CP-CHARM: segmentation-free image classification made accessible

Abstract

BackgroundAutomated classification using machine learning often relies on features derived from segmenting individual objects, which can be difficult to automate. WND-CHARM is a previously developed classification algorithm in which features are computed on the whole image, thereby avoiding the need for segmentation. The algorithm obtained encouraging results but requires considerable computational expertise to execute. Furthermore, some benchmark sets have been shown to be subject to confounding artifacts that overestimate classification accuracy.ResultsWe developed CP-CHARM, a user-friendly image-based classification algorithm inspired by WND-CHARM in (i) its ability to capture a wide variety of morphological aspects of the image, and (ii) the absence of requirement for segmentation. In order to make such an image-based classification method easily accessible to the biological research community, CP-CHARM relies on the widely-used open-source image analysis software CellProfiler for feature extraction. To validate our method, we reproduced WND-CHARM’s results and ensured that CP-CHARM obtained comparable performance. We then successfully applied our approach on cell-based assay data and on tissue images. We designed these new training and test sets to reduce the effect of batch-related artifacts.ConclusionsThe proposed method preserves the strengths of WND-CHARM - it extracts a wide variety of morphological features directly on whole images thereby avoiding the need for cell segmentation, but additionally, it makes the methods easily accessible for researchers without computational expertise by implementing them as a CellProfiler pipeline. It has been demonstrated to perform well on a wide range of bioimage classification problems, including on new datasets that have been carefully selected and annotated to minimize batch effects. This provides for the first time a realistic and reliable assessment of the whole image classification strategy.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-0895-y) contains supplementary material, which is available to authorized users.

Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyes

“…It should be noted, however, that it may still be possible to obtain rich and useful data without the accurate segmentation of individual cells. A segmentation-free approach has been demonstrated to work for some image classification applications 36–38 , but whether this suffices for intensive morphological profiling applications remains untested.…”

Fluopack screening platform for unbiased cellular phenotype profiling

“…Images were analyzed using CellProfiler v2.2.2 on a Linux high performance compute cluster using the Jenkins-LSCI framework as previously described 13 . For segmentation-free image analysis, image features were computed on the whole image using the CellProfiler CHARM modules 14 . As of this writing, the CHARM modules are not included in the official release of CellProfiler, but the modules and the image feature extraction pipeline ([TrainTestMode]CHARM-like) can be obtained from the CPCharm git repository 15 .…”

Domain-invariant features for mechanism of action prediction in a multi-cell-line drug screen

“…Alternatively, one might analyse the image field directly in a per-image analysis, such as in [25], [35], or [10]. Such approaches are referred to as segmentationfree, as they obviate the segmentation phase of the conventional pipeline.…”

“…These features, hereafter referred to as handcrafted features, thus retain a degree of biological interpretability. In contrast, in [25] and [35] a large number of handcrafted features are extracted over each image as a whole.…”