Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning

By Thouis Raymond Jones, Anne E Carpenter, M. R. Lamprecht, Jason Moffat, S. Silver, J. Grenier, Adam B. Castoreno, U. Eggert, D. Root, Polina Golland and 1 more. Proceedings of the National Academy of Sciences of the United States of America, 2009

396 citations recorded by the source corpus.

Subfields: Biophysics, Media Technology, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/c1317f812bfaec25958ec7b5b583eb035fe6d5a1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Media Technology

In Molecular Biology

Citations in the corpus

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review (2016, background): “phenotypes, and it has well served the community for years [322], [323].”
Applications in image-based profiling of perturbations. (2016, methodology): “This requires flexible software tools for extracting measurements from images and robust computational models for subsequent data analytics [33], whether a single morphological feature is the basis of the screen, or whether machine learning is used to combine multiple morphological features in order”
Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software (2011, methodology): “The diverse measurements generated by CellProfiler provide raw material for machinelearning algorithms that can identify challenging phenotypes (Jones et al., 2009; Misselwitz et al., 2010; Ramo et al., 2009).”
Data-analysis strategies for image-based cell profiling (2017, methodology): “Hierarchical clustering is computed by using a similarity matrix that contains the similarity values for all pairs of samples (described in ‘Measuring profile similarity’).”
Machine learning in cell biology – teaching computers to recognize phenotypes (2013, positive): “Data points are selected by the learning algorithm in order to maximize the learning progress, and hence, minimize the overall annotation effort (Jones et al., 2009).”
Computer vision for high content screening (2016, background): “Jones et al. (2009) implemented this learning scheme to classify 15 cellular phenotypes in RNAi screens of human and Drosophila melanogaster cells.”
Comparison of Different Classifiers with Active Learning to Support Quality Control in Nucleus Segmentation in Pathology Images (2018, methodology): “A variety of classification methods have been employed, such as linear classifiers (logistic regression 15 and Support Vector Machine 14 ), ensemble methods (Probabilistic Boosting Tree 16 , Random Forest 18 , and Gentle Boosting 17 ) and deep learning method (Bayesian CNN 19 ).”
Cellular heterogeneity: when do differences make a difference? (2010, background): “…in flow cytometry) to more complex, machinelearning algorithms that iteratively train computers to identify subpopulations based on examples (such as recently developed for high-throughput microscopy screening; Boland and Murphy, 2001; Jones et al., 2009; Ramo et al., 2009; Yin et al., 2008).”
A human-machine adversarial scoring framework for urban perception assessment using street-view images (2019, methodology): “Inspired by the iterative feedback module designed for scoring cell phenotypes (Jones et al .”
Biological Imaging Software Tools (2012, background): “For example, in CellProfiler Analyst 50 , the biologist is presented with machine classifications of new cells based on their previous input and is given the opportunity to correct errors.”
High-Content Screening for Quantitative Cell Biology. (2016, background): “…ﬁ rst manually labels examples of ROIs (for example individual cells) or whole images exhibiting a phenotype of interest and groups them together in distinct classes; additional occurrences of the same phenotype within the full data set are subsequently identi ﬁ ed by the trained classi ﬁ er [42].”