Image segmentation software tools | Single plane illumination microscopy analysis
A variety of algorithms are available for segmentation of nuclei, including: watershed, iterative voting methods, level set approach based on gradient flow and flexible contour model. However the implementation of these algorithms to segment Light Sheet Fluorescent Microscopy (LSFM) data is not straightforward, due to complex installation procedures, or difficulty in tuning the parameters for individual biological samples. Moreover, a good segmentation result relies not only on an efficient segmentation algorithm but also on a sequence of steps preparing the image so that the segmentation algorithm can perform efficiently. Therefore, putting all these steps together requires a systematic design of the pipeline and the interface.
Serves for effective segmentation of multidimensional datasets. MIB can recognize several number of imaging formats and offers a variety of image processing tools. It also simplifies utilization and quantification of acquired data. It permits users to segment large datasets, to realize 3D visualization, and to quantify images and models. Its parameters enable users to insert plugin s to customize the program for specific needs.
Provides a cleared 3D brain image processing and analysis methods for light-sheet fluorescence microscopy (LSFM). CUBIC is a standalone software getting its name from the CUBIC protocol wich is a chemical sample clearing protocol especially designed for brain tissues. It provides multiple functionalities: (i) The image file conversion and manipulation, (ii) the detection of sample edges, (iii) the brain alignent and (iv) the atlasing of the brain sample.
Segments neural cells by combining deep learning and a topology-preserving geometric deformable model. This algorithm separates cell bodies in light-sheet microscopy images of cleared post mortem human brain tissue. It only requires sparse annotation for training. It can be adapted to enhance clearing, staining and imaging protocols and can be extended to the full 3D image data.
Performs interactive segmentation and investigation of 3D+t microscopy datasets containing cell boundary information. CellECT allows users to add, delete, or modify segments. It offers an adaptive confidence metric assisting users in the recognition of areas of uncertain segmentation. This tool enables the detection of spurious boundaries and can suggest corrections. Moreover, it can be useful for assessing the quality of segmentations and the efficiency of the available metrics.
Assists in exploration of possible watershed segmentation. Interactive-H-Watershed is a plugin for the image analysis software ImageJ. It provides an interactive way to explore local minima (maxima) on the fly. This module is based on Watershed, a common tool to segment objects in an 2D and 3D images. The method permits to gradually flood the valleys starting from their lowest point.
Identifies and segments the glomeruli present within digitized images of human kidney biopsies. This method is a framework that can perform image classification. It is built on a deep learning architecture based on convolutional neural networks (CNN). This model can be utilized in the form of a software tool at the point-of-care to assist nephropathologists. It can also be adapted to other images obtained via different histological staining protocols.
An open access and user friendly 3D automatic quantitative analysis tool for single plane illumination microscopy (SPIM) data. OpenSegSPIM is designed to extract quantitative relevant information from SPIM image stacks, such as the number of nuclei/cells and provide quantitative measurement (volume, sphericity, distance, intensity) on light sheet microscopy (LSM) images. Typically, it is a useful quantitative analysis tool for different biological samples such as neurospheres, zebrafish embryos, drosophila embryos, skin sample, mouse embryos and other organotypic cell culture. The OpenSegSPIM pipeline consists of a succession of step each one being enabled once the previous step has been completed. To provide a simple interface OpenSegSPIM minimizes the number of parameters without loss of segmentation quality. Furthermore, parameter input is an interactive process. For example, image smoothing is done in a few steps and the user only needs to measure the diameter of the nuclei. To facilitate the difficult step of parameter tuning the intermediate results are visualized in real time and can be evaluated.