SEGMENT3D: A Web-based Application for Collaborative Segmentation of 3D images used in the Shoot Apical Meristem

摘要

The quantitative analysis of 3D confocal microscopy images of the shootapical meristem helps understanding the growth process of some plants. Cellsegmentation in these images is crucial for computational plant analysis andmany automated methods have been proposed. However, variations in signalintensity across the image mitigate the effectiveness of those approaches withno easy way for user correction. We propose a web-based collaborative 3D imagesegmentation application, SEGMENT3D, to leverage automatic segmentationresults. The image is divided into 3D tiles that can be either segmentedinteractively from scratch or corrected from a pre-existing segmentation.Individual segmentation results per tile are then automatically merged viaconsensus analysis and then stitched to complete the segmentation for theentire image stack. SEGMENT3D is a comprehensive application that can beapplied to other 3D imaging modalities and general objects. It also provides aneasy way to create supervised data to advance segmentation using machinelearning models.