Radiomics for the noninvasive prediction of the BRAF mutation status in patients with melanoma brain metastases

Abstract

Background The BRAF V600E mutation is present in approximately 50% of patients with melanoma brain metastases and an important prerequisite for response to targeted therapies, particularly BRAF inhibitors. As heterogeneity in terms of BRAF mutation status may occur in melanoma patients, a wild-type extracranial primary tumor does not necessarily rule out a targetable mutation in brain metastases using BRAF inhibitors. We evaluated the potential of MRI radiomics for a non-invasive prediction of the intracranial BRAF mutation status. Methods Fifty-nine patients with melanoma brain metastases from two university brain tumor centers (group 1, 45 patients; group 2, 14 patients) underwent tumor resection with subsequent genetic analysis of the intracranial BRAF mutation status. Preoperative contrast-enhanced MRI was manually segmented and analyzed. Group 1 was used for model training and validation, group 2 for model testing. After radiomics feature extraction, a test-retest analysis was performed to identify robust features prior to feature selection. Finally, the best performing radiomics model was applied to the test data. Diagnostic performances were evaluated using receiver operating characteristic (ROC) analyses. Results 22 of 45 patients (49%) in group 1, and 8 of 14 patients (57%) in group 2 had an intracranial BRAF V600E mutation. A linear support vector machine classifier using a six-parameter radiomics signature yielded an area under the ROC curve of 0.92 (sensitivity, 83%; specificity, 88%) in the test data. Conclusions The developed radiomics classifier allows a non-invasive prediction of the intracranial BRAF V600E mutation status in patients with melanoma brain metastases with high diagnostic performance.

The Role of [68Ga]Ga-DOTA-SSTR PET Radiotracers in Brain Tumors: A Systematic Review of the Literature and Ongoing Clinical Trials

“…[ 18 F]F-FDG and amino acid tracers (i.e., [ 11 C]C-MET, [ 18 F]F-FET, and [ 18 F]F-FDOPA) are mostly used in patients with gliomas, brain metastases, and primary central nervous system lymphomas (PCNSL). They show variable sensitivity and specificity in differentiating tumor tissue from the normal brain tissue, distinguishing post-treatment changes from tumor recurrences, and, more recently, predicting molecular patterns and patient prognosis when implemented for radiomics analyses [ 91 , 92 ]. In view of meningiomas’ overexpression of SSTR, especially SSTR2, [ 68 Ga]Ga-labeled DOTA (i.e., somatostatin analogue) tracers targeting SSTR, primarily developed for neuroendocrine tumors, have been largely used to allow highly selected meningioma uptake, low healthy brain tissue uptake, and, thus, higher specificity in the tumor-to-background contrast with excellent tumor visualization [ 59 , 79 ].…”

PET Imaging in Neuro-Oncology: An Update and Overview of a Rapidly Growing Area

“…Several PET radiomics analyses have been performed in neuro-oncology with promising accuracies ranging from 85 to 95% being reported. These include an initial diagnosis study to predict glioma grade with 18 F-FET [ 133 , 134 ], as well as studies to detect the IDH mutation in glioma with 18 F-FET [ 134 , 135 ] or 18 F-FDOPA [ 136 ], MGMT promoter methylation with 18 F-FDG [ 137 ] and BRAF mutation status in patients with melanoma brain metastases, although the latter study was only based on a small validation cohort [ 138 ]. Although performances with these radiomics analyses using 18 F-FET PET reach accuracies of around 80%, for glioma recurrences [ 132 , 139 ] and recurrent brain metastases [ 140 ], their added value over conventional analyses remains to be defined [ 141 ].…”

Radiomics as an emerging tool in the management of brain metastases

“…Another group has also published a support vector machine based classifier that could specifically predict the presence of BRAF V600E mutation in melanoma patients with BM with an accuracy of 86%. 102 The classifier incorporated features from CE-T1W images, T2W images, and clinical information.…”