computed tomography (SPECT), as well as other emerging imaging techniques. They conclude that most of the advanced neuroimaging techniques are reliable in differentiating low- from high-grade gliomas, whereas MRS and DTI may further support molecular subclassification of the tumor. PET has been best employed for the purpose of tumor biopsy, whereas fMRI and DTI can be particularly valuable in preoperative surgical planning, as they delineate the functionally eloquent brain regions that need to be preserved during tumor resection. MRS, PET, SPECT, and perfusion MRI are best suited to monitor tumor progression, as their respective metrics closely correlate with the underlying metabolic activity of the tumor. Together, these techniques offer a vast amount of information and serve as tools for neurologists and neurosurgeons managing patients with low-grade gliomas.