Using a visual discrimination model for the detection of compression artifacts in virtual pathology images

Jeffrey P. Johnson, Elizabeth A Krupinski, Michelle Yan, Hans Roehrig, Anna R. Graham, Ronald S Weinstein

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

A major issue in telepathology is the extremely large and growing size of digitized virtual slides, which can require several gigabytes of storage and cause significant delays in data transmission for remote image interpretation and interactive visualization by pathologists. Compression can reduce this massive amount of virtual slide data, but reversible (lossless) methods limit data reduction to less than 50%, while lossy compression can degrade image quality and diagnostic accuracy. Visually lossless compression offers the potential for using higher compression levels without noticeable artifacts, but requires a rate-control strategy that adapts to image content and loss visibility. We investigated the utility of a visual discrimination model (VDM) and other distortion metrics for predicting JPEG 2000 bit rates corresponding to visually lossless compression of virtual slides for breast biopsy specimens. Threshold bit rates were determined experimentally with human observers for a variety of tissue regions cropped from virtual slides. For test images compressed to their visually lossless thresholds, just-noticeable difference (JND) metrics computed by the VDM were nearly constant at the 95th percentile level or higher, and were significantly less variable than peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics. Our results suggest that VDM metrics could be used to guide the compression of virtual slides to achieve visually lossless compression while providing 512 times the data reduction of reversible methods.

Original languageEnglish (US)
Article number5582290
Pages (from-to)306-314
Number of pages9
JournalIEEE Transactions on Medical Imaging
Volume30
Issue number2
DOIs
StatePublished - Feb 2011

Fingerprint

Pathology
Artifacts
Data reduction
Telepathology
Differential Threshold
Biopsy
Signal-To-Noise Ratio
Visibility
Data communication systems
Image quality
Signal to noise ratio
Breast
Visualization
Tissue
Discrimination (Psychology)

Keywords

  • Compression
  • just noticeable differences
  • virtual pathology slides
  • visual discrimination model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

Using a visual discrimination model for the detection of compression artifacts in virtual pathology images. / Johnson, Jeffrey P.; Krupinski, Elizabeth A; Yan, Michelle; Roehrig, Hans; Graham, Anna R.; Weinstein, Ronald S.

In: IEEE Transactions on Medical Imaging, Vol. 30, No. 2, 5582290, 02.2011, p. 306-314.

Research output: Contribution to journalArticle

@article{b2347198061d4092a4c160a1fe298318,
title = "Using a visual discrimination model for the detection of compression artifacts in virtual pathology images",
abstract = "A major issue in telepathology is the extremely large and growing size of digitized virtual slides, which can require several gigabytes of storage and cause significant delays in data transmission for remote image interpretation and interactive visualization by pathologists. Compression can reduce this massive amount of virtual slide data, but reversible (lossless) methods limit data reduction to less than 50{\%}, while lossy compression can degrade image quality and diagnostic accuracy. Visually lossless compression offers the potential for using higher compression levels without noticeable artifacts, but requires a rate-control strategy that adapts to image content and loss visibility. We investigated the utility of a visual discrimination model (VDM) and other distortion metrics for predicting JPEG 2000 bit rates corresponding to visually lossless compression of virtual slides for breast biopsy specimens. Threshold bit rates were determined experimentally with human observers for a variety of tissue regions cropped from virtual slides. For test images compressed to their visually lossless thresholds, just-noticeable difference (JND) metrics computed by the VDM were nearly constant at the 95th percentile level or higher, and were significantly less variable than peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics. Our results suggest that VDM metrics could be used to guide the compression of virtual slides to achieve visually lossless compression while providing 512 times the data reduction of reversible methods.",
keywords = "Compression, just noticeable differences, virtual pathology slides, visual discrimination model",
author = "Johnson, {Jeffrey P.} and Krupinski, {Elizabeth A} and Michelle Yan and Hans Roehrig and Graham, {Anna R.} and Weinstein, {Ronald S}",
year = "2011",
month = "2",
doi = "10.1109/TMI.2010.2077308",
language = "English (US)",
volume = "30",
pages = "306--314",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Using a visual discrimination model for the detection of compression artifacts in virtual pathology images

AU - Johnson, Jeffrey P.

AU - Krupinski, Elizabeth A

AU - Yan, Michelle

AU - Roehrig, Hans

AU - Graham, Anna R.

AU - Weinstein, Ronald S

PY - 2011/2

Y1 - 2011/2

N2 - A major issue in telepathology is the extremely large and growing size of digitized virtual slides, which can require several gigabytes of storage and cause significant delays in data transmission for remote image interpretation and interactive visualization by pathologists. Compression can reduce this massive amount of virtual slide data, but reversible (lossless) methods limit data reduction to less than 50%, while lossy compression can degrade image quality and diagnostic accuracy. Visually lossless compression offers the potential for using higher compression levels without noticeable artifacts, but requires a rate-control strategy that adapts to image content and loss visibility. We investigated the utility of a visual discrimination model (VDM) and other distortion metrics for predicting JPEG 2000 bit rates corresponding to visually lossless compression of virtual slides for breast biopsy specimens. Threshold bit rates were determined experimentally with human observers for a variety of tissue regions cropped from virtual slides. For test images compressed to their visually lossless thresholds, just-noticeable difference (JND) metrics computed by the VDM were nearly constant at the 95th percentile level or higher, and were significantly less variable than peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics. Our results suggest that VDM metrics could be used to guide the compression of virtual slides to achieve visually lossless compression while providing 512 times the data reduction of reversible methods.

AB - A major issue in telepathology is the extremely large and growing size of digitized virtual slides, which can require several gigabytes of storage and cause significant delays in data transmission for remote image interpretation and interactive visualization by pathologists. Compression can reduce this massive amount of virtual slide data, but reversible (lossless) methods limit data reduction to less than 50%, while lossy compression can degrade image quality and diagnostic accuracy. Visually lossless compression offers the potential for using higher compression levels without noticeable artifacts, but requires a rate-control strategy that adapts to image content and loss visibility. We investigated the utility of a visual discrimination model (VDM) and other distortion metrics for predicting JPEG 2000 bit rates corresponding to visually lossless compression of virtual slides for breast biopsy specimens. Threshold bit rates were determined experimentally with human observers for a variety of tissue regions cropped from virtual slides. For test images compressed to their visually lossless thresholds, just-noticeable difference (JND) metrics computed by the VDM were nearly constant at the 95th percentile level or higher, and were significantly less variable than peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics. Our results suggest that VDM metrics could be used to guide the compression of virtual slides to achieve visually lossless compression while providing 512 times the data reduction of reversible methods.

KW - Compression

KW - just noticeable differences

KW - virtual pathology slides

KW - visual discrimination model

UR - http://www.scopus.com/inward/record.url?scp=79551600371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79551600371&partnerID=8YFLogxK

U2 - 10.1109/TMI.2010.2077308

DO - 10.1109/TMI.2010.2077308

M3 - Article

VL - 30

SP - 306

EP - 314

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 2

M1 - 5582290

ER -