Growing interest in perivascular spaces (PVS) quantification has highlighted the need for accurate and robust methods, particularly in magnetic resonance imaging (MRI). The Frangi filter is widely used to enhance tubular structures, including PVS, however its performance is highly dependent on scale selection. In the context of computer vision, "scale" refers to the size of the structures or features being detected by a filter or detector. In multiscale filtering, multiple scales are used to capture structures of varying sizes, and an optimal scale corresponds to the size at which a structure of interest is best enhanced or detected. Despite advancements in multiscale filtering techniques, determining an optimal scale for PVS quantification remains an open challenge. We introduce SCALR, a machine learning-based approach for scale selection in Frangi filtering to improve PVS quantification. A linear regression model, trained on synthetic and real MRI data, is used to infer an optimal scale based on a range of noise levels and voxel sizes across various imaging conditions. The findings indicate that SCALR enhances PVS detection, particularly in low signal-to-noise ratio MRI. By automating scale selection, SCALR increases the reliability of quantification and provides a scalable solution for integrating Frangi-based PVS analysis into clinical and research workflows.