Label-free classification of cells based on supervised machine learning of subcellular structures

It is demonstrated that cells can be classified by pattern recognition of the subcellular structure of non-stained live cells, and the pattern recognition was performed by machine learning. Human white blood cells and five types of cancer cell lines were imaged by quantitative phase microscopy, whic...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2019-01, Vol.14 (1), p.e0211347-e0211347
Main Authors: Ozaki, Yusuke, Yamada, Hidenao, Kikuchi, Hirotoshi, Hirotsu, Amane, Murakami, Tomohiro, Matsumoto, Tomohiro, Kawabata, Toshiki, Hiramatsu, Yoshihiro, Kamiya, Kinji, Yamauchi, Toyohiko, Goto, Kentaro, Ueda, Yukio, Okazaki, Shigetoshi, Kitagawa, Masatoshi, Takeuchi, Hiroya, Konno, Hiroyuki
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Biology and Life Sciences
Biotechnology
Blood cells
Breast cancer
Cancer
Cancer cells
Cell Line
Cell lines
Cellular biology
Classification
Computer and Information Sciences
Cytotoxicity
Feature extraction
Flow cytometry
HCT116 Cells
Hep G2 Cells
Humans
Image classification
Laboratory animals
Learning algorithms
Leukocytes
Leukocytes - ultrastructure
Machine learning
Medical imaging
Medical imaging equipment
Medicine
Medicine and Health Sciences
Microscopy
Morphology
Optical thickness
Optics
Pathology
Pattern recognition
Pattern Recognition, Automated
Phase contrast microscopes
Photonics
Research and Analysis Methods
Single-Cell Analysis - instrumentation
Single-Cell Analysis - methods
Supervised Machine Learning
Surgery
Tumor cell lines
White blood cells
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is demonstrated that cells can be classified by pattern recognition of the subcellular structure of non-stained live cells, and the pattern recognition was performed by machine learning. Human white blood cells and five types of cancer cell lines were imaged by quantitative phase microscopy, which provides morphological information without staining quantitatively in terms of optical thickness of cells. Subcellular features were then extracted from the obtained images as training data sets for the machine learning. The built classifier successfully classified WBCs from cell lines (area under ROC curve = 0.996). This label-free, non-cytotoxic cell classification based on the subcellular structure of QPM images has the potential to serve as an automated diagnosis of single cells.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0211347