Segmentation of the Zebrafish Brain Vasculature from Light Sheet Fluorescence Microscopy Datasets

Abstract

Light sheet fluorescent microscopy allows imaging of zebrafish vascular development in great detail. However, interpretation of data often relies on visual assessment and approaches to validate image analysis steps are broadly lacking. Here, we compare different enhancement and segmentation approaches to extract the zebrafish cerebral vasculature, provide comprehensive validation, study segmentation robustness, examine sensitivity, apply the validated method to quantify embryonic cerebrovascular volume, and examine applicability to different transgenic reporter lines. The best performing segmentation method was used to train different deep learning networks for segmentation. We found that U-Net based architectures outperform SegNet. While there was a slight overestimation of vascular volume using the U-Net methodologies, variances were low, suggesting that sensitivity to biological changes would still be obtained. HighlightsO_LIGeneral filtering is less applicable than Sato enhancement to enhance zebrafish cerebral vessels. C_LIO_LIBiological data sets help to overcome the lack of segmentation gold-standards and phantom models. C_LIO_LISato enhancement followed by Otsu thresholding is highly accurate, robust, and sensitive. C_LIO_LIDirect generalization of the segmentation approach to transgenics, other than the one optimized for, should be treated with caution. C_LIO_LIDeep learning based segmentation is applicable to the zebrafish cerebral vasculature, with U-Net based architectures outperforming SegNet architectures. C_LI Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=147 SRC="FIGDIR/small/213843v1_ufig1.gif" ALT="Figure 1"> View larger version (88K): org.highwire.dtl.DTLVardef@6b45a3org.highwire.dtl.DTLVardef@a90c0borg.highwire.dtl.DTLVardef@55be1borg.highwire.dtl.DTLVardef@1340df9_HPS_FORMAT_FIGEXP M_FIG C_FIG