PVBM: A Python Vasculature Biomarker Toolbox Based on Retinal Blood Vessel Segmentation

Introduction: Blood vessels can be non-invasively visualized from a digital fundus image (DFI). Several studies have shown an association between cardiovascular risk and vascular features obtained DFI. Recent advances in computer vision segmentation enable automatising DFI blood vessel segmentation. There is need for resource that automatically compute vasculature biomarkers (VBM) these segmented Methods: In this paper, we introduce Python Vasculature BioMarker toolbox, denoted PVBM. A total of 11 VBMs were implemented. particular, new algorithmic methods to estimate tortuosity branching angles. Using PVBM, as proof usability, analyze geometric differences glaucomatous patients healthy controls. Results: We built fully automated biomarker toolbox based on segmentations provided usability characterize the changes glaucoma. For arterioles venules, all significant lower glaucoma compared controls except tortuosity, venular singularity length Conclusion: computation retinal The PVBM made open source under GNU GPL 3 license available physiozoo.com (following publication).