Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification

Abstract

Biologists increasingly use co-culture systems in which two or more cell types are grown in cell culture together in order to better model cells’ native microenvironments. Co-cultures are often required for cell survival or proliferation, or to maintain physiological functioning in vitro. Having two cell types co-exist in culture, however, poses several challenges, including difficulties distinguishing the two populations during analysis using automated image analysis algorithms. We previously analyzed co-cultured primary human hepatocytes and mouse fibroblasts in a high-throughput image-based chemical screen, using a combination of segmentation, measurement, and subsequent machine learning to score each cell as hepatocyte or fibroblast. While this approach was successful in counting hepatocytes for primary screening, segmentation of the fibroblast nuclei was less accurate. Here, we present an improved approach that more accurately identifies both cell types. Pixel-based machine learning (using the software ilastik) is used to seed segmentation of each cell type individually (using the software CellProfiler). This streamlined and accurate workflow can be carried out using freely available and open source software.

High-content image informatics of the structural nuclear protein NuMA parses trajectories for stem/progenitor cell lineages and oncogenic transformation

“…The morphotextural profiling approach is distinct from classic machine learning methods that distinguish between image features appearing clearly different to the human eye, such as prominent heterochromatin domains in mouse vs. human nuclei [31] or grossly different nuclear morphologies (e.g., hepatocytes vs. fibroblasts; [32]). In contrast, high-content image profiling yields an unbiased assessment that does not rely on any preconception or biased supervision.…”

CytoCensus: mapping cell identity and division in tissues and organs using machine learning

“…However, these three approaches require advanced knowledge of image processing, programming and/or extensive manual annotation. Other software such as Advanced Cell Classifier are targeted at analysis of 2D data, whilst programs such as RACE, SuRVoS, 3D-RSD and MINS are generally tailored to specific applications (Luengo et al, 2017;Stegmaier et al, 2016;Lou et al, 2014;Cabernard & Doe, 2013;Homem et al, 2013;Arganda-Carreras et al, 2017;Logan et al, 2016;Gertych et al, 2015). Recently, efforts to make deep learning approaches easily accessible have made great strides (Falk e t a l .…”

Shaping the Cell and the Future: Recent Advancements in Biophysical Aspects Relevant to Regenerative Medicine

“…Machine learning uses pattern recognition and computational tools to find functional relationships from the training data with minimal intervention or bias [55]. For example, Logan et al used cell segmentation combined with pixel-based machine learning to identify hepatocytes vs. fibroblasts in co-culture conditions [57]. While use of cell segmentation accurately identified hepatocytes, use of cell segmentation for identification of fibroblasts was not as accurate [58].…”

“…While use of cell segmentation accurately identified hepatocytes, use of cell segmentation for identification of fibroblasts was not as accurate [58]. Tuning the software to both cell types using defined regions of interest (ROIs) and pixel-based machine learning enhanced the system and resulted in higher accuracy in identification of both tested cell types [57]. Pixel-based machine learning using was accomplished with the usage of ilastik software [55] succeeded by model-based segmentation of the predefined ROIs using the software CellProfiler [57].…”

“…Tuning the software to both cell types using defined regions of interest (ROIs) and pixel-based machine learning enhanced the system and resulted in higher accuracy in identification of both tested cell types [57]. Pixel-based machine learning using was accomplished with the usage of ilastik software [55] succeeded by model-based segmentation of the predefined ROIs using the software CellProfiler [57]. Whereas machine learning or other computational strategies are highly promising approaches, it is not within the scope nor the aim of this review to recommend a particular strategy/system, as almost no comparative data is available.…”