Analysing hyperplasia in Atlantic salmon gills using empirical wavelets

Alexander F.B. Carmichael; Johanna L. Baily; Aaron Reeves; Gabriela Ochoa; Annette S. Boerlage; George Gunn; Rosa Allshire; Deepayan Bhowmik

doi:10.1117/12.2655889

Analysing hyperplasia in Atlantic salmon gills using empirical wavelets

Alexander F.B. Carmichael^*, Johanna L. Baily, Aaron Reeves, Gabriela Ochoa, Annette S. Boerlage, George Gunn, Rosa Allshire, Deepayan Bhowmik

^*Corresponding author for this work

Centre for Epidemiology and Planetary Health (CEPH)

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

Abstract

Measuring hyperplasia in Atlantic salmon gills can give important insight into fish health and environmental conditions such as water quality. This paper proposes a novel histology image classification technique to identify hyperplastic regions using an emerging signal decomposition technique, Empirical Wavelet Transform (EWT) in combination with a fully connected neural network (FCNN). Due to its adaptive nature, we hypothesise and show that EWT effectively represents unique features of gill histopathology whole slide images that help in the classification task. Our hybrid approach is unique and significantly outperformed regular deep learning-based methods considering a joint speed-accuracy metric.

Original language	English
Title of host publication	Medical Imaging 2023
Subtitle of host publication	Digital and Computational Pathology
Editors	John E. Tomaszewski, Aaron D. Ward
Publisher	SPIE
ISBN (Electronic)	9781510660472
DOIs	https://doi.org/10.1117/12.2655889
Publication status	First published - 6 Apr 2023
Event	Medical Imaging 2023: Digital and Computational Pathology - San Diego, United States Duration: 19 Feb 2023 → 23 Feb 2023

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	12471
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2023: Digital and Computational Pathology
Country/Territory	United States
City	San Diego
Period	19/02/23 → 23/02/23

Bibliographical note

Publisher Copyright:
© 2023 SPIE.

Keywords

Atlantic salmon gills
deep learning
digital pathology
empirical wavelet transform
histopathology
Hyperplasia
image classification

Access to Document

10.1117/12.2655889

Cite this

Carmichael, A. F. B., Baily, J. L., Reeves, A., Ochoa, G., Boerlage, A. S., Gunn, G., Allshire, R., & Bhowmik, D. (2023). Analysing hyperplasia in Atlantic salmon gills using empirical wavelets. In J. E. Tomaszewski, & A. D. Ward (Eds.), Medical Imaging 2023: Digital and Computational Pathology Article 124710I (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12471). SPIE. Advance online publication. https://doi.org/10.1117/12.2655889

@inproceedings{047cd50bf7684f84bedd9a7ebc32ffc3,

title = "Analysing hyperplasia in Atlantic salmon gills using empirical wavelets",

abstract = "Measuring hyperplasia in Atlantic salmon gills can give important insight into fish health and environmental conditions such as water quality. This paper proposes a novel histology image classification technique to identify hyperplastic regions using an emerging signal decomposition technique, Empirical Wavelet Transform (EWT) in combination with a fully connected neural network (FCNN). Due to its adaptive nature, we hypothesise and show that EWT effectively represents unique features of gill histopathology whole slide images that help in the classification task. Our hybrid approach is unique and significantly outperformed regular deep learning-based methods considering a joint speed-accuracy metric.",

keywords = "Atlantic salmon gills, deep learning, digital pathology, empirical wavelet transform, histopathology, Hyperplasia, image classification",

author = "Carmichael, {Alexander F.B.} and Baily, {Johanna L.} and Aaron Reeves and Gabriela Ochoa and Boerlage, {Annette S.} and George Gunn and Rosa Allshire and Deepayan Bhowmik",

note = "Publisher Copyright: {\textcopyright} 2023 SPIE.; Medical Imaging 2023: Digital and Computational Pathology ; Conference date: 19-02-2023 Through 23-02-2023",

year = "2023",

month = apr,

day = "6",

doi = "10.1117/12.2655889",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Tomaszewski, {John E.} and Ward, {Aaron D.}",

booktitle = "Medical Imaging 2023",

}

Carmichael, AFB, Baily, JL, Reeves, A, Ochoa, G, Boerlage, AS, Gunn, G, Allshire, R & Bhowmik, D 2023, Analysing hyperplasia in Atlantic salmon gills using empirical wavelets. in JE Tomaszewski & AD Ward (eds), Medical Imaging 2023: Digital and Computational Pathology., 124710I, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 12471, SPIE, Medical Imaging 2023: Digital and Computational Pathology, San Diego, United States, 19/02/23. https://doi.org/10.1117/12.2655889

Analysing hyperplasia in Atlantic salmon gills using empirical wavelets. / Carmichael, Alexander F.B.; Baily, Johanna L.; Reeves, Aaron et al.
Medical Imaging 2023: Digital and Computational Pathology. ed. / John E. Tomaszewski; Aaron D. Ward. SPIE, 2023. 124710I (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12471).

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

TY - GEN

T1 - Analysing hyperplasia in Atlantic salmon gills using empirical wavelets

AU - Carmichael, Alexander F.B.

AU - Baily, Johanna L.

AU - Reeves, Aaron

AU - Ochoa, Gabriela

AU - Boerlage, Annette S.

AU - Gunn, George

AU - Allshire, Rosa

AU - Bhowmik, Deepayan

PY - 2023/4/6

Y1 - 2023/4/6

N2 - Measuring hyperplasia in Atlantic salmon gills can give important insight into fish health and environmental conditions such as water quality. This paper proposes a novel histology image classification technique to identify hyperplastic regions using an emerging signal decomposition technique, Empirical Wavelet Transform (EWT) in combination with a fully connected neural network (FCNN). Due to its adaptive nature, we hypothesise and show that EWT effectively represents unique features of gill histopathology whole slide images that help in the classification task. Our hybrid approach is unique and significantly outperformed regular deep learning-based methods considering a joint speed-accuracy metric.

AB - Measuring hyperplasia in Atlantic salmon gills can give important insight into fish health and environmental conditions such as water quality. This paper proposes a novel histology image classification technique to identify hyperplastic regions using an emerging signal decomposition technique, Empirical Wavelet Transform (EWT) in combination with a fully connected neural network (FCNN). Due to its adaptive nature, we hypothesise and show that EWT effectively represents unique features of gill histopathology whole slide images that help in the classification task. Our hybrid approach is unique and significantly outperformed regular deep learning-based methods considering a joint speed-accuracy metric.

KW - Atlantic salmon gills

KW - deep learning

KW - digital pathology

KW - empirical wavelet transform

KW - histopathology

KW - Hyperplasia

KW - image classification

UR - http://www.scopus.com/inward/record.url?scp=85160542785&partnerID=8YFLogxK

U2 - 10.1117/12.2655889

DO - 10.1117/12.2655889

M3 - Conference contribution

AN - SCOPUS:85160542785

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2023

A2 - Tomaszewski, John E.

A2 - Ward, Aaron D.

PB - SPIE

T2 - Medical Imaging 2023: Digital and Computational Pathology

Y2 - 19 February 2023 through 23 February 2023

ER -

Analysing hyperplasia in Atlantic salmon gills using empirical wavelets

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this