LABKIT: Labeling and Segmentation Toolkit for Big Image Data

Abstract

We present LABKIT, a user-friendly Fiji plugin for the segmentation of microscopy image data. It offers easy to use manual and automated image segmentation routines that can be rapidly applied to single- and multi-channel images as well as to timelapse movies in 2D or 3D. LABKIT is specifically designed to work efficiently on big image data and enables users of consumer laptops to conveniently work with multiple-terabyte images. This efficiency is achieved by using ImgLib2 and BigDataViewer as well as a memory efficient and fast implementation of the random forest based pixel classification algorithm as the foundation of our software. Optionally we harness the power of graphics processing units (GPU) to gain additional runtime performance. LABKIT is easy to install on virtually all laptops and workstations. Additionally, LABKIT is compatible with high performance computing (HPC) clusters for distributed processing of big image data. The ability to use pixel classifiers trained in LABKIT via the ImageJ macro language enables our users to integrate this functionality as a processing step in automated image processing workflows. Finally, LABKIT comes with rich online resources such as tutorials and examples that will help users to familiarize themselves with available features and how to best use LABKIT in a number of practical real-world use-cases.

BioImage Model Zoo: A Community-Driven Resource for Accessible Deep Learning in BioImage Analysis

“…This approach provides more robust results for mitochondria segmentation in EM modalities when applied to new images since the model only sees the changes in the shape distribution, rather than the intensity distribution. For a new EM dataset, “shallow” pixel classification can be performed fast and interactively using established tools such as ilastik, LabKit 46 or the Trainable Weka toolkit 47 . The “enhancer” model can be applied using the ilastik neural network workflow or deepImageJ to significantly improve the segmentation results without further data annotation or training.…”

“…For mitochondria segmentation in images from a different EM modality or target tissue the user only needs to train a shallow model, which is fast and convenient due to established tools that provide interactive training functionality. Here, we demonstrate this approach with the trainable Weka 47 plugin, Labkit 46 and ilastik pixel classification for data from the MitoEM challenge 45 . The predictions can then be improved by applying the domain adaptation model, using either deepImageJ or the ilastik neural network workflow (any other software that supports running bioimage.io models would also work).…”

FtsZ at mid-cell is essential in Escherichia coli until the late stage of constriction

“…We segmented the images by hand with LabKit in FIJI [22]. We then analysed the segments in Python3 [18] with our own algorithm that automated the process.…”

Segmentation, tracking and cell cycle analysis of live-cell imaging data with Cell-ACDC

“…Although many software tools dedicated to the analysis of live-cell microscopy have been developed in the past (ImageJ/Fiji [19], MorphoLibJ [20], PhyloCell [21], Cell-Profiler [22], Cell Tracer [23], Wood et al [24,25], Cell Star [26], Cell Serpent [27], Tracker [28], YeastSpotter [29], YeastNet [30], DeepCell [31], Cellbow [32], LAB-KIT [33], largely focussed on classification tasks CellID [34] and Advanced Cell Classifier [35] and, specifically for ageing experiments using dedicated microfluidics, DISCO [36], DetecDiv [37] and BABY [38]), to the best of our knowledge, none of them spanned the entire image analysis pipeline from CNN-based segmentation to cell cycle analysis in growing colonies, and fluorescent signal quantification (Table 1).…”