![]() ![]() MOrgAna is a Python package that implements an easy-to-use ML pipeline to segment hundreds of organoids, each fully contained in a single 2D image, within minutes ( Fig. 1A,B Fig. S1). In this work, we present MOrgAna, a Machine-learning-based Organoid Analysis software. Even though data-driven approaches to characterizing organoid phenotypes exist ( Serra et al., 2019), so far little effort has been made to develop a user-friendly intuitive pipeline that can be used by a large community with limited programming experience. Thus, standard high-throughput segmentation pipelines need to be adapted to detect individual large objects distributed among several images. However, organoids display highly complex phenotypes, which are difficult to describe with traditional morphological features such as radius length, area, perimeter or average fluorescence intensity. #CELLPROFILER ANALYSING A SET OF IMAGES SOFTWARE#In the context of HCS of 2D adherent cell culture, such software have been capable of, for example, identifying thousands of cells within wide fields of view and extracting biologically relevant features ( McQuin et al., 2018). FIJI, CellProfiler and ilastik) ( Berg et al., 2019 Schindelin et al., 2012 Carpenter et al., 2006). MetaMorph, Imaris, Harmony and ZEN) or distributed open-source (e.g. Nowadays, machine learning (ML)-based algorithms have become an essential tool across biomedical disciplines to perform a quantitative, unbiased analysis of microscopy images, and are either provided as part of proprietary software (e.g. ![]() Therefore, in order to extract quantitative information, much effort is required to adapt, if not rewrite, conventional algorithms to work around the signal to noise in images generated by the diverse devices used. However, there is a tradeoff between microscope availability, high-throughput capacity and image quality, often forcing researchers to use low-end stereoscopic microscopes that can suffice for qualitative assessment. Generally, high-content screening (HCS) devices represent an ideal platform to image a large number of samples under a variety of conditions ( Durens et al., 2020 Brandenberg et al., 2020 Vrij et al., 2016). Another hindrance is the limited access to an imaging system that can accommodate the variety of plates and devices used in organoid culture ( Rossi et al., 2018). When quantitatively interpreted, such data have been crucial in dissecting the mechanisms responsible for organoid development ( Phipson et al., 2019 Lukonin et al., 2020 Hof et al., 2021). There is therefore now a major bottleneck in the ability to inspect this huge number of images and quantify morphological and fluorescence parameters in space and time with high accuracy and in an unbiased manner. In recent years, due to novel engineering solutions and the need of buffering the large variability of organoid generation ( Gritti et al., 2021), the number of experimental conditions have grown combinatorially and it is now possible to generate increasingly large datasets. We showcase the versatility of MOrgAna on several in vitro systems, each imaged with a different microscope, thus demonstrating the wide applicability of the software to diverse organoid types and biomedical studies. Although the MOrgAna interface is developed for users with little to no programming experience, its modular structure makes it a customizable package for advanced users. Here, we present MOrgAna, a Python-based software that implements machine learning to segment images, quantify and visualize morphological and fluorescence information of organoids across hundreds of images, each with one object, within minutes. Hence, there is a pressing demand for a coding-free, intuitive and scalable solution that analyses such image data in an automated yet rapid manner. The large volumes of images, resulting from hundreds of organoids cultured at once, are becoming increasingly difficult to inspect and interpret. Organoids are large structures with high phenotypic complexity and are imaged on a wide range of platforms, from simple benchtop stereoscopes to high-content confocal-based imaging systems. Recent years have seen a dramatic increase in the application of organoids to developmental biology, biomedical and translational studies. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |