Morphology-based prediction of cancer cell migration using an artificial neural network and a random decision forest

Zhixiong Zhang, Lili Chen, Brock Humphries, Riley Brien, Max S. Wicha, Kathryn E. Luker, Gary D. Luker, Yu Chih Chen, Euisik Yoon

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Metastasis is the cause of death in most patients of breast cancer and other solid malignancies. Identification of cancer cells with highly migratory capability to metastasize relies on markers for epithelial-to-mesenchymal transition (EMT), a process increasing cell migration and metastasis. Marker-based approaches are limited by inconsistences among patients, types of cancer, and partial EMT states. Alternatively, we analyzed cancer cell migration behavior using computer vision. Using a microfluidic single-cell migration chip and high-content imaging, we extracted morphological features and recorded migratory direction and speed of breast cancer cells. By applying a Random Decision Forest (RDF) and an Artificial Neural Network (ANN), we achieved over 99% accuracy for cell movement direction prediction and 91% for speed prediction. Unprecedentedly, we identified highly motile cells and non-motile cells based on microscope images and a machine learning model, and pinpointed and validated morphological features determining cell migration, including not only known features related to cell polarization but also novel ones that can drive future mechanistic studies. Predicting cell movement by computer vision and machine learning establishes a ground-breaking approach to analyze cell migration and metastasis.

Original languageEnglish
Pages (from-to)758-767
Number of pages10
JournalIntegrative Biology (United Kingdom)
Volume10
Issue number12
DOIs
Publication statusPublished - 2018 Dec

Fingerprint

Cell Movement
Cells
Neural networks
Neoplasms
Computer vision
Learning systems
Epithelial-Mesenchymal Transition
Neoplasm Metastasis
Breast Neoplasms
Microfluidics
Microscopes
Forests
Polarization
Imaging techniques
Cause of Death
Direction compound

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Biochemistry

Cite this

Zhang, Zhixiong ; Chen, Lili ; Humphries, Brock ; Brien, Riley ; Wicha, Max S. ; Luker, Kathryn E. ; Luker, Gary D. ; Chen, Yu Chih ; Yoon, Euisik. / Morphology-based prediction of cancer cell migration using an artificial neural network and a random decision forest. In: Integrative Biology (United Kingdom). 2018 ; Vol. 10, No. 12. pp. 758-767.
@article{a6272b37a0f34dd6ac6f315008d1d3a7,
title = "Morphology-based prediction of cancer cell migration using an artificial neural network and a random decision forest",
abstract = "Metastasis is the cause of death in most patients of breast cancer and other solid malignancies. Identification of cancer cells with highly migratory capability to metastasize relies on markers for epithelial-to-mesenchymal transition (EMT), a process increasing cell migration and metastasis. Marker-based approaches are limited by inconsistences among patients, types of cancer, and partial EMT states. Alternatively, we analyzed cancer cell migration behavior using computer vision. Using a microfluidic single-cell migration chip and high-content imaging, we extracted morphological features and recorded migratory direction and speed of breast cancer cells. By applying a Random Decision Forest (RDF) and an Artificial Neural Network (ANN), we achieved over 99{\%} accuracy for cell movement direction prediction and 91{\%} for speed prediction. Unprecedentedly, we identified highly motile cells and non-motile cells based on microscope images and a machine learning model, and pinpointed and validated morphological features determining cell migration, including not only known features related to cell polarization but also novel ones that can drive future mechanistic studies. Predicting cell movement by computer vision and machine learning establishes a ground-breaking approach to analyze cell migration and metastasis.",
author = "Zhixiong Zhang and Lili Chen and Brock Humphries and Riley Brien and Wicha, {Max S.} and Luker, {Kathryn E.} and Luker, {Gary D.} and Chen, {Yu Chih} and Euisik Yoon",
year = "2018",
month = "12",
doi = "10.1039/c8ib00106e",
language = "English",
volume = "10",
pages = "758--767",
journal = "Integrative Biology (United Kingdom)",
issn = "1757-9694",
publisher = "Royal Society of Chemistry",
number = "12",

}

Morphology-based prediction of cancer cell migration using an artificial neural network and a random decision forest. / Zhang, Zhixiong; Chen, Lili; Humphries, Brock; Brien, Riley; Wicha, Max S.; Luker, Kathryn E.; Luker, Gary D.; Chen, Yu Chih; Yoon, Euisik.

In: Integrative Biology (United Kingdom), Vol. 10, No. 12, 12.2018, p. 758-767.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Morphology-based prediction of cancer cell migration using an artificial neural network and a random decision forest

AU - Zhang, Zhixiong

AU - Chen, Lili

AU - Humphries, Brock

AU - Brien, Riley

AU - Wicha, Max S.

AU - Luker, Kathryn E.

AU - Luker, Gary D.

AU - Chen, Yu Chih

AU - Yoon, Euisik

PY - 2018/12

Y1 - 2018/12

N2 - Metastasis is the cause of death in most patients of breast cancer and other solid malignancies. Identification of cancer cells with highly migratory capability to metastasize relies on markers for epithelial-to-mesenchymal transition (EMT), a process increasing cell migration and metastasis. Marker-based approaches are limited by inconsistences among patients, types of cancer, and partial EMT states. Alternatively, we analyzed cancer cell migration behavior using computer vision. Using a microfluidic single-cell migration chip and high-content imaging, we extracted morphological features and recorded migratory direction and speed of breast cancer cells. By applying a Random Decision Forest (RDF) and an Artificial Neural Network (ANN), we achieved over 99% accuracy for cell movement direction prediction and 91% for speed prediction. Unprecedentedly, we identified highly motile cells and non-motile cells based on microscope images and a machine learning model, and pinpointed and validated morphological features determining cell migration, including not only known features related to cell polarization but also novel ones that can drive future mechanistic studies. Predicting cell movement by computer vision and machine learning establishes a ground-breaking approach to analyze cell migration and metastasis.

AB - Metastasis is the cause of death in most patients of breast cancer and other solid malignancies. Identification of cancer cells with highly migratory capability to metastasize relies on markers for epithelial-to-mesenchymal transition (EMT), a process increasing cell migration and metastasis. Marker-based approaches are limited by inconsistences among patients, types of cancer, and partial EMT states. Alternatively, we analyzed cancer cell migration behavior using computer vision. Using a microfluidic single-cell migration chip and high-content imaging, we extracted morphological features and recorded migratory direction and speed of breast cancer cells. By applying a Random Decision Forest (RDF) and an Artificial Neural Network (ANN), we achieved over 99% accuracy for cell movement direction prediction and 91% for speed prediction. Unprecedentedly, we identified highly motile cells and non-motile cells based on microscope images and a machine learning model, and pinpointed and validated morphological features determining cell migration, including not only known features related to cell polarization but also novel ones that can drive future mechanistic studies. Predicting cell movement by computer vision and machine learning establishes a ground-breaking approach to analyze cell migration and metastasis.

UR - http://www.scopus.com/inward/record.url?scp=85058886945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058886945&partnerID=8YFLogxK

U2 - 10.1039/c8ib00106e

DO - 10.1039/c8ib00106e

M3 - Article

C2 - 30420987

AN - SCOPUS:85058886945

VL - 10

SP - 758

EP - 767

JO - Integrative Biology (United Kingdom)

JF - Integrative Biology (United Kingdom)

SN - 1757-9694

IS - 12

ER -