ABSTRACT
Pseudoprogression (PsP) is a diagnostic clinical dilemma in cancer. In this study, we retrospectively analyse glioblastoma patients, and using their dynamic susceptibility contrast and dynamic contrast-enhanced perfusion MRI images we build a classifier using radiomic features obtained from both Ktrans and rCBV maps coupled with support vector machines. We achieve an accuracy of 90.82% (area under the curve (AUC) = 89.10%, sensitivity = 91.36%, 67 specificity = 88.24%, p = 0.017) in differentiating between pseudoprogression (PsP) and progressive disease (PD). The diagnostic performances of the models built using radiomic features from Ktrans and rCBV separately were equally high (Ktrans: AUC = 94%, 69 p = 0.012; rCBV: AUC = 89.8%, p = 0.004). Thus, this MR perfusion-based radiomic model demonstrates high accuracy, sensitivity and specificity in discriminating PsP from PD, thus provides a reliable alternative for noninvasive identification of PsP versus PD at the time of clinical/radiologic question. This study also illustrates the successful application of radiomic analysis as an advanced processing step on different MR perfusion maps.
Subject(s)
Brain Neoplasms/diagnostic imaging , Brain Neoplasms/diagnosis , Glioblastoma/diagnostic imaging , Glioblastoma/diagnosis , Magnetic Resonance Imaging/methods , Brain Neoplasms/pathology , Disease Progression , Female , Glioblastoma/pathology , Humans , Male , Middle Aged , Retrospective Studies , Sensitivity and Specificity , Support Vector MachineABSTRACT
PURPOSE: To evaluate the role of multimodality imaging tools for intraprocedural guidance and outcome evaluation during sclerotherapy of low-flow orbital vascular malformations. MATERIALS AND METHODS: A retrospective review was performed of 17 consecutive patients with low-flow orbital malformations (14 lymphatic, two venous, and one venolymphatic) who underwent multimodality image-guided sclerotherapy between November 2012 and May 2015. Sclerotherapy technique, image guidance tools, and complications were recorded. Sclerotherapy outcome was evaluated using clinical response, magnetic resonance (MR) image-based lesion volumetry, and proptosis quantification. RESULTS: There were 22 sclerotherapy sessions performed. Intraprocedural ultrasound (US), fluoroscopy, cone-beam computed tomography (CT) and MR image fusion were used for image guidance with 100% technical success. Resolution of presenting symptoms was observed in all patients at 1-month follow-up. Four major sclerotherapy complications were successfully managed. Statistically significant reduction in lesion volume (P = .001) and proptosis (P = .0117) by MR image analysis was achieved in all patients in whom 3-month follow-up MR imaging was available (n = 13/17). There was no lesion recurrence at a median follow-up of 18 months (range, 8-38 mo). CONCLUSIONS: Multimodality imaging tools, including US, fluoroscopy, cone-beam CT, and MR fusion, during sclerotherapy of low-flow orbital malformations provide intraprocedural guidance and quantitative image-based evaluation of treatment outcome.
