A cell-level quality control workflow for high-throughput image analysis.
Minhua QiuBin ZhouFrederick LoSteven CookJason ChybaDoug QuackenbushJason MatzenZhizhong LiPuiying Annie MakKaisheng ChenYingyao ZhouPublished in: BMC bioinformatics (2020)
Our cell-level QC workflow enables identification of artificial cells created not only by staining or imaging artifacts but also by the limitations of image segmentation algorithms. The single readout ARcell that summaries the ratio of artifacts contained in each image can be used to reliably rank images by quality and more accurately determine QC cutoff thresholds. Machine learning-based cellular phenotype clustering and sampling reduces the amount of manual work required for training example collection. Our QC workflow automatically handles assay-specific phenotypic variations and generalizes to different HT image assays.
Keyphrases
- deep learning
- high throughput
- single cell
- machine learning
- quality control
- convolutional neural network
- artificial intelligence
- rna seq
- electronic health record
- cell therapy
- induced apoptosis
- high resolution
- cell cycle arrest
- cell death
- big data
- mass spectrometry
- stem cells
- oxidative stress
- optical coherence tomography
- cell proliferation
- image quality