liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Digital pathology whole slide image compression with Vector Quantized Variational Autoencoders
Univ Leeds, England.
Univ Leeds, England; Alan Turing Inst, England.
Univ Leeds, England; Leeds Teaching Hosp NHS Trust, England.
Linköping University, Department of Biomedical and Clinical Sciences, Division of Inflammation and Infection. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Center for Diagnostics, Clinical pathology. Univ Leeds, England; Leeds Teaching Hosp NHS Trust, England.ORCID iD: 0000-0002-4579-484X
2023 (English)In: MEDICAL IMAGING 2023, SPIE-INT SOC OPTICAL ENGINEERING , 2023, Vol. 12471, article id 124711BConference paper, Published paper (Refereed)
Abstract [en]

Digital pathology Whole Slide Images (WSIs) are large images (similar to 30 GB/slide uncompressed) of high resolution (0.25 microns per pixel), presenting a significant data storage challenge for hospitals wishing to adopt digital pathology. Lossy compression has been adopted by scanner manufacturers to address this issue - we compare lossy Joint Photographic Experts Group (JPEG) compression for WSIs and investigate the Vector Quantised Variational Autoencoder 2 variant (VQVAE2) as a possible alternative to reduce file size while encoding useful features in the compressed representation. We trained three VQVAE2 models on a Camelyon 2016 subset to the Compression Ratio (CR) of 19.2:1 (CR1), 9.6:1 (CR2) and 4.8:1 (CR3) and tested on a Camelyon 2016 (DS1) subset; University of California (DS2) and Internal Validation Set (DS3). We then compared compression performance to ImageMagick JPEG and JPEG 2000 implementations. Both JPEG and JPEG 2000 compression outperformed the VQVAE2 implementation within the Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) metrics. The trained VQVAE2 models could visually reproduce WSI tissue structure, but used colours from the original training data within the reconstructions on other datasets.

Place, publisher, year, edition, pages
SPIE-INT SOC OPTICAL ENGINEERING , 2023. Vol. 12471, article id 124711B
Series
Progress in Biomedical Optics and Imaging, ISSN 1605-7422
Keywords [en]
Variational Autoencoder; Quantisation; Compression; Pathology; Whole Slide Images; Digital; Pathology
National Category
Medical Image Processing
Identifiers
URN: urn:nbn:se:liu:diva-196954DOI: 10.1117/12.2647844ISI: 001011463700045ISBN: 9781510660472 (print)ISBN: 9781510660489 (print)OAI: oai:DiVA.org:liu-196954DiVA, id: diva2:1792500
Conference
Conference on Medical Imaging - Digital and Computational Pathology, San Diego, CA, feb 19-23, 2023
Note

Funding Agencies|EPSRC [2271095]; National Pathology Imaging Co-operative, NPIC [104687]

Available from: 2023-08-29 Created: 2023-08-29 Last updated: 2023-08-29

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Treanor, Darren
By organisation
Division of Inflammation and InfectionFaculty of Medicine and Health SciencesClinical pathology
Medical Image Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 37 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf