Logo image
Segmentation of Occluded Hematopoietic Stem Cells from Tracking
Conference proceeding   Open access

Segmentation of Occluded Hematopoietic Stem Cells from Tracking

Walter C. Mankowski, Mark R. Winter, Eric Wait, Mels Lodder, Ton Schumacher, Shalin H. Naik, Andrew R. Cohen and IEEE
2014 36TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), v 2014, pp 5510-5513
01 Jan 2014
PMID: 25571242
url
https://europepmc.org/articles/pmc4324458View
Accepted (AM)Open Access (License Unspecified) Open

Abstract

Engineering Engineering, Biomedical Engineering, Electrical & Electronic Science & Technology Technology
Image sequences of live proliferating cells often contain visual ambiguities that are difficult even for human domain experts to resolve. Here we present a new approach to analyzing image sequences that capture the development of clones of hematopoietic stem cells (HSCs) from live cell time lapse microscopy. The HSCs cannot survive long term imaging unless they are cultured together with a secondary cell type, OP9 stromal cells. The HSCs frequently disappear under the OP9 cell layer, making segmentation difficult or impossible from a single image frame, even for a human domain expert. We have developed a new approach to the segmentation of HSCs that captures these occluded cells. Starting with an a priori segmentation that uses a Monte Carlo technique to estimate the number of cells in a clump of touching cells, we proceed to track and lineage the image data. Following user validation of the lineage information, an a posteriori resegmentation step utilizing tracking results delineates the HSCs occluded by the OP9 layer. Resegmentation has been applied to 3031 occluded segmentations from 77 tracks, correctly recovering over 84% of the occluded segmentations.

Metrics

13 Record Views
6 citations in Scopus

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Engineering, Biomedical
Engineering, Electrical & Electronic
Logo image