Blog

Fernanda Garcia-Fossa & Anne Carpenter In a typical quantitative microscopy experiment, biologists choose fluorescent biomarkers and measure particular features (that is “metrics”) that they hypothesize will be perturbed in their samples. But in image-based profiling, you aim to let the cells tell...

Melissa Gillis In the final section of this blogpost series, I will discuss some of the benefits and drawbacks of this model and discuss some of the data I acquired from the images. This model was able to successfully segment the images that were not able to be accurately segmented by Pearl’s...

Melissa Gillis In the previous two sections of this blogpost I explained how I analyzed multiple methods to segment fluorescent images of collagen IV fibers, and generated accurate segmentation using an ilastik machine learning model. In this section I will explain how I constructed a CellProfiler...

Melissa Gillis In the first part of this blogpost I described some of the tools I tried to accurately segment collagen IV fibers including, CellProfiler, Cellpose, and Piximi. Unfortunately none of these methods were successful in accurately segmenting the fibers so I decided to develop a machine...

Melissa Gillis Segmenting fibers using traditional cell segmentation software can be challenging. Because most biological cell segmentation tools were designed for cells, most programs have difficulty identifying and distinguishing longer and thinner objects such as fibers. Also, unlike cells...

Pearl V. Ryder The Robust Background algorithm is a powerful algorithm for automatically setting thresholds to segment objects of interest when your image contains mostly background. However, since it contains the largest number of tunable parameters of any thresholding algorithm in CellProfiler, it...

David R. Stirling We’ve all done this before – CellProfiler Analyst needs a database file, but your CellProfiler pipeline that took days to run was set up to export spreadsheets. To make matters worse, you also need a .properties file explaining what to do with that database. Fortunately, you don’t...

Beth Cimini Defining the input to CellProfiler can be the hardest part of getting your pipeline set up and your analysis underway. Incoming images are configured in the first 4 modules of CellProfiler – Images, Metadata, NamesAndTypes, and Groups – which offer lots of flexibility. But it’s sometimes...

Beth Cimini It can be confusing when you’re trying to set up your first pipeline to figure out which modules to use to generate your objects! A helpful way to understand the difference between Identifying Primary, Secondary, and Tertiary objects: Primary objects are segmented independently from any...