Quantitative Bright-Field Microscopy Combined with Deep Neural Networks Predict Live Tissue Function

Published

February 29, 2020

Author(s)

Carl Simon, Nicholas J. Schaub, Petru S. Manescu, Sarala Padi, Mylene Simon, Peter Bajcsy, Nathan A. Hotaling, Joe Chalfoun, Mohamed Ouladi, Qin Wan, Kapil Bharti, Ruchi Sharma

Abstract

Progressive increases in the number of cell therapies in the preclinical and clinical phases has prompted the need for reliable and non-invasive assays to validate transplant function in clinical biomanufacturing. Here, we developed a robust characterization platform composed of quantitative bright- field absorbance microscopy (QBAM) and deep neural networks (DNNs) to non-invasively predict tissue function and cellular donor identity. The platform was validated using clinical-grade induced pluripotent stem cell derived retinal pigment epithelial cells (iRPE). QBAM images of iRPE were used to train DNNs that predicted iRPE monolayer transepithelial resistance (R2=0.97), predicted polarized VEGF secretion (R2=0.89), and matched iRPE monolayers to the iPSC donors (accuracy=85%). DNN predictions were supplemented with traditional machine learning algorithms that identified shape and texture features of single cells that were used to predict tissue function and iPSC donor identity. These results demonstrate non-invasive cell therapy characterization can be achieved with quantitative bright-field microscopy and machine learning.

Citation

Biomaterials

Pub Type

Journals

Download Paper

https://doi.org/10.1172/JCI131187

Local Download

Keywords

deep neural networks, induced pluripotent stem cells, retinal pigment epithelial cells, bright-field microscopy, machine learning, cell therapy

Citation

Simon, C. , Schaub, N. , Manescu, P. , Padi, S. , Simon, M. , Bajcsy, P. , Hotaling, N. , Chalfoun, J. , Ouladi, M. , Wan, Q. , Bharti, K. and Sharma, R. (2020), Quantitative Bright-Field Microscopy Combined with Deep Neural Networks Predict Live Tissue Function, Biomaterials, [online], https://doi.org/10.1172/JCI131187, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=926975 (Accessed October 13, 2025)