Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations

Katerina Lomanov; Jesus Martinez del Rincon; Paul Miller; Hugh Gribben

doi:10.1109/ISBI.2019.8759411

Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations

Katerina Lomanov
, Jesus Martinez del Rincon
, Paul Miller
, Hugh Gribben

School of Electronics, Electrical Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

437 Downloads (Pure)

Abstract

In this paper, we propose and thoroughly compare strategies for training convolutional neural networks (CNNs) for cell localization and segmentation in microscopy images with both little training data and in presence of significant label noise. Insufficient availability of ground truth (GT) is a common issue in the field of microscopy image analysis, hence the usefulness of such approaches. Performance evaluation is done using phase contrast microscopy human fibrosarcoma (HT1080) cells and comparing the resulting F-scores.

Original language	English
Title of host publication	IEEE International Symposium on Biomedical Imaging (ISBI) 2019 proceeding
Pages	943-947
Number of pages	5
ISBN (Electronic)	978-1-5386-3641-1
DOIs	https://doi.org/10.1109/ISBI.2019.8759411
Publication status	Published - 11 Jul 2019
Event	IEEE International Symposium on Biomedical Imaging - Venice, Italy Duration: 08 Apr 2019 → 11 Apr 2019 Conference number: 2019 https://biomedicalimaging.org/2019/

Publication series

Name	IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
Publisher	IEEE
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	IEEE International Symposium on Biomedical Imaging
Abbreviated title	ISBI
Country/Territory	Italy
City	Venice
Period	08/04/2019 → 11/04/2019
Internet address	https://biomedicalimaging.org/2019/

Access to Document

10.1109/ISBI.2019.8759411Licence: Unspecified

Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations
© 2018 IEEE. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.56 MBLicence: Unspecified

Detection and tracking of cells and focal adhesions in microscopy images
Lomanov, K. (Author), Miller, P. (Supervisor) & Martinez del Rincon, J. (Supervisor), Dec 2020
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

@inproceedings{b6b21e6513d44e4fbbc25d7f335da155,

title = "Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations",

abstract = "In this paper, we propose and thoroughly compare strategies for training convolutional neural networks (CNNs) for cell localization and segmentation in microscopy images with both little training data and in presence of significant label noise. Insufficient availability of ground truth (GT) is a common issue in the field of microscopy image analysis, hence the usefulness of such approaches. Performance evaluation is done using phase contrast microscopy human fibrosarcoma (HT1080) cells and comparing the resulting F-scores.",

author = "Katerina Lomanov and \{Martinez del Rincon\}, Jesus and Paul Miller and Hugh Gribben",

year = "2019",

month = jul,

day = "11",

doi = "10.1109/ISBI.2019.8759411",

language = "English",

isbn = "978-1-5386-3642-8",

series = "IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)",

publisher = "IEEE",

pages = "943--947",

booktitle = "IEEE International Symposium on Biomedical Imaging (ISBI) 2019 proceeding",

note = "IEEE International Symposium on Biomedical Imaging, ISBI ; Conference date: 08-04-2019 Through 11-04-2019",

url = "https://biomedicalimaging.org/2019/",

}

Lomanov, K, Martinez del Rincon, J , Miller, P & Gribben, H 2019, Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations. in IEEE International Symposium on Biomedical Imaging (ISBI) 2019 proceeding. IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 943-947, IEEE International Symposium on Biomedical Imaging, Venice, Italy, 08/04/2019. https://doi.org/10.1109/ISBI.2019.8759411

Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations. / Lomanov, Katerina; Martinez del Rincon, Jesus ; Miller, Paul et al.
IEEE International Symposium on Biomedical Imaging (ISBI) 2019 proceeding. 2019. p. 943-947 (IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations

AU - Lomanov, Katerina

AU - Martinez del Rincon, Jesus

AU - Miller, Paul

AU - Gribben, Hugh

N1 - Conference code: 2019

PY - 2019/7/11

Y1 - 2019/7/11

N2 - In this paper, we propose and thoroughly compare strategies for training convolutional neural networks (CNNs) for cell localization and segmentation in microscopy images with both little training data and in presence of significant label noise. Insufficient availability of ground truth (GT) is a common issue in the field of microscopy image analysis, hence the usefulness of such approaches. Performance evaluation is done using phase contrast microscopy human fibrosarcoma (HT1080) cells and comparing the resulting F-scores.

AB - In this paper, we propose and thoroughly compare strategies for training convolutional neural networks (CNNs) for cell localization and segmentation in microscopy images with both little training data and in presence of significant label noise. Insufficient availability of ground truth (GT) is a common issue in the field of microscopy image analysis, hence the usefulness of such approaches. Performance evaluation is done using phase contrast microscopy human fibrosarcoma (HT1080) cells and comparing the resulting F-scores.

U2 - 10.1109/ISBI.2019.8759411

DO - 10.1109/ISBI.2019.8759411

M3 - Conference contribution

SN - 978-1-5386-3642-8

T3 - IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

SP - 943

EP - 947

BT - IEEE International Symposium on Biomedical Imaging (ISBI) 2019 proceeding

T2 - IEEE International Symposium on Biomedical Imaging

Y2 - 8 April 2019 through 11 April 2019

ER -

Cell Detection With Deep Convolutional Networks Trained With Minimal Annotations

Abstract

Publication series

Conference

Access to Document

Fingerprint

Student theses

Detection and tracking of cells and focal adhesions in microscopy images

Cite this