Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging

© 2015 IEEE. With its single cell sensitivity over volumes as large as or larger than a mouse, cryo-imaging enables imaging of stem cell biodistribution, homing, engraftment, and molecular mechanisms. We developed and evaluated a highly automated software tool to detect fluorescently labeled stem ce...

Full description

Saved in:
Bibliographic Details
Main Authors: Wuttisarnwattana P., Gargesha M., Van'T Hof W., Cooke K., Wilson D.
Format: Journal
Published: 2017
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84963774469&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/42070
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-42070
record_format dspace
spelling th-cmuir.6653943832-420702017-09-28T04:25:05Z Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging Wuttisarnwattana P. Gargesha M. Van'T Hof W. Cooke K. Wilson D. © 2015 IEEE. With its single cell sensitivity over volumes as large as or larger than a mouse, cryo-imaging enables imaging of stem cell biodistribution, homing, engraftment, and molecular mechanisms. We developed and evaluated a highly automated software tool to detect fluorescently labeled stem cells within very large (∼ 200 GB) cryo-imaging datasets. Cell detection steps are: preprocess, remove immaterial regions, spatially filter to create features, identify candidate pixels, classify pixels using bagging decision trees, segment cell patches, and perform 3D labeling. There are options for analysis and visualization. To train the classifier, we created synthetic images by placing realistic digital cell models onto cryo-images of control mice devoid of cells. Very good cell detection results were (precision = 98.49%, recall = 99.97%) for synthetic cryo-images, (precision = 97.81%, recall = 97.71%) for manually evaluated, actual cryo-images, and < 1% false positives in control mice. An α-multiplier applied to features allows one to correct for experimental variations in cell brightness due to labeling. On dim cells (37% of standard brightness), with correction, we improved recall (49.26% → 99.36%) without a significant drop in precision (99.99% → 99.75%). With tail vein injection, multipotent adult progenitor cells in a graft-versus-host-disease model in the first days post injection were predominantly found in lung, liver, spleen, and bone marrow. Distribution was not simply related to blood flow. The lung contained clusters of cells while other tissues contained single cells. Our methods provided stem cell distribution anywhere in mouse with single cell sensitivity. Methods should provide a rational means of evaluating dosing, delivery methods, cell enhancements, and mechanisms for therapeutic cells. 2017-09-28T04:25:05Z 2017-09-28T04:25:05Z 2016-03-01 Journal 02780062 2-s2.0-84963774469 10.1109/TMI.2015.2497285 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84963774469&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/42070
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
description © 2015 IEEE. With its single cell sensitivity over volumes as large as or larger than a mouse, cryo-imaging enables imaging of stem cell biodistribution, homing, engraftment, and molecular mechanisms. We developed and evaluated a highly automated software tool to detect fluorescently labeled stem cells within very large (∼ 200 GB) cryo-imaging datasets. Cell detection steps are: preprocess, remove immaterial regions, spatially filter to create features, identify candidate pixels, classify pixels using bagging decision trees, segment cell patches, and perform 3D labeling. There are options for analysis and visualization. To train the classifier, we created synthetic images by placing realistic digital cell models onto cryo-images of control mice devoid of cells. Very good cell detection results were (precision = 98.49%, recall = 99.97%) for synthetic cryo-images, (precision = 97.81%, recall = 97.71%) for manually evaluated, actual cryo-images, and < 1% false positives in control mice. An α-multiplier applied to features allows one to correct for experimental variations in cell brightness due to labeling. On dim cells (37% of standard brightness), with correction, we improved recall (49.26% → 99.36%) without a significant drop in precision (99.99% → 99.75%). With tail vein injection, multipotent adult progenitor cells in a graft-versus-host-disease model in the first days post injection were predominantly found in lung, liver, spleen, and bone marrow. Distribution was not simply related to blood flow. The lung contained clusters of cells while other tissues contained single cells. Our methods provided stem cell distribution anywhere in mouse with single cell sensitivity. Methods should provide a rational means of evaluating dosing, delivery methods, cell enhancements, and mechanisms for therapeutic cells.
format Journal
author Wuttisarnwattana P.
Gargesha M.
Van'T Hof W.
Cooke K.
Wilson D.
spellingShingle Wuttisarnwattana P.
Gargesha M.
Van'T Hof W.
Cooke K.
Wilson D.
Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging
author_facet Wuttisarnwattana P.
Gargesha M.
Van'T Hof W.
Cooke K.
Wilson D.
author_sort Wuttisarnwattana P.
title Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging
title_short Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging
title_full Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging
title_fullStr Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging
title_full_unstemmed Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-Imaging
title_sort automatic stem cell detection in microscopic whole mouse cryo-imaging
publishDate 2017
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84963774469&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/42070
_version_ 1681422119771045888