Figshare+
Browse

Retinal Pigment Epithelium (RPE) Segmentation Stacks

dataset
posted on 2025-04-28, 22:48 authored by Davide OrtolanDavide Ortolan, Pushkar Sathe, Andrei Volkov, Dominik Reichert, Sheldon Sebastian, Arvydas Maminishkis, Nicholas Shaub, Bengt Ljungquist, Devika Bose, Jorge Ferrari, Nyusha Lin, Gianluca PegoraroGianluca Pegoraro, Carl Simon, Ruchi Sharma, Peter Bajcsy, Kapil Bharti

This items contains stacks of cell, nuclei, and organelle segmentation. These were combined to facilitate browsing.

Dataset description:

The dataset contains images of retinal pigment epithelium (RPE) cells derived from 16 isogenic iPSC lines expressing proteins tagged with a fluorophore.


  1. Each cell line was seeded in a row of a 96-well plate. For every row:

Well numbers 02 to 06 – Cells treated with PGE2

Well numbers 07 to 11 – Cells treated with HPI4


  1. Six fields of view were acquired within each well with no tile overlap. They were evenly distributed around the well, and no field of view was placed at the very center of the well or at the edges as these locations may introduce a bias in the cell phenotype.
  2. Each cell line was imaged once a week for four weeks (W1-W4)
  3. The z-stacks contain three channels:

– Cell border segmentation
– Nuclear border segmentation
– Organelle segmentation


  1. Voxel dimension: 0.217 x 0.217 x 0.500 µm (xyz)
  2. File name convention:
    Ex: P1-W2-LAMP1_B02_F001.tif
    Plate # (1 to 5) - Week # (1 to 6) - Organelle of interest _ Well # (02 to 11) _ Field of view # (001-006)

Funding

Developing functional and authenticated RPE tissue from iPS cells

National Eye Institute

Find out more...

History

Research Institution(s)

National Eye Institute; National Institute of Standards and Technology; National Center for Advancing Translational Sciences; National Cancer Institute

I confirm there is no human personally identifiable information in the files or description shared

  • Yes

I confirm the files and description shared may be publicly distributed under the license selected

  • Yes