Annotated image data is valuable for assessing the performance of an image processing pipeline and as training data for machine learning methods such as deep learning. When assessing the performance of a CellProfiler pipeline, for example a pipeline that segments nuclei, the annotated image data are used as the ground truth. The performance of the pipeline can be quantified by comparing the segmentation output to the ground truth and calculating a comparison metric, such as the Jaccard Index or F1 Score. Annotated images are also essential for deep learning applications as training data, for example see the 2018 Data Science Bowl; an in-depth discussion on how the Data Science Bowl images were annotated can be found on the Kaggle forum. Continue reading
For those of you who’ve been with us for a long time though, the obvious next question after how to use the new test mode is will my old CellProfiler pipelines work in the new version? We feel the same way – the pipelines you’ve accumulated over the years are precious resources! The good and bad news is that the answer is Yes, mostly. In order to facilitate the speedup and continue the process of streamlining the code, a few things had to go; we also removed some things we felt were causing “option fatigue” for the sake of user friendliness going forward.
# Sharing Image Data
At the Imaging Platform we frequently need to send and receive images between collaborators or forum users. Working with images can become challenging simply due to their file size. Memory and disk limitations are often irritants when analyzing images, but in some cases, such as multi-dimensional images and whole-slide scans, images’ file sizes can be large enough that even accessing images becomes a major roadblock, especially when the size starts to rival the size of desktop or laptop hard drives. Continue reading
This post was written by a guest author, Kun-Hsing Yu, who can be reached at Kun-Hsing_Yu@hms.harvard.edu.
Lung cancer causes more than 1.4 million deaths per year. To diagnose lung cancer, pathologists prepare microscopic slides from surgical or biopsy samples, stain them with appropriate chemicals, and observe the visual patterns of cell morphology under the microscope. This manual (and often laborious) approach is the gold standard for lung cancer diagnosis and distinguished lung cancer subtypes. Continue reading
Not every image you capture on your microscope is suited for quantification, no matter how nice they may look. Even though you might not notice any problems by eye, the tips outlined here for acquiring and storing images can improve the quality of data derived from digital image analysis. These tips are a bit CellProfiler-centric but generally applicable to any quantification you might do.
Now that CellProfiler can handle 3D images, how do you view the results? When processing 2D images, the IdentifyPrimaryObjects module will produce a figure that displays the original image next to the segmented image to make validation fast and convenient, a side-by-side comparison. However, the extra dimension in 3D complicates this approach, because the 3D image must be transformed in some manner in order to appear on a flat surface (e.g. the monitor or phone you’re using to read this blog post!). This blog post contains advice on how to look at 3D images and the 3D segmentation image produced by CellProfiler and introduces orthoviews in FIJI. If you would like to explore the example used in this post please check out the demo posted on the CellProfiler forum. Continue reading
CellProfiler is capable of accurate and reliable segmentation of cells by utilizing a broad collection of classical image processing methods. Peruse the documentation on the IdentifyPrimaryObjects module, for example, to get a sense of these, e.g., thresholding, declumping, and watershed. However, despite the many problems CellProfiler can readily solve, certain types of images are particularly challenging. For instance, when the biologically relevant objects are defined more by texture and context than raw intensity many classical image processing techiques can be foiled; DIC images of cells are a common biological example.