Yasmin M. KassimV. B.Surya PrasathRengarajan PelapurOlga V. GlinskiiRichard J. MaudeVladislav V. GlinskyVirginia H. HuxleyKannappan PalaniappanComputational Imaging and VisAnalysis (CIVA) LabVA Medical CenterDepartment of Medical Pharmacology and PhysiologyUniversity of Missouri-ColumbiaNuffield Department of Clinical MedicineMahidol UniversityHarvard School of Public Health2018-12-112019-03-142018-12-112019-03-142016-10-13Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Vol.2016-October, (2016), 2901-29041557170X2-s2.0-85009083425https://repository.li.mahidol.ac.th/handle/20.500.14594/43433© 2016 IEEE. Automatic segmentation of microvascular structures is a critical step in quantitatively characterizing vessel remodeling and other physiological changes in the dura mater or other tissues. We developed a supervised random forest (RF) classifier for segmenting thin vessel structures using multiscale features based on Hessian, oriented second derivatives, Laplacian of Gaussian and line features. The latter multiscale line detector feature helps in detecting and connecting faint vessel structures that would otherwise be missed. Experimental results on epifluorescence imagery show that the RF approach produces foreground vessel regions that are almost 20 and 25 percent better than Niblack and Otsu threshold-based segmentations respectively.Mahidol UniversityComputer ScienceEngineeringMedicineConference PaperSCOPUS10.1109/EMBC.2016.7591336