Characteristics and Value of Machine Learning for Imaging in High Content Screening

AbstractSupervised machine learning is a powerful and widely used method to analyze high-content screening data. Despite its accuracy, efficiency, and versatility, supervised machine learning has drawbacks, most notably its dependence on a priori knowledge of expected phenotypes and time-consuming classifier training. We provide a solution to these limitations with CellCognition Explorer, a generic novelty detection and deep learning framework. Application to several large-scale screening data sets on nuclear and mitotic cell morphologies demonstrates that CellCognition Explorer enables discovery of rare phenotypes without user training, which has broad implications for improved assay development in high-content screening.

Download Full-text

A deep learning and novelty detection framework for rapid phenotyping in high-content screening

Molecular Biology of the Cell ◽

10.1091/mbc.e17-05-0333 ◽

2017 ◽

Vol 28 (23) ◽

pp. 3428-3436 ◽

Cited By ~ 34

Author(s):

Christoph Sommer ◽

Rudolf Hoefler ◽

Matthias Samwer ◽

Daniel W. Gerlich

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Large Scale ◽

Novelty Detection ◽

A Priori ◽

Mitotic Cell ◽

Supervised Machine Learning ◽

High Content Screening ◽

Data Sets ◽

User Training

Supervised machine learning is a powerful and widely used method for analyzing high-content screening data. Despite its accuracy, efficiency, and versatility, supervised machine learning has drawbacks, most notably its dependence on a priori knowledge of expected phenotypes and time-consuming classifier training. We provide a solution to these limitations with CellCognition Explorer, a generic novelty detection and deep learning framework. Application to several large-scale screening data sets on nuclear and mitotic cell morphologies demonstrates that CellCognition Explorer enables discovery of rare phenotypes without user training, which has broad implications for improved assay development in high-content screening.

Download Full-text

Automated Image Analysis for High-Content Screening and Analysis

CrossRef Listing of Deleted DOIs ◽

10.1177/1087057110370894 ◽

2010 ◽

Vol 15 (7) ◽

pp. 726-734 ◽

Cited By ~ 81

Author(s):

Aabid Shariff ◽

Joshua Kangas ◽

Luis Pedro Coelho ◽

Shannon Quinn ◽

Robert F. Murphy

Keyword(s):

Machine Learning ◽

Image Processing ◽

Image Analysis ◽

Cell Biology ◽

Image Data ◽

Automated Analysis ◽

Image Features ◽

Automated Image Analysis ◽

High Content Screening ◽

Spatial Transformation

The field of high-content screening and analysis consists of a set of methodologies for automated discovery in cell biology and drug development using large amounts of image data. In most cases, imaging is carried out by automated microscopes, often assisted by automated liquid handling and cell culture. Image processing, computer vision, and machine learning are used to automatically process high-dimensional image data into meaningful cell biological results. The key is creating automated analysis pipelines typically consisting of 4 basic steps: (1) image processing (normalization, segmentation, tracing, tracking), (2) spatial transformation to bring images to a common reference frame (registration), (3) computation of image features, and (4) machine learning for modeling and interpretation of data. An overview of these image analysis tools is presented here, along with brief descriptions of a few applications.

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text