Development of an automated detection algorithm for patient motion blur in digital mammograms

Melissa L. Hill, Patsy Whelehan, Sarah J. Vinnicombe, Christopher E. Tromans, Andrew Evans, Violet R. Warwick, J. Michael Brady, Ralph P. Highnam

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

63 Downloads (Pure)

Abstract

The purpose is to develop and validate an automated method for detecting image unsharpness caused by patient motion blur in digital mammograms. The goal is that such a tool would facilitate immediate re-taking of blurred images, which has the potential to reduce the number of recalled examinations, and to ensure that sharp, high-quality mammograms are presented for reading. To meet this goal, an automated method was developed based on interpretation of the normalized image Wiener Spectrum. A preliminary algorithm was developed using 25 cases acquired using a single vendor system, read by two expert readers identifying the presence of blur, location, and severity. A predictive blur severity score was established using multivariate modeling, which had an adjusted coefficient of determination, R2 =0.63±0.02, for linear regression against the average reader-scored blur severity. A heatmap of the relative blur magnitude showed good correspondence with reader sketches of blur location, with a Spearman rank correlation of 0.70 between the algorithmestimated area fraction with blur and the maximum of the blur area fraction categories of the two readers. Given these promising results, the algorithm-estimated blur severity score and heatmap are proposed to be used to aid observer interpretation. The use of this automated blur analysis approach, ideally with feedback during an exam, could lead to a reduction in repeat appointments for technical reasons, saving time, cost, potential anxiety, and improving image quality for accurate diagnosis.

Original languageEnglish
Title of host publicationProceedings of the SPIE
Subtitle of host publication14th International Workshop on Breast Imaging (IWBI 2018)
EditorsElizabeth A. Krupinski
PublisherSPIE-International Society for Optical Engineering
Number of pages8
Volume10718
ISBN (Electronic)9781510620070
DOIs
Publication statusPublished - 6 Jul 2018
Event14th International Workshop on Breast Imaging (IWBI 2018) - Atlanta, United States
Duration: 8 Jul 201811 Jul 2018

Publication series

NameProceedings of SPIE
PublisherSPIE - International Society for Optical Engineering
Volume10718

Conference

Conference14th International Workshop on Breast Imaging (IWBI 2018)
CountryUnited States
CityAtlanta
Period8/07/1811/07/18

Fingerprint

readers
Linear regression
Image quality
Reading
Linear Models
Appointments and Schedules
Anxiety
anxiety
Feedback
Costs and Cost Analysis
Costs
regression analysis
examination
costs
coefficients

Keywords

  • automated detection
  • blur
  • digital radiography
  • mammography
  • Patient motion
  • unsharpness

Cite this

Hill, M. L., Whelehan, P., Vinnicombe, S. J., Tromans, C. E., Evans, A., Warwick, V. R., ... Highnam, R. P. (2018). Development of an automated detection algorithm for patient motion blur in digital mammograms. In E. A. Krupinski (Ed.), Proceedings of the SPIE: 14th International Workshop on Breast Imaging (IWBI 2018) (Vol. 10718). [107180K] (Proceedings of SPIE; Vol. 10718). SPIE-International Society for Optical Engineering. https://doi.org/10.1117/12.2318225
Hill, Melissa L. ; Whelehan, Patsy ; Vinnicombe, Sarah J. ; Tromans, Christopher E. ; Evans, Andrew ; Warwick, Violet R. ; Brady, J. Michael ; Highnam, Ralph P. / Development of an automated detection algorithm for patient motion blur in digital mammograms. Proceedings of the SPIE: 14th International Workshop on Breast Imaging (IWBI 2018). editor / Elizabeth A. Krupinski. Vol. 10718 SPIE-International Society for Optical Engineering, 2018. (Proceedings of SPIE).
@inproceedings{580e1617eaed4f20a585e71192ce9966,
title = "Development of an automated detection algorithm for patient motion blur in digital mammograms",
abstract = "The purpose is to develop and validate an automated method for detecting image unsharpness caused by patient motion blur in digital mammograms. The goal is that such a tool would facilitate immediate re-taking of blurred images, which has the potential to reduce the number of recalled examinations, and to ensure that sharp, high-quality mammograms are presented for reading. To meet this goal, an automated method was developed based on interpretation of the normalized image Wiener Spectrum. A preliminary algorithm was developed using 25 cases acquired using a single vendor system, read by two expert readers identifying the presence of blur, location, and severity. A predictive blur severity score was established using multivariate modeling, which had an adjusted coefficient of determination, R2 =0.63±0.02, for linear regression against the average reader-scored blur severity. A heatmap of the relative blur magnitude showed good correspondence with reader sketches of blur location, with a Spearman rank correlation of 0.70 between the algorithmestimated area fraction with blur and the maximum of the blur area fraction categories of the two readers. Given these promising results, the algorithm-estimated blur severity score and heatmap are proposed to be used to aid observer interpretation. The use of this automated blur analysis approach, ideally with feedback during an exam, could lead to a reduction in repeat appointments for technical reasons, saving time, cost, potential anxiety, and improving image quality for accurate diagnosis.",
keywords = "automated detection, blur, digital radiography, mammography, Patient motion, unsharpness",
author = "Hill, {Melissa L.} and Patsy Whelehan and Vinnicombe, {Sarah J.} and Tromans, {Christopher E.} and Andrew Evans and Warwick, {Violet R.} and Brady, {J. Michael} and Highnam, {Ralph P.}",
year = "2018",
month = "7",
day = "6",
doi = "10.1117/12.2318225",
language = "English",
volume = "10718",
series = "Proceedings of SPIE",
publisher = "SPIE-International Society for Optical Engineering",
editor = "Krupinski, {Elizabeth A.}",
booktitle = "Proceedings of the SPIE",

}

Hill, ML, Whelehan, P, Vinnicombe, SJ, Tromans, CE, Evans, A, Warwick, VR, Brady, JM & Highnam, RP 2018, Development of an automated detection algorithm for patient motion blur in digital mammograms. in EA Krupinski (ed.), Proceedings of the SPIE: 14th International Workshop on Breast Imaging (IWBI 2018). vol. 10718, 107180K, Proceedings of SPIE, vol. 10718, SPIE-International Society for Optical Engineering, 14th International Workshop on Breast Imaging (IWBI 2018), Atlanta, United States, 8/07/18. https://doi.org/10.1117/12.2318225

Development of an automated detection algorithm for patient motion blur in digital mammograms. / Hill, Melissa L.; Whelehan, Patsy; Vinnicombe, Sarah J.; Tromans, Christopher E.; Evans, Andrew; Warwick, Violet R.; Brady, J. Michael; Highnam, Ralph P.

Proceedings of the SPIE: 14th International Workshop on Breast Imaging (IWBI 2018). ed. / Elizabeth A. Krupinski. Vol. 10718 SPIE-International Society for Optical Engineering, 2018. 107180K (Proceedings of SPIE; Vol. 10718).

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

TY - GEN

T1 - Development of an automated detection algorithm for patient motion blur in digital mammograms

AU - Hill, Melissa L.

AU - Whelehan, Patsy

AU - Vinnicombe, Sarah J.

AU - Tromans, Christopher E.

AU - Evans, Andrew

AU - Warwick, Violet R.

AU - Brady, J. Michael

AU - Highnam, Ralph P.

PY - 2018/7/6

Y1 - 2018/7/6

N2 - The purpose is to develop and validate an automated method for detecting image unsharpness caused by patient motion blur in digital mammograms. The goal is that such a tool would facilitate immediate re-taking of blurred images, which has the potential to reduce the number of recalled examinations, and to ensure that sharp, high-quality mammograms are presented for reading. To meet this goal, an automated method was developed based on interpretation of the normalized image Wiener Spectrum. A preliminary algorithm was developed using 25 cases acquired using a single vendor system, read by two expert readers identifying the presence of blur, location, and severity. A predictive blur severity score was established using multivariate modeling, which had an adjusted coefficient of determination, R2 =0.63±0.02, for linear regression against the average reader-scored blur severity. A heatmap of the relative blur magnitude showed good correspondence with reader sketches of blur location, with a Spearman rank correlation of 0.70 between the algorithmestimated area fraction with blur and the maximum of the blur area fraction categories of the two readers. Given these promising results, the algorithm-estimated blur severity score and heatmap are proposed to be used to aid observer interpretation. The use of this automated blur analysis approach, ideally with feedback during an exam, could lead to a reduction in repeat appointments for technical reasons, saving time, cost, potential anxiety, and improving image quality for accurate diagnosis.

AB - The purpose is to develop and validate an automated method for detecting image unsharpness caused by patient motion blur in digital mammograms. The goal is that such a tool would facilitate immediate re-taking of blurred images, which has the potential to reduce the number of recalled examinations, and to ensure that sharp, high-quality mammograms are presented for reading. To meet this goal, an automated method was developed based on interpretation of the normalized image Wiener Spectrum. A preliminary algorithm was developed using 25 cases acquired using a single vendor system, read by two expert readers identifying the presence of blur, location, and severity. A predictive blur severity score was established using multivariate modeling, which had an adjusted coefficient of determination, R2 =0.63±0.02, for linear regression against the average reader-scored blur severity. A heatmap of the relative blur magnitude showed good correspondence with reader sketches of blur location, with a Spearman rank correlation of 0.70 between the algorithmestimated area fraction with blur and the maximum of the blur area fraction categories of the two readers. Given these promising results, the algorithm-estimated blur severity score and heatmap are proposed to be used to aid observer interpretation. The use of this automated blur analysis approach, ideally with feedback during an exam, could lead to a reduction in repeat appointments for technical reasons, saving time, cost, potential anxiety, and improving image quality for accurate diagnosis.

KW - automated detection

KW - blur

KW - digital radiography

KW - mammography

KW - Patient motion

KW - unsharpness

U2 - 10.1117/12.2318225

DO - 10.1117/12.2318225

M3 - Conference contribution

VL - 10718

T3 - Proceedings of SPIE

BT - Proceedings of the SPIE

A2 - Krupinski, Elizabeth A.

PB - SPIE-International Society for Optical Engineering

ER -

Hill ML, Whelehan P, Vinnicombe SJ, Tromans CE, Evans A, Warwick VR et al. Development of an automated detection algorithm for patient motion blur in digital mammograms. In Krupinski EA, editor, Proceedings of the SPIE: 14th International Workshop on Breast Imaging (IWBI 2018). Vol. 10718. SPIE-International Society for Optical Engineering. 2018. 107180K. (Proceedings of SPIE). https://doi.org/10.1117/12.2318225