Final Report on Clinical Outcomes and Tumor Recurrence Patterns of a Pilot Study Assessing Efficacy of Belinostat (PXD-101) with Chemoradiation for Newly Diagnosed Glioblastoma.

Glioblastoma (GBM) is highly aggressive and has a poor prognosis. Belinostat is a histone deacetylase inhibitor with blood-brain barrier permeability, anti-GBM activity, and the potential to enhance chemoradiation. The purpose of this clinical trial was to assess the efficacy of combining belinostat with standard-of-care therapy. Thirteen patients were enrolled in each of control and belinostat cohorts. The belinostat cohort was given a belinostat regimen (500-750 mg/m2 1×/day × 5 days) every three weeks (weeks 0, 3, and 6 of RT). All patients received temozolomide and radiation therapy (RT). RT margins of 5-10 mm were added to generate clinical tumor volumes and 3 mm added to create planning target volumes. Median overall survival (OS) was 15.8 months for the control cohort and 18.5 months for the belinostat cohort (p = 0.53). The recurrence volumes (rGTVs) for the control cohort occurred in areas that received higher radiation doses than that in the belinostat cohort. For those belinostat patients who experienced out-of-field recurrence, tumors were detectable by spectroscopic MRI before RT. Recurrence analysis suggests better in-field control with belinostat. This study highlights the potential of belinostat as a synergistic therapeutic agent for GBM. It may be particularly beneficial to combine this radio-sensitizing effect with spectroscopic MRI-guided RT.

A convolutional neural network to filter artifacts in spectroscopic MRI.

PURPOSE: Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information. METHODS: A deep learning model was developed that was capable of identifying and filtering out poor quality spectra. The core of the model used a tiled convolutional neural network that analyzed frequency-domain spectra to detect artifacts. RESULTS: When compared with a panel of MRS experts, our convolutional neural network achieved high sensitivity and specificity with an area under the curve of 0.95. A visualization scheme was implemented to better understand how the convolutional neural network made its judgement on single-voxel or multivoxel MRSI, and the convolutional neural network was embedded into a pipeline capable of producing whole-brain spectroscopic MRI volumes in real time. CONCLUSION: The fully automated method for assessment of spectral quality provides a valuable tool to support clinical MRSI or spectroscopic MRI studies for use in fields such as adaptive radiation therapy planning.