Analysing hyperplasia in Atlantic salmon gills using empirical wavelets

Carmichael, AFB; Baily, JL; Reeves, A; Ochoa, G; Boerlage, AS; Gunn, G; Allshire, R; Bhowmik, D

doi:10.1117/12.2655889

Analysing hyperplasia in Atlantic salmon gills using empirical wavelets

Lookup NU author(s): Dr Deepayan Bhowmik ORCiD

Downloads

Accepted version [.pdf]

Licence

This is the of a conference proceedings (inc. abstract) that has been published in its final definitive form by SPIE, 2023.

For re-use rights please refer to the publisher's terms and conditions.

Abstract

© 2023 SPIE. 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.