Model prediction of just noticeable differences

Are the eyes attracted to the same areas?

Elizabeth A Krupinski, Jeffrey Johnson, Hans Roehrig, John Nafziger, Jeffrey Lubin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The JNDmetrix human visual system model developed by the Sarnoff Corporation is used to predict observer performance on visual discrimination tasks. It begins with two paired images as the initial input and ends with a JND map that shows the magnitude and spatial location of visible differences between the two input images. The goal of this experiment was to determine if the location and magnitude of JNDs identified by the model corresponded to visual search parameters of the human observer. Radiologists searched 20 mammograms with multiple masses and microcalcifications of different subtleties as their eye-position was recorded. The JNDmetrix model analyzed the same images and identified, with JNDs, discriminable areas on the images. Lesions with lower subtlety ratings were detected later in search than more obvious ones (FNs later than TPs). When the subtler lesions were detected (TP) dwell time was longer than more obvious lesions, but the FNs received shorter total dwell. The subtler lesions when detected (TP) received more total fixation clusters than more obvious ones, but the FNs received fewer. The correlation between the model JNDs and the eye-position parameters was high. Understanding the influence of lesion subtlety on search may help us better model and predict human observer performance.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
EditorsM.P. Eckstein, Y. Jiang
Pages496-501
Number of pages6
Volume5749
DOIs
StatePublished - 2005
EventMedical Imaging 2005 - Image Perception, Observer Performance, and Technology Assessment - San Diego, CA, United States
Duration: Feb 15 2005Feb 17 2005

Other

OtherMedical Imaging 2005 - Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CitySan Diego, CA
Period2/15/052/17/05

Fingerprint

Prediction Model
lesions
Observer
predictions
dwell
visual discrimination
Microcalcifications
Visual Search
Predict
Dwell Time
Mammogram
Human Visual System
Model
ratings
Fixation
Discrimination
Experiment
Industry
Experiments
Human

Keywords

  • Discrimination model
  • Eye-position
  • JND
  • Performance

ASJC Scopus subject areas

  • Engineering(all)
  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Krupinski, E. A., Johnson, J., Roehrig, H., Nafziger, J., & Lubin, J. (2005). Model prediction of just noticeable differences: Are the eyes attracted to the same areas? In M. P. Eckstein, & Y. Jiang (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 5749, pp. 496-501). [54] https://doi.org/10.1117/12.592217

Model prediction of just noticeable differences : Are the eyes attracted to the same areas? / Krupinski, Elizabeth A; Johnson, Jeffrey; Roehrig, Hans; Nafziger, John; Lubin, Jeffrey.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. ed. / M.P. Eckstein; Y. Jiang. Vol. 5749 2005. p. 496-501 54.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Krupinski, EA, Johnson, J, Roehrig, H, Nafziger, J & Lubin, J 2005, Model prediction of just noticeable differences: Are the eyes attracted to the same areas? in MP Eckstein & Y Jiang (eds), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 5749, 54, pp. 496-501, Medical Imaging 2005 - Image Perception, Observer Performance, and Technology Assessment, San Diego, CA, United States, 2/15/05. https://doi.org/10.1117/12.592217
Krupinski EA, Johnson J, Roehrig H, Nafziger J, Lubin J. Model prediction of just noticeable differences: Are the eyes attracted to the same areas? In Eckstein MP, Jiang Y, editors, Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 5749. 2005. p. 496-501. 54 https://doi.org/10.1117/12.592217
Krupinski, Elizabeth A ; Johnson, Jeffrey ; Roehrig, Hans ; Nafziger, John ; Lubin, Jeffrey. / Model prediction of just noticeable differences : Are the eyes attracted to the same areas?. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. editor / M.P. Eckstein ; Y. Jiang. Vol. 5749 2005. pp. 496-501
@inproceedings{a8acd748d98e4b73830bc2255b8860bb,
title = "Model prediction of just noticeable differences: Are the eyes attracted to the same areas?",
abstract = "The JNDmetrix human visual system model developed by the Sarnoff Corporation is used to predict observer performance on visual discrimination tasks. It begins with two paired images as the initial input and ends with a JND map that shows the magnitude and spatial location of visible differences between the two input images. The goal of this experiment was to determine if the location and magnitude of JNDs identified by the model corresponded to visual search parameters of the human observer. Radiologists searched 20 mammograms with multiple masses and microcalcifications of different subtleties as their eye-position was recorded. The JNDmetrix model analyzed the same images and identified, with JNDs, discriminable areas on the images. Lesions with lower subtlety ratings were detected later in search than more obvious ones (FNs later than TPs). When the subtler lesions were detected (TP) dwell time was longer than more obvious lesions, but the FNs received shorter total dwell. The subtler lesions when detected (TP) received more total fixation clusters than more obvious ones, but the FNs received fewer. The correlation between the model JNDs and the eye-position parameters was high. Understanding the influence of lesion subtlety on search may help us better model and predict human observer performance.",
keywords = "Discrimination model, Eye-position, JND, Performance",
author = "Krupinski, {Elizabeth A} and Jeffrey Johnson and Hans Roehrig and John Nafziger and Jeffrey Lubin",
year = "2005",
doi = "10.1117/12.592217",
language = "English (US)",
volume = "5749",
pages = "496--501",
editor = "M.P. Eckstein and Y. Jiang",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Model prediction of just noticeable differences

T2 - Are the eyes attracted to the same areas?

AU - Krupinski, Elizabeth A

AU - Johnson, Jeffrey

AU - Roehrig, Hans

AU - Nafziger, John

AU - Lubin, Jeffrey

PY - 2005

Y1 - 2005

N2 - The JNDmetrix human visual system model developed by the Sarnoff Corporation is used to predict observer performance on visual discrimination tasks. It begins with two paired images as the initial input and ends with a JND map that shows the magnitude and spatial location of visible differences between the two input images. The goal of this experiment was to determine if the location and magnitude of JNDs identified by the model corresponded to visual search parameters of the human observer. Radiologists searched 20 mammograms with multiple masses and microcalcifications of different subtleties as their eye-position was recorded. The JNDmetrix model analyzed the same images and identified, with JNDs, discriminable areas on the images. Lesions with lower subtlety ratings were detected later in search than more obvious ones (FNs later than TPs). When the subtler lesions were detected (TP) dwell time was longer than more obvious lesions, but the FNs received shorter total dwell. The subtler lesions when detected (TP) received more total fixation clusters than more obvious ones, but the FNs received fewer. The correlation between the model JNDs and the eye-position parameters was high. Understanding the influence of lesion subtlety on search may help us better model and predict human observer performance.

AB - The JNDmetrix human visual system model developed by the Sarnoff Corporation is used to predict observer performance on visual discrimination tasks. It begins with two paired images as the initial input and ends with a JND map that shows the magnitude and spatial location of visible differences between the two input images. The goal of this experiment was to determine if the location and magnitude of JNDs identified by the model corresponded to visual search parameters of the human observer. Radiologists searched 20 mammograms with multiple masses and microcalcifications of different subtleties as their eye-position was recorded. The JNDmetrix model analyzed the same images and identified, with JNDs, discriminable areas on the images. Lesions with lower subtlety ratings were detected later in search than more obvious ones (FNs later than TPs). When the subtler lesions were detected (TP) dwell time was longer than more obvious lesions, but the FNs received shorter total dwell. The subtler lesions when detected (TP) received more total fixation clusters than more obvious ones, but the FNs received fewer. The correlation between the model JNDs and the eye-position parameters was high. Understanding the influence of lesion subtlety on search may help us better model and predict human observer performance.

KW - Discrimination model

KW - Eye-position

KW - JND

KW - Performance

UR - http://www.scopus.com/inward/record.url?scp=24644488286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24644488286&partnerID=8YFLogxK

U2 - 10.1117/12.592217

DO - 10.1117/12.592217

M3 - Conference contribution

VL - 5749

SP - 496

EP - 501

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

A2 - Eckstein, M.P.

A2 - Jiang, Y.

ER -