Image Segmentation
Image Segmentation - Related Videos
10:39
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
0 Views •
Cited by 11 •
2022
The intravital imaging method described here utilizes collagen second harmonic generation and endogenous fluorescence from the metabolic co-factor NAD(P)H to non-invasively segment an unlabeled tumor microenvironment into tumor, stromal, and vascular compartments for in-depth analysis of 4D intravital images.
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
0 Views •
Cited by 4 •
2022
An object segmentation protocol for orbital computed tomography (CT) images is introduced. The methods of labeling the ground truth of orbital structures by using super-resolution, extracting the volume of interest from CT images, and modeling multi-label segmentation using 2D sequential U-Net for orbital CT images are explained for supervised learning.
04:25
Manual Segmentation of the Human Choroid Plexus Using Brain MRI
0 Views •
Cited by 13 •
2023
Despite the crucial role of the choroid plexus in the brain, neuroimaging studies of this structure are scarce due to the lack of reliable automated segmentation tools. The present protocol aims to ensure gold-standard manual segmentation of the choroid plexus that can inform future neuroimaging studies.
13:09
Segmentation and Measurement of Fat Volumes in Murine Obesity Models Using X-ray Computed Tomography
0 Views •
Cited by 23 •
2012
Fat content analysis is routinely conducted in studies utilizing murine obesity models. Emerging methods in small animal CT imaging and analysis are providing for longitudinal detail rich fat content analysis. Here we detail step by step procedures for performing small animal CT imaging, analysis, and visualization.
10:41
Generation of Dispersed Presomitic Mesoderm Cell Cultures for Imaging of the Zebrafish Segmentation Clock in Single Cells
0 Views •
Cited by 8 •
2014
Somitogenesis is a rhythmic developmental process that spatially patterns the body axis of vertebrate embryos. Previously, we developed transgenic zebrafish lines that use fluorescent reporters to observe the cyclic genes that drive this process. Here, we culture dispersed cells from these lines and image their oscillations over time in vitro.
FAQs
These approaches provide different ways to assign pixels or groups of pixels to categories. Thresholding, edge detection, and machine-learning-based classification can each produce labeled regions or binary masks, but their outputs may differ in how clearly they separate biological structures from surrounding image content. Comparing results helps identify regions suitable for subsequent biological measurement.
A binary mask records which image locations belong to a selected region, while labeled regions distinguish categories or separate structures. This distinction matters when analysis requires measurements of size, shape, number, or spatial organization. The output converts visual structures into representations that can be examined quantitatively, rather than leaving interpretation at the level of an unprocessed image.
Segmentation accuracy directly affects downstream biological conclusions. If regions do not correspond well to intended cells, nuclei, tissues, organelles, or lesions, measurements of their size, shape, number, or spatial organization may become less reliable. Accurate results strengthen quantitative comparisons across experiments and make it easier to track biological changes represented in image data.
By isolating structures from their surroundings, the technique makes biological organization measurable in images. In cell biology and developmental biology, it can support analysis of cells, nuclei, organelles, and changing spatial arrangements. In pathology and biomedical engineering, it can be applied to tissue or lesion images, connecting image-derived measurements with broader biological or biomedical questions.
A practical workflow begins with an image containing structures of interest, followed by selection of a segmentation approach such as thresholding, edge detection, or machine-learning-based classification. The chosen method produces labeled regions or a binary mask. Researchers can then measure size, shape, number, or spatial organization and compare those results across images or experiments.
Image Segmentation is especially useful when researchers need consistent quantitative information from images collected across experiments. Representing cells, nuclei, tissues, organelles, or lesions as regions allows their properties and spatial organization to be compared more systematically. Repeated measurements can also help track changes across experiments, supporting investigations in cell biology, development, pathology, and biomedical engineering.