Anglia Ruskin Research Online (ARRO)
Browse

A deep learning-based compression and classification technique for whole slide histopathology images

Download (1.52 MB)
journal contribution
posted on 2024-09-24, 12:41 authored by Agnes Barsi, Suvendu Chandan Nayak, Sasmita Parida, Raj Mani Shukla

This paper presents an autoencoder-based neural network architecture to compress histopathological images while retaining the denser and more meaningful representation of the original images. Current research into improving compression algorithms is focused on methods allowing lower compression rates for Regions of Interest (ROI-based approaches). Neural networks are great at extracting meaningful semantic representations from images and, therefore can select the regions to be considered of interest for the compression process. In this work, we focus on the compression of whole slide histopathology images. The objective is to build an ensemble of neural networks that enables a compressive autoencoder in a supervised fashion to retain a denser and more meaningful representation of the input histology images. Our proposed system is a simple and novel method to supervise compressive neural networks. We test the compressed images using transfer learning-based classifiers and show that they provide promising accuracy and classification performance.

History

Refereed

  • Yes

Volume

16

Page range

4517-4526

Publication title

International Journal of Information Technology

ISSN

2511-2104

Publisher

Springer Science and Business Media LLC

File version

  • Published version

Language

  • eng

Item sub-type

Journal Article

Affiliated with

  • School of Computing and Information Science Outputs

Usage metrics

    ARU Outputs

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC