Go to JCI Insight
  • About
  • Editors
  • Consulting Editors
  • For authors
  • Alerts
  • Advertising/recruitment
  • Subscribe
  • Contact
  • Current Issue
  • Past Issues
  • By specialty
    • COVID-19
    • Cardiology
    • Gastroenterology
    • Immunology
    • Metabolism
    • Nephrology
    • Neuroscience
    • Oncology
    • Pulmonology
    • Vascular biology
    • All ...
  • Videos
    • Conversations with Giants in Medicine
    • Author's Takes
  • Reviews
    • View all reviews ...
    • Tumor Microenvironment (Mar 2021)
    • 100th Anniversary of Insulin's Discovery (Jan 2021)
    • Hypoxia-inducible factors in disease pathophysiology and therapeutics (Oct 2020)
    • Latency in Infectious Disease (Jul 2020)
    • Immunotherapy in Hematological Cancers (Apr 2020)
    • Big Data's Future in Medicine (Feb 2020)
    • Mechanisms Underlying the Metabolic Syndrome (Oct 2019)
    • View all review series ...
  • Viewpoint
  • Collections
    • In-Press Preview
    • Commentaries
    • Concise Communication
    • Editorials
    • Viewpoint
    • Top read articles
  • Clinical Medicine
  • JCI This Month
    • Current issue
    • Past issues

  • Current issue
  • Past issues
  • Specialties
  • Reviews
  • Review series
  • Conversations with Giants in Medicine
  • Author's Takes
  • In-Press Preview
  • Commentaries
  • Concise Communication
  • Editorials
  • Viewpoint
  • Top read articles
  • About
  • Editors
  • Consulting Editors
  • For authors
  • Alerts
  • Advertising/recruitment
  • Subscribe
  • Contact
Deep learning predicts function of live retinal pigment epithelium from quantitative microscopy
Nicholas J. Schaub, … , Peter Bajcsy, Kapil Bharti
Nicholas J. Schaub, … , Peter Bajcsy, Kapil Bharti
Published November 12, 2019
Citation Information: J Clin Invest. 2020;130(2):1010-1023. https://doi.org/10.1172/JCI131187.
View: Text | PDF
Research Article Ophthalmology

Deep learning predicts function of live retinal pigment epithelium from quantitative microscopy

  • Text
  • PDF
Abstract

Increases in the number of cell therapies in the preclinical and clinical phases have prompted the need for reliable and noninvasive assays to validate transplant function in clinical biomanufacturing. We developed a robust characterization methodology composed of quantitative bright-field absorbance microscopy (QBAM) and deep neural networks (DNNs) to noninvasively predict tissue function and cellular donor identity. The methodology was validated using clinical-grade induced pluripotent stem cell–derived retinal pigment epithelial cells (iPSC-RPE). QBAM images of iPSC-RPE were used to train DNNs that predicted iPSC-RPE monolayer transepithelial resistance, predicted polarized vascular endothelial growth factor (VEGF) secretion, and matched iPSC-RPE monolayers to the stem cell donors. 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 noninvasive cell therapy characterization can be achieved with QBAM and machine learning.

Authors

Nicholas J. Schaub, Nathan A. Hotaling, Petre Manescu, Sarala Padi, Qin Wan, Ruchi Sharma, Aman George, Joe Chalfoun, Mylene Simon, Mohamed Ouladi, Carl G. Simon Jr., Peter Bajcsy, Kapil Bharti

×

Figure 4

DNN segmentation of iPSC-RPE in QBAM images.

Options: View larger image (or click on image) Download as PowerPoint
DNN segmentation of iPSC-RPE in QBAM images.
(A) A DNN (DNN-S) was const...
(A) A DNN (DNN-S) was constructed to segment iPSC-RPE cells in absorbance images. To train the DNN, iPSC-RPE monolayers were fluorescently labeled for cell borders (ZO-1) and registered to absorbance images for hand labeling of cell borders. Scale bar: 25 μm. (B–D) A comparison of 3 of 42 cell feature histograms for hand segmented (green) and DNN segmented (red) images, where yellow is the overlap in the histograms. (E) Time course of the average number of cells bordering each cell for an entire well. Shaded region represents 95% SEM. Twelve wells per time per treatment are shown. (F) A scatterplot of mean cell area and mean intensity (absorbance) for each treatment group assessed for each microscope FOV. Each dot represents 1 of 864 fields of view (12 wells per treatment, 12 images per well, 6 time points). (G) Minimum intensity (absorbance) found for individual cells as a function of treatment. Whiskers represent 3 times SD and single dots behind the violin represent individual cells measured. n = 3,871,106 cells for control; n = 3,831,362 cells for aphidicolin; n = 4,146,927 cells for HPI4. A complete set of feature histogram comparisons is presented in Supplemental Figure 5, and results of statistical tests are in Supplemental Table 2. Red diamond indicates the mean.

Copyright © 2021 American Society for Clinical Investigation
ISSN: 0021-9738 (print), 1558-8238 (online)

Sign up for email alerts