Taisaku Ogawa, Data curation, Investigation, Writing – original draft, 1 Koji Ochiai, Software, Validation, Writing – original draft, 2 Tomoharu Iwata, Methodology, 3 Tomokatsu Ikawa, Resources, 4 Taku Tsuzuki, Software, 5 , 6 Katsuyuki Shiroguchi, Conceptualization, Funding acquisition, Project administration, Supervision, Writing – review & editing, 1 ,* and Koichi Takahashi, Conceptualization, Funding acquisition, Project administration, Supervision, Writing – review & editing 2 ,*
"1 Laboratory for Prediction of Cell Systems Dynamics, RIKEN Center for Biosystems Dynamics Research (BDR), Suita, Osaka, Japan
2 Laboratory for Biologically Inspired Computing, RIKEN Center for Biosystems Dynamics Research (BDR), Suita, Osaka, Japan
3 Ueda Research Laboratory, NTT Communication Science Laboratories, Kyoto, Japan
4 Division of Immunology and Allergy, Research Institute for Biomedical Sciences, Tokyo University of Science, Noda, Chiba, Japan
5 Laboratory for Computational Molecular Design, RIKEN Center for Biosystems Dynamics Research (BDR), Suita, Osaka, Japan
6 Epistra Inc., Tokyo, Japan
Fuzhou University, CHINA,
Competing Interests: Epistra, Inc. provided support in the form of salaries for authors Taku Tsuzuki and Koichi Takahashi, but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. This commercial affiliation does not alter our adherence to PLOS ONE policies on sharing data and materials.
* E-mail: [email protected] (KS); [email protected] (KT)"
"Developments in high-throughput microscopy have made it possible to collect huge amounts of cell image data that are difficult to analyse manually. Machine learning (e.g., deep learning) is often employed to automate the extraction of information from these data, such as cell counting, cell type classification and image segmentation. However, the effects of different imaging methods on the accuracy of image processing have not been examined systematically. We studied the effects of different imaging methods on the performance of machine learning-based cell type classifiers. We observed lymphoid-primed multipotential progenitor (LMPP) and pro-B cells using three imaging methods: differential interference contrast (DIC), phase contrast (Ph) and bright-field (BF). We examined the classification performance of convolutional neural networks (CNNs) with each of them and their combinations. CNNs achieved an area under the receiver operating characteristic (ROC) curve (AUC) of ~0.9, which was significantly better than when the classifier used only cell size or cell contour shape as input. However, no significant differences were found between imaging methods and focal positions.
DOI: https://dx.doi.org/ 10.1371/journal.pone.0262397
Alx594-conjugated anti-CD19 antibody fluorescence images were observed with standard epifluorescence optics consisting of an LED (pE-300 white; CoolLED, UK) and a mirror unit (mCherry HQ; Nikon).
Product Associated Features
The pE-300white is a popular illuminator for everyday fluorescent screening and analysis with simple operatation and individual irradiance control of each LED channel.
Year of Publication
Country of Publication