Unlocking the potential of digital pathology: Novel baselines for compression

Digital pathology offers a groundbreaking opportunity to transform clinical practice in histopathological image analysis, yet faces a significant hurdle: the substantial file sizes of pathological whole slide images (WSIs). Whereas current digital pathology solutions rely on lossy JPEG compression t...

Full description

Saved in:
Bibliographic Details
Main Authors: Maximilian Fischer, Peter Neher, Peter Schüffler, Sebastian Ziegler, Shuhan Xiao, Robin Peretzke, David Clunie, Constantin Ulrich, Michael Baumgartner, Alexander Muckenhuber, Silvia Dias Almeida, Michael Gőtz, Jens Kleesiek, Marco Nolden, Rickmer Braren, Klaus Maier-Hein
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:Journal of Pathology Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2153353925000033
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850268035877699584
author Maximilian Fischer
Peter Neher
Peter Schüffler
Sebastian Ziegler
Shuhan Xiao
Robin Peretzke
David Clunie
Constantin Ulrich
Michael Baumgartner
Alexander Muckenhuber
Silvia Dias Almeida
Michael Gőtz
Jens Kleesiek
Marco Nolden
Rickmer Braren
Klaus Maier-Hein
author_facet Maximilian Fischer
Peter Neher
Peter Schüffler
Sebastian Ziegler
Shuhan Xiao
Robin Peretzke
David Clunie
Constantin Ulrich
Michael Baumgartner
Alexander Muckenhuber
Silvia Dias Almeida
Michael Gőtz
Jens Kleesiek
Marco Nolden
Rickmer Braren
Klaus Maier-Hein
author_sort Maximilian Fischer
collection DOAJ
description Digital pathology offers a groundbreaking opportunity to transform clinical practice in histopathological image analysis, yet faces a significant hurdle: the substantial file sizes of pathological whole slide images (WSIs). Whereas current digital pathology solutions rely on lossy JPEG compression to address this issue, lossy compression can introduce color and texture disparities, potentially impacting clinical decision-making. Whereas prior research addresses perceptual image quality and downstream performance independently of each other, we jointly evaluate compression schemes for perceptual and downstream task quality on four different datasets. In addition, we collect an initially uncompressed dataset for an unbiased perceptual evaluation of compression schemes. Our results show that deep learning models fine-tuned for perceptual quality outperform conventional compression schemes like JPEG-XL or WebP for further compression of WSI. However, they exhibit a significant bias towards the compression artifacts present in the training data and struggle to generalize across various compression schemes. We introduce a novel evaluation metric based on feature similarity between original files and compressed files that aligns very well with the actual downstream performance on the compressed WSI. Our metric allows for a general and standardized evaluation of lossy compression schemes and mitigates the requirement to independently assess different downstream tasks. Our study provides novel insights for the assessment of lossy compression schemes for WSI and encourages a unified evaluation of lossy compression schemes to accelerate the clinical uptake of digital pathology.
format Article
id doaj-art-74c8d770d38a44aa80cb852717e4a6fe
institution OA Journals
issn 2153-3539
language English
publishDate 2025-04-01
publisher Elsevier
record_format Article
series Journal of Pathology Informatics
spelling doaj-art-74c8d770d38a44aa80cb852717e4a6fe2025-08-20T01:53:34ZengElsevierJournal of Pathology Informatics2153-35392025-04-011710042110.1016/j.jpi.2025.100421Unlocking the potential of digital pathology: Novel baselines for compressionMaximilian Fischer0Peter Neher1Peter Schüffler2Sebastian Ziegler3Shuhan Xiao4Robin Peretzke5David Clunie6Constantin Ulrich7Michael Baumgartner8Alexander Muckenhuber9Silvia Dias Almeida10Michael Gőtz11Jens Kleesiek12Marco Nolden13Rickmer Braren14Klaus Maier-Hein15Institute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; German Cancer Consortium (DKTK), partner site Heidelberg, Heidelberg, Germany; Medical Faculty, Heidelberg University, Heidelberg, Germany; Research Campus M2OLIE, Mannheim, Germany; Corresponding author at: German Cancer Research Center, Im Neuenheimer Feld 280, 69120 Heidelberg, Germany.Institute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; German Cancer Consortium (DKTK), partner site Heidelberg, Heidelberg, Germany; Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, GermanyInstitute of Pathology, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany; Munich Center for Machine Learning, Munich, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Helmholtz Imaging, German Cancer Research Center, Helmholtz, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, GermanyPixelMed Publishing, Bangor, Pennsylvania, United StatesInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Medical Faculty, Heidelberg University, Heidelberg, Germany; National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, GermanyInstitute of Pathology, TUM School of Medicine and Health, Technical University of Munich, Munich, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Medical Faculty, Heidelberg University, Heidelberg, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Clinic of Diagnostics and Interventional Radiology, Section Experimental, Radiology, Ulm University Medical Centre, Ulm, GermanyInstitute for AI in Medicine (IKIM), University Medicine Essen, Essen, Germany; German Cancer Consortium (DKTK), partner site Essen, Essen, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; Research Campus M2OLIE, Mannheim, GermanyDepartment of Diagnostic and Interventional Radiology, Faculty of Medicine, Technical University of Munich, Munich, GermanyInstitute Division of Medical Image Computing, German Cancer Research Center, (DKFZ), Heidelberg, Germany; Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany; Medical Faculty, Heidelberg University, Heidelberg, Germany; Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, GermanyDigital pathology offers a groundbreaking opportunity to transform clinical practice in histopathological image analysis, yet faces a significant hurdle: the substantial file sizes of pathological whole slide images (WSIs). Whereas current digital pathology solutions rely on lossy JPEG compression to address this issue, lossy compression can introduce color and texture disparities, potentially impacting clinical decision-making. Whereas prior research addresses perceptual image quality and downstream performance independently of each other, we jointly evaluate compression schemes for perceptual and downstream task quality on four different datasets. In addition, we collect an initially uncompressed dataset for an unbiased perceptual evaluation of compression schemes. Our results show that deep learning models fine-tuned for perceptual quality outperform conventional compression schemes like JPEG-XL or WebP for further compression of WSI. However, they exhibit a significant bias towards the compression artifacts present in the training data and struggle to generalize across various compression schemes. We introduce a novel evaluation metric based on feature similarity between original files and compressed files that aligns very well with the actual downstream performance on the compressed WSI. Our metric allows for a general and standardized evaluation of lossy compression schemes and mitigates the requirement to independently assess different downstream tasks. Our study provides novel insights for the assessment of lossy compression schemes for WSI and encourages a unified evaluation of lossy compression schemes to accelerate the clinical uptake of digital pathology.http://www.sciencedirect.com/science/article/pii/S2153353925000033Whole slide imagesLossy compressionFeature similarity
spellingShingle Maximilian Fischer
Peter Neher
Peter Schüffler
Sebastian Ziegler
Shuhan Xiao
Robin Peretzke
David Clunie
Constantin Ulrich
Michael Baumgartner
Alexander Muckenhuber
Silvia Dias Almeida
Michael Gőtz
Jens Kleesiek
Marco Nolden
Rickmer Braren
Klaus Maier-Hein
Unlocking the potential of digital pathology: Novel baselines for compression
Journal of Pathology Informatics
Whole slide images
Lossy compression
Feature similarity
title Unlocking the potential of digital pathology: Novel baselines for compression
title_full Unlocking the potential of digital pathology: Novel baselines for compression
title_fullStr Unlocking the potential of digital pathology: Novel baselines for compression
title_full_unstemmed Unlocking the potential of digital pathology: Novel baselines for compression
title_short Unlocking the potential of digital pathology: Novel baselines for compression
title_sort unlocking the potential of digital pathology novel baselines for compression
topic Whole slide images
Lossy compression
Feature similarity
url http://www.sciencedirect.com/science/article/pii/S2153353925000033
work_keys_str_mv AT maximilianfischer unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT peterneher unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT peterschuffler unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT sebastianziegler unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT shuhanxiao unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT robinperetzke unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT davidclunie unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT constantinulrich unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT michaelbaumgartner unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT alexandermuckenhuber unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT silviadiasalmeida unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT michaelgotz unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT jenskleesiek unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT marconolden unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT rickmerbraren unlockingthepotentialofdigitalpathologynovelbaselinesforcompression
AT klausmaierhein unlockingthepotentialofdigitalpathologynovelbaselinesforcompression