Abstract
The recent advancements in automated microscopy and information systems allow the acquisition and storage of massive datasets of microscopy images. Here we describe CHLOE, a software tool for automatic extraction of novelty in microscopy image datasets. The tool is based on a comprehensive set of numerical image content descriptors reflecting image morphology, and can be used in combination with ROI detection and segmentation tools such as ITK. The rich feature set allows automatic detection of repetitive outlier images that are visually different from the common images in the dataset. The code and software are publicly available for free download at http://vfacstaff.ltu.edu/lshamir/downloads/chloe .
Highlights
The recent advancements in automated microscopy and information systems allow the acquisition and storage of massive datasets of microscopy images
One of the challenges of experimentalists who work with large datasets of microscopy images is outlier detection - detecting repetitive phenotypes that are visually different from the common phenotypes
If a certain gene, for instance, is expressed in just 1% of the cells, the experimentalist who analyses the microscopy images manually might not notice that and will not be able to use that information to comprehensively study the functionality of the gene
Summary
CHLOE: A Software Tool for Automatic Novelty Detection in Microscopy Image Datasets. The rich feature set allows automatic detection of repetitive outlier images that are visually different from the common images in the dataset. Applications of the software tool include high-content screening, but the versatile nature of the method makes it effective for detecting outlier images in many other types of experiments. These descriptors are extracted not just from the raw image, and from image transforms and multi-order image transforms as thoroughly discussed in [23, 24] This large feature set provides a comprehensive analysis, and can be applied to various experiments that involve different types of microscopy, magnifications, and organisms [25]. Once distances between all possible pairs of samples in the dataset are computed, the distances for each sample
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
