Workflow and Metrics for Image Quality Control in Large-Scale High-Content Screens

@article{Bray2012WorkflowAM,
  title={Workflow and Metrics for Image Quality Control in Large-Scale High-Content Screens},
  author={Mark-Anthony Bray and Adam Fraser and Thomas P. Hasaka and Anne E Carpenter},
  journal={Journal of Biomolecular Screening},
  year={2012},
  volume={17},
  pages={266 - 274}
}
Automated microscopes have enabled the unprecedented collection of images at a rate that precludes visual inspection. Automated image analysis is required to identify interesting samples and extract quantitative information for high-content screening (HCS). However, researchers are impeded by the lack of metrics and software tools to identify image-based aberrations that pollute data, limiting experiment quality. The authors have developed and validated approaches to identify those image… 

Figures from this paper

Quality Control for High-Throughput Imaging Experiments Using Machine Learning in Cellprofiler.
TLDR
An automated quality control protocol implemented in validated open-source software, leveraging the suite of image-based measurements generated by CellProfiler and the machine-learning functionality of CellProfilers Analyst is described.
Image Quality Ranking Method for Microscopy
TLDR
A simple method and a software tool for sorting images within a dataset, according to their relative quality, and how this method can be applied to eliminate useless out-of-focus images in a High-Content-Screening experiment is proposed.
Advanced Assay Development Guidelines for Image-Based High Content Screening and Analysis
TLDR
This chapter builds on the material presented in the introductory HCS section and examines positive and negative controls, which are required to calculate a performance envelope for measuring the assay quality and phenotype feature space.
Pipeline for illumination correction of images for high-throughput microscopy
TLDR
The presence of systematic noise in images in high‐throughput microscopy experiments can significantly impact the accuracy of downstream results and precludes biological experiments that rely on accurate fluorescence intensity measurements.
Understanding the impact of image quality on segmentation accuracy
TLDR
This work builds on previous work by designing a method to detect suboptimal microscopy settings and to derive a computational model based on image quality descriptors to predict segmentation accuracy.
Assessing microscope image focus quality with deep learning
TLDR
A deep neural network model is presented capable of predicting an absolute measure of image focus on a single image in isolation, without any user-specified parameters, and also outputs a measure of prediction certainty, enabling interpretable predictions.
A New Unsupervised Approach for Segmenting and Counting Cells in High-Throughput Microscopy Image Sets
TLDR
This paper presents an unsupervised approach for automatic cell segmentation and counting, namely CSC, in high-throughput microscopy images and shows that CSC outperforms the current state-of-the-art techniques.
Focus Quality Assessment of High-Throughput Whole Slide Imaging in Digital Pathology
TLDR
A no-reference focus quality assessment metric is proposed specifically for digital pathology images that operate by using a sum of even-derivative filter bases to synthesize a human visual system-like kernel, which is modeled as the inverse of the lens’ point spread function.
A cell-level quality control workflow for high-throughput image analysis
TLDR
A novel cell-level QC workflow built on machine learning approaches for classifying artifacts from HT image data enables identification of artificial cells created not only by staining or imaging artifacts but also by the limitations of image segmentation algorithms.
Towards assessment of the image quality in the high-content screening
TLDR
The importance of the image quality control for the HCS is emphasized, with the following possible advantages: validation of the visual quality of the screening; detection of the potentially problem images; and more accurate setting of the processing parameters.
...
...

References

SHOWING 1-10 OF 14 REFERENCES
Autofocusing in computer microscopy: Selecting the optimal focus algorithm
TLDR
This article presents a comprehensive comparison study of 18 focus algorithms in which a total of 139,000 microscope images were analyzed and guidelines allow for the selection of the optimal focus algorithm for different microscopy applications.
Quantitative quality control in microarray image processing and data acquisition.
TLDR
The potential of quantitative quality control for microarray data and the possibility of filtering and normalizing micro array data using a quality metrics-dependent scheme are discussed.
Enhanced CellClassifier: a multi-class classification tool for microscopy images
TLDR
Enhanced CellClassifier is designed for the biologist who wants both, simple and flexible analysis of images without requiring programming skills, and should facilitate the implementation of automated high-content screening.
Simulating fluorescent microscope images of cell populations
TLDR
By creating a parametric model for cell shape, and simulating images of cell populations including errors and aberrations caused by the measurement system, validation of different image analysis methods is enabled and studies with large populations can be carried out by using simulated cell population images.
Image analysis benchmarking methods for high‐content screen design
TLDR
By applying simple benchmarking principles an a priori estimate of the image acquisition requirements for phenotypic analysis can be made before initiating an image‐based screen, which provides a mechanism to significantly reduce data acquisition and analysis burdens and to improve data quality and information content.
CellProfiler Analyst: data exploration and analysis software for complex image-based screens
TLDR
Here, CellProfiler Analyst, open-source software for the interactive exploration and analysis of multidimensional data, particularly data from high-throughput, image-based experiments, is described.
HIGH RESOLUTION SHADING CORRECTION
TLDR
A method of shading correction on single pixels is introduced as a new way to reduce some errors that currently plague scanning systems.
Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning
TLDR
A supervised machine learning approach that uses iterative feedback to readily score multiple subtle and complex morphological phenotypes in high-throughput, image-based screens is presented.
A comparison of different focus functions for use in autofocus algorithms.
TLDR
Among the best focus functions found in this study are the squared magnitude gradient, the squared Laplacian, and the normalized image standard deviation.
...
...