A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche

C. Ryan Oliver; Megan A. Altemus; Trisha M. Westerhof; Hannah Cheriyan; Xu Cheng; Michelle Dziubinski; Zhifen Wu; Joel Yates; Aki Morikawa; Jason Heth; Maria G. Castro; Brendan M. Leung; Shuichi Takayama; Sofia D. Merajver

doi:10.1039/c8lc01387j

A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche

C. Ryan Oliver, Megan A. Altemus, Trisha M. Westerhof, Hannah Cheriyan, Xu Cheng, Michelle Dziubinski, Zhifen Wu, Joel Yates, Aki Morikawa, Jason Heth, Maria G. Castro, Brendan M. Leung, Shuichi Takayama, Sofia D. Merajver

Medicine

Research output: Contribution to journal › Article › peer-review

42 Citations (Scopus)

Abstract

Brain metastases are the most lethal complication of advanced cancer; therefore, it is critical to identify when a tumor has the potential to metastasize to the brain. There are currently no interventions that shed light on the potential of primary tumors to metastasize to the brain. We constructed and tested a platform to quantitatively profile the dynamic phenotypes of cancer cells from aggressive triple negative breast cancer cell lines and patient derived xenografts (PDXs), generated from a primary tumor and brain metastases from tumors of diverse organs of origin. Combining an advanced live cell imaging algorithm and artificial intelligence, we profile cancer cell extravasation within a microfluidic blood-brain niche (μBBN) chip, to detect the minute differences between cells with brain metastatic potential and those without with a PPV of 0.91 in the context of this study. The results show remarkably sharp and reproducible distinction between cells that do and those which do not metastasize inside of the device.

Original language	English
Pages (from-to)	1162-1173
Number of pages	12
Journal	Lab on a Chip
Volume	19
Issue number	7
DOIs	https://doi.org/10.1039/c8lc01387j
Publication status	Published - Apr 7 2019

Bibliographical note

Funding Information:
Work was supported by: NIH T32CA009676 (CRO, MA), the University of Michigan Rogel Cancer Center Nancy Newton Loeb Fund (MA), by NIH grants P30CA046592 (BL, SDM, MA, CRO), CA196018 (CRO, ST), AI116482 (CRO, ST), by the META-vivor Foundation (MA, SDM) and the Breast Cancer Research Foundation (CRO, SDM).

Publisher Copyright:
© 2019 The Royal Society of Chemistry.

ASJC Scopus Subject Areas

Bioengineering
Biochemistry
General Chemistry
Biomedical Engineering

PubMed: MeSH publication types

Journal Article
Research Support, N.I.H., Extramural

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1039/c8lc01387j

Cite this

Oliver, C. R., Altemus, M. A., Westerhof, T. M., Cheriyan, H., Cheng, X., Dziubinski, M., Wu, Z., Yates, J., Morikawa, A., Heth, J., Castro, M. G., Leung, B. M., Takayama, S., & Merajver, S. D. (2019). A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche. Lab on a Chip, 19(7), 1162-1173. https://doi.org/10.1039/c8lc01387j

Oliver, CR, Altemus, MA, Westerhof, TM, Cheriyan, H, Cheng, X, Dziubinski, M, Wu, Z, Yates, J, Morikawa, A, Heth, J, Castro, MG, Leung, BM, Takayama, S & Merajver, SD 2019, 'A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche', Lab on a Chip, vol. 19, no. 7, pp. 1162-1173. https://doi.org/10.1039/c8lc01387j

@article{2bb9d88436ae45b78eb7d9cfc677417d,

title = "A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche",

abstract = "Brain metastases are the most lethal complication of advanced cancer; therefore, it is critical to identify when a tumor has the potential to metastasize to the brain. There are currently no interventions that shed light on the potential of primary tumors to metastasize to the brain. We constructed and tested a platform to quantitatively profile the dynamic phenotypes of cancer cells from aggressive triple negative breast cancer cell lines and patient derived xenografts (PDXs), generated from a primary tumor and brain metastases from tumors of diverse organs of origin. Combining an advanced live cell imaging algorithm and artificial intelligence, we profile cancer cell extravasation within a microfluidic blood-brain niche (μBBN) chip, to detect the minute differences between cells with brain metastatic potential and those without with a PPV of 0.91 in the context of this study. The results show remarkably sharp and reproducible distinction between cells that do and those which do not metastasize inside of the device.",

author = "Oliver, {C. Ryan} and Altemus, {Megan A.} and Westerhof, {Trisha M.} and Hannah Cheriyan and Xu Cheng and Michelle Dziubinski and Zhifen Wu and Joel Yates and Aki Morikawa and Jason Heth and Castro, {Maria G.} and Leung, {Brendan M.} and Shuichi Takayama and Merajver, {Sofia D.}",

note = "Funding Information: Work was supported by: NIH T32CA009676 (CRO, MA), the University of Michigan Rogel Cancer Center Nancy Newton Loeb Fund (MA), by NIH grants P30CA046592 (BL, SDM, MA, CRO), CA196018 (CRO, ST), AI116482 (CRO, ST), by the META-vivor Foundation (MA, SDM) and the Breast Cancer Research Foundation (CRO, SDM). Publisher Copyright: {\textcopyright} 2019 The Royal Society of Chemistry.",

year = "2019",

month = apr,

day = "7",

doi = "10.1039/c8lc01387j",

language = "English",

volume = "19",

pages = "1162--1173",

journal = "Lab on a Chip",

issn = "1473-0197",

publisher = "Royal Society of Chemistry",

number = "7",

}

TY - JOUR

T1 - A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche

AU - Oliver, C. Ryan

AU - Altemus, Megan A.

AU - Westerhof, Trisha M.

AU - Cheriyan, Hannah

AU - Cheng, Xu

AU - Dziubinski, Michelle

AU - Wu, Zhifen

AU - Yates, Joel

AU - Morikawa, Aki

AU - Heth, Jason

AU - Castro, Maria G.

AU - Leung, Brendan M.

AU - Takayama, Shuichi

AU - Merajver, Sofia D.

N1 - Funding Information: Work was supported by: NIH T32CA009676 (CRO, MA), the University of Michigan Rogel Cancer Center Nancy Newton Loeb Fund (MA), by NIH grants P30CA046592 (BL, SDM, MA, CRO), CA196018 (CRO, ST), AI116482 (CRO, ST), by the META-vivor Foundation (MA, SDM) and the Breast Cancer Research Foundation (CRO, SDM). Publisher Copyright: © 2019 The Royal Society of Chemistry.

PY - 2019/4/7

Y1 - 2019/4/7

N2 - Brain metastases are the most lethal complication of advanced cancer; therefore, it is critical to identify when a tumor has the potential to metastasize to the brain. There are currently no interventions that shed light on the potential of primary tumors to metastasize to the brain. We constructed and tested a platform to quantitatively profile the dynamic phenotypes of cancer cells from aggressive triple negative breast cancer cell lines and patient derived xenografts (PDXs), generated from a primary tumor and brain metastases from tumors of diverse organs of origin. Combining an advanced live cell imaging algorithm and artificial intelligence, we profile cancer cell extravasation within a microfluidic blood-brain niche (μBBN) chip, to detect the minute differences between cells with brain metastatic potential and those without with a PPV of 0.91 in the context of this study. The results show remarkably sharp and reproducible distinction between cells that do and those which do not metastasize inside of the device.

AB - Brain metastases are the most lethal complication of advanced cancer; therefore, it is critical to identify when a tumor has the potential to metastasize to the brain. There are currently no interventions that shed light on the potential of primary tumors to metastasize to the brain. We constructed and tested a platform to quantitatively profile the dynamic phenotypes of cancer cells from aggressive triple negative breast cancer cell lines and patient derived xenografts (PDXs), generated from a primary tumor and brain metastases from tumors of diverse organs of origin. Combining an advanced live cell imaging algorithm and artificial intelligence, we profile cancer cell extravasation within a microfluidic blood-brain niche (μBBN) chip, to detect the minute differences between cells with brain metastatic potential and those without with a PPV of 0.91 in the context of this study. The results show remarkably sharp and reproducible distinction between cells that do and those which do not metastasize inside of the device.

UR - http://www.scopus.com/inward/record.url?scp=85063438524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063438524&partnerID=8YFLogxK

U2 - 10.1039/c8lc01387j

DO - 10.1039/c8lc01387j

M3 - Article

C2 - 30810557

AN - SCOPUS:85063438524

SN - 1473-0197

VL - 19

SP - 1162

EP - 1173

JO - Lab on a Chip

JF - Lab on a Chip

IS - 7

ER -

A platform for artificial intelligence based identification of the extravasation potential of cancer cells into the brain metastatic niche

Abstract

Bibliographical note

ASJC Scopus Subject Areas

PubMed: MeSH publication types

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this