A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images

Although deep learning and computer vision based approaches have demonstrated success in the field of cell counting and detection in microscopic images, they continue to have certain limitations. More specifically, they experience an overall increase in false positives when dealing with cell populat...

Full description

Saved in:
Bibliographic Details
Main Authors: C. Emre Dedeagac, Can F. Koyuncu, Michelle M. Adams, Cagatay Edemen, Berk C. Ugurdag, N. Ilgim Ardic-Avci, H. Fatih Ugurdag
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10802904/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037705491087360
author C. Emre Dedeagac
Can F. Koyuncu
Michelle M. Adams
Cagatay Edemen
Berk C. Ugurdag
N. Ilgim Ardic-Avci
H. Fatih Ugurdag
author_facet C. Emre Dedeagac
Can F. Koyuncu
Michelle M. Adams
Cagatay Edemen
Berk C. Ugurdag
N. Ilgim Ardic-Avci
H. Fatih Ugurdag
author_sort C. Emre Dedeagac
collection DOAJ
description Although deep learning and computer vision based approaches have demonstrated success in the field of cell counting and detection in microscopic images, they continue to have certain limitations. More specifically, they experience an overall increase in false positives when dealing with cell populations that show high density and heterogeneity. Existing approaches require the reselection of parameters for each new dataset to improve the accuracy of cell counting. Therefore, it is necessary to revise the fundamental models for each new microscopic image. This study introduces a novel neural network-based method that eliminates the need for retraining by combining the pretrained Cellpose and Stardist models. The accuracy of our proposed approach was evaluated on a variety of microscopic images. Despite variations in cell densities, our proposed approach demonstrated a notably improved cell counting performance in comparison to solely utilizing the Cellpose and Stardist models.
format Article
id doaj-art-eed7487972eb4808938f0e6080ce4857
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-eed7487972eb4808938f0e6080ce48572025-08-20T02:56:47ZengIEEEIEEE Access2169-35362024-01-011219555219556010.1109/ACCESS.2024.351764110802904A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy ImagesC. Emre Dedeagac0https://orcid.org/0000-0001-7197-9541Can F. Koyuncu1https://orcid.org/0000-0001-5990-2226Michelle M. Adams2https://orcid.org/0000-0002-5249-6461Cagatay Edemen3Berk C. Ugurdag4N. Ilgim Ardic-Avci5H. Fatih Ugurdag6https://orcid.org/0000-0002-6256-0850Department of Computer Science, Özyeğin University, İstanbul, TürkiyeDepartment of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USAInterdisciplinary Graduate Program in Neuroscience, National Nanotechnology Research Center (UNAM), Ankara, TürkiyeDepartment of Electrical and Electronics Engineering, Özyeğin University, İstanbul, TürkiyeDepartment of Computer Science, Georgetown University, Washington, DC, USAInterdisciplinary Graduate Program in Neuroscience, National Nanotechnology Research Center (UNAM), Ankara, TürkiyeDepartment of Electrical and Electronics Engineering, Özyeğin University, İstanbul, TürkiyeAlthough deep learning and computer vision based approaches have demonstrated success in the field of cell counting and detection in microscopic images, they continue to have certain limitations. More specifically, they experience an overall increase in false positives when dealing with cell populations that show high density and heterogeneity. Existing approaches require the reselection of parameters for each new dataset to improve the accuracy of cell counting. Therefore, it is necessary to revise the fundamental models for each new microscopic image. This study introduces a novel neural network-based method that eliminates the need for retraining by combining the pretrained Cellpose and Stardist models. The accuracy of our proposed approach was evaluated on a variety of microscopic images. Despite variations in cell densities, our proposed approach demonstrated a notably improved cell counting performance in comparison to solely utilizing the Cellpose and Stardist models.https://ieeexplore.ieee.org/document/10802904/Cell countingcell detectiondeep learningensemble learning
spellingShingle C. Emre Dedeagac
Can F. Koyuncu
Michelle M. Adams
Cagatay Edemen
Berk C. Ugurdag
N. Ilgim Ardic-Avci
H. Fatih Ugurdag
A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images
IEEE Access
Cell counting
cell detection
deep learning
ensemble learning
title A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images
title_full A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images
title_fullStr A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images
title_full_unstemmed A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images
title_short A Guided-Ensembling Approach for Cell Counting in Fluorescence Microscopy Images
title_sort guided ensembling approach for cell counting in fluorescence microscopy images
topic Cell counting
cell detection
deep learning
ensemble learning
url https://ieeexplore.ieee.org/document/10802904/
work_keys_str_mv AT cemrededeagac aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT canfkoyuncu aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT michellemadams aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT cagatayedemen aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT berkcugurdag aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT nilgimardicavci aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT hfatihugurdag aguidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT cemrededeagac guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT canfkoyuncu guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT michellemadams guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT cagatayedemen guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT berkcugurdag guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT nilgimardicavci guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages
AT hfatihugurdag guidedensemblingapproachforcellcountinginfluorescencemicroscopyimages