Paul Rees

TL;DR: The steps required to create high-quality image-based (i.e., morphological) profiles from a collection of microscopy images are introduced and techniques that have proven useful in each stage of the data analysis process are recommended on the basis of the experience of 20 laboratories worldwide that are refining their image- based cell-profiling methodologies.

TL;DR: This work demonstrates label-free prediction of DNA content and quantification of the mitotic cell cycle phases by applying supervised machine learning to morphological features extracted from brightfield and the typically ignored darkfield images of cells from an imaging flow cytometer.

TL;DR: It is shown that deep convolutional neural networks combined with nonlinear dimension reduction enable reconstructing biological processes based on raw image data and are fast enough for on-the-fly analysis in an imaging flow cytometer.

TL;DR: The results show that cellular targeting of nanoparticles is inherently imprecise due to the randomness of nature at the molecular scale, and the statistical framework offers a way to predict nanoparticle dosage for therapy and for the study of nanotoxins.

TL;DR: Imaging flow cytometry is seeing a paradigm shift from low- to high-information-content analysis, driven partly by deep learning algorithms, and a wealth of applications with potential translation into clinical practice are predicted.