Applying Pattern Recognition to High-Resolution Images to Determine Cellular Signaling Status

Michael F. Lohrer, Darrin M. Hanna, Yang Liu, Kang Hsin Wang, Fu-Tong Liu, Ted A. Laurence, Gang-yu Liu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Two frequently used tools to acquire high-resolution images of cells are scanning electron microscopy (SEM) and atomic force microscopy (AFM). The former provides a nanometer resolution view of cellular features rapidly and with high throughput, while the latter enables visualizing hydrated and living cells. In current practice, these images are viewed by eye to determine cellular status, e.g. activated versus resting. Automatic and quantitative data analysis is lacking. This work develops an algorithm of pattern recognition that works very effectively for AFM and SEM images. Using rat basophilic leukemia (RBL) cells, our approach creates a support vector machine (SVM) to automatically classify resting and activated cells. 10-fold cross-validation with cells that are known to be activated or resting gives a good estimate of the generalized classification results. The pattern recognition of AFM images achieves 100% accuracy, while SEM reaches 95.4% for our images as well as images published in prior literature. This outcome suggests that our methodology could become an important and frequently used tool for researchers utilizing AFM and SEM for structural characterization as well as determining cellular signaling status and function.

Original languageEnglish (US)
JournalIEEE Transactions on Nanobioscience
DOIs
StateAccepted/In press - Jun 21 2017

Fingerprint

Cell signaling
Image resolution
Atomic Force Microscopy
Pattern recognition
Atomic force microscopy
Electron Scanning Microscopy
Scanning electron microscopy
Support vector machines
Rats
Cells
Throughput
Leukemia
Research Personnel

ASJC Scopus subject areas

  • Biotechnology
  • Medicine (miscellaneous)
  • Bioengineering
  • Biomedical Engineering
  • Pharmaceutical Science
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Applying Pattern Recognition to High-Resolution Images to Determine Cellular Signaling Status. / Lohrer, Michael F.; Hanna, Darrin M.; Liu, Yang; Wang, Kang Hsin; Liu, Fu-Tong; Laurence, Ted A.; Liu, Gang-yu.

In: IEEE Transactions on Nanobioscience, 21.06.2017.

Research output: Contribution to journalArticle

Lohrer, Michael F. ; Hanna, Darrin M. ; Liu, Yang ; Wang, Kang Hsin ; Liu, Fu-Tong ; Laurence, Ted A. ; Liu, Gang-yu. / Applying Pattern Recognition to High-Resolution Images to Determine Cellular Signaling Status. In: IEEE Transactions on Nanobioscience. 2017.
@article{96e192fc2b51428b8ff8a41f6d79ac7a,
title = "Applying Pattern Recognition to High-Resolution Images to Determine Cellular Signaling Status",
abstract = "Two frequently used tools to acquire high-resolution images of cells are scanning electron microscopy (SEM) and atomic force microscopy (AFM). The former provides a nanometer resolution view of cellular features rapidly and with high throughput, while the latter enables visualizing hydrated and living cells. In current practice, these images are viewed by eye to determine cellular status, e.g. activated versus resting. Automatic and quantitative data analysis is lacking. This work develops an algorithm of pattern recognition that works very effectively for AFM and SEM images. Using rat basophilic leukemia (RBL) cells, our approach creates a support vector machine (SVM) to automatically classify resting and activated cells. 10-fold cross-validation with cells that are known to be activated or resting gives a good estimate of the generalized classification results. The pattern recognition of AFM images achieves 100{\%} accuracy, while SEM reaches 95.4{\%} for our images as well as images published in prior literature. This outcome suggests that our methodology could become an important and frequently used tool for researchers utilizing AFM and SEM for structural characterization as well as determining cellular signaling status and function.",
author = "Lohrer, {Michael F.} and Hanna, {Darrin M.} and Yang Liu and Wang, {Kang Hsin} and Fu-Tong Liu and Laurence, {Ted A.} and Gang-yu Liu",
year = "2017",
month = "6",
day = "21",
doi = "10.1109/TNB.2017.2717871",
language = "English (US)",
journal = "IEEE Transactions on Nanobioscience",
issn = "1536-1241",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Applying Pattern Recognition to High-Resolution Images to Determine Cellular Signaling Status

AU - Lohrer, Michael F.

AU - Hanna, Darrin M.

AU - Liu, Yang

AU - Wang, Kang Hsin

AU - Liu, Fu-Tong

AU - Laurence, Ted A.

AU - Liu, Gang-yu

PY - 2017/6/21

Y1 - 2017/6/21

N2 - Two frequently used tools to acquire high-resolution images of cells are scanning electron microscopy (SEM) and atomic force microscopy (AFM). The former provides a nanometer resolution view of cellular features rapidly and with high throughput, while the latter enables visualizing hydrated and living cells. In current practice, these images are viewed by eye to determine cellular status, e.g. activated versus resting. Automatic and quantitative data analysis is lacking. This work develops an algorithm of pattern recognition that works very effectively for AFM and SEM images. Using rat basophilic leukemia (RBL) cells, our approach creates a support vector machine (SVM) to automatically classify resting and activated cells. 10-fold cross-validation with cells that are known to be activated or resting gives a good estimate of the generalized classification results. The pattern recognition of AFM images achieves 100% accuracy, while SEM reaches 95.4% for our images as well as images published in prior literature. This outcome suggests that our methodology could become an important and frequently used tool for researchers utilizing AFM and SEM for structural characterization as well as determining cellular signaling status and function.

AB - Two frequently used tools to acquire high-resolution images of cells are scanning electron microscopy (SEM) and atomic force microscopy (AFM). The former provides a nanometer resolution view of cellular features rapidly and with high throughput, while the latter enables visualizing hydrated and living cells. In current practice, these images are viewed by eye to determine cellular status, e.g. activated versus resting. Automatic and quantitative data analysis is lacking. This work develops an algorithm of pattern recognition that works very effectively for AFM and SEM images. Using rat basophilic leukemia (RBL) cells, our approach creates a support vector machine (SVM) to automatically classify resting and activated cells. 10-fold cross-validation with cells that are known to be activated or resting gives a good estimate of the generalized classification results. The pattern recognition of AFM images achieves 100% accuracy, while SEM reaches 95.4% for our images as well as images published in prior literature. This outcome suggests that our methodology could become an important and frequently used tool for researchers utilizing AFM and SEM for structural characterization as well as determining cellular signaling status and function.

UR - http://www.scopus.com/inward/record.url?scp=85021789955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021789955&partnerID=8YFLogxK

U2 - 10.1109/TNB.2017.2717871

DO - 10.1109/TNB.2017.2717871

M3 - Article

C2 - 28644811

AN - SCOPUS:85021789955

JO - IEEE Transactions on Nanobioscience

JF - IEEE Transactions on Nanobioscience

SN - 1536-1241

ER -