CP-CHARM: segmentation-free image classification made accessible

Abstract

Background: Automated 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.

Results: We 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.

Conclusions: The 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.

Fig. 1

Comparison between WND-CHARM [10] and the CP-CHARM algorithm presented in this paper. The overall construction of the algorithm is retained, but individual operations have been modified

Fig. 2

Example of images from each of the tested BBBC datasets. BBBC013: (a) positive, (b) negative; BBBC014: (c) positive, (d) negative; BBBC015: (e) positive, (f) negative; BBBC016: (g) positive, (h) negative

Fig. 3

Examples of elements of the four cell compartments classified in the HPA tissue dataset. (a) Cytoplasm, (b) nuclei, (c) connective tissue, and (d) background