A method for size estimation for small objects and its application in brachytherapy seed identification

Yi Su, Brian J. Davis, Richard A. Robb

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

2 Citations (Scopus)

Abstract

This study compared the performance of four different object size estimation methods using numerically created experimental images with features relevant to the practice of prostate brachytherapy. The four methods are: 1) pixel count of objects in the segmented binary mask; 2) half peak thresholding based on the previously created binary mask from method 1 and the original image; 3) gray scale averaging of pixels in the binary mask and the surrounding area; and 4) a point spread function corrected version of method 3. The first method demonstrated a 16% error in object size estimation while the other three methods exhibited average errors near 4%. Methods 3 and 4 gave a more consistent estimation of the size for different image contrasts. The first three methods were also applied on three fluoroscopic images of a prostate phantom with 64 implanted seeds. In combination with a classification algorithm, the seed image number and location were determined. Again, method 3 showed superior performance, because it correctly identified 64 seeds in 2 of 3 fluoroscopic images, while 4 false positives appeared in one of the three images. This study confirms that partial volume effects on the size estimation can be compensated by using a gray scale averaging technique. When applied to the seed image identification process, it will improve the accuracy of seed image detection.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsJ.M. Fitzpatrick, M. Sonka
Pages1679-1684
Number of pages6
Volume5370 III
DOIs
StatePublished - 2004
EventProgress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing - San Diego, CA, United States
Duration: Feb 16 2004Feb 19 2004

Other

OtherProgress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing
CountryUnited States
CitySan Diego, CA
Period2/16/042/19/04

Fingerprint

Seed
seeds
Masks
Pixels
masks
gray scale
Optical transfer function
pixels
image contrast
point spread functions

Keywords

  • Brachytherapy
  • Segmentation
  • Size estimation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Su, Y., Davis, B. J., & Robb, R. A. (2004). A method for size estimation for small objects and its application in brachytherapy seed identification. In J. M. Fitzpatrick, & M. Sonka (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5370 III, pp. 1679-1684) https://doi.org/10.1117/12.535426

A method for size estimation for small objects and its application in brachytherapy seed identification. / Su, Yi; Davis, Brian J.; Robb, Richard A.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / J.M. Fitzpatrick; M. Sonka. Vol. 5370 III 2004. p. 1679-1684.

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

Su, Y, Davis, BJ & Robb, RA 2004, A method for size estimation for small objects and its application in brachytherapy seed identification. in JM Fitzpatrick & M Sonka (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5370 III, pp. 1679-1684, Progress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing, San Diego, CA, United States, 2/16/04. https://doi.org/10.1117/12.535426
Su Y, Davis BJ, Robb RA. A method for size estimation for small objects and its application in brachytherapy seed identification. In Fitzpatrick JM, Sonka M, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5370 III. 2004. p. 1679-1684 https://doi.org/10.1117/12.535426
Su, Yi ; Davis, Brian J. ; Robb, Richard A. / A method for size estimation for small objects and its application in brachytherapy seed identification. Proceedings of SPIE - The International Society for Optical Engineering. editor / J.M. Fitzpatrick ; M. Sonka. Vol. 5370 III 2004. pp. 1679-1684
@inproceedings{e48f555d80e3444f9ada4698e79e4971,
title = "A method for size estimation for small objects and its application in brachytherapy seed identification",
abstract = "This study compared the performance of four different object size estimation methods using numerically created experimental images with features relevant to the practice of prostate brachytherapy. The four methods are: 1) pixel count of objects in the segmented binary mask; 2) half peak thresholding based on the previously created binary mask from method 1 and the original image; 3) gray scale averaging of pixels in the binary mask and the surrounding area; and 4) a point spread function corrected version of method 3. The first method demonstrated a 16{\%} error in object size estimation while the other three methods exhibited average errors near 4{\%}. Methods 3 and 4 gave a more consistent estimation of the size for different image contrasts. The first three methods were also applied on three fluoroscopic images of a prostate phantom with 64 implanted seeds. In combination with a classification algorithm, the seed image number and location were determined. Again, method 3 showed superior performance, because it correctly identified 64 seeds in 2 of 3 fluoroscopic images, while 4 false positives appeared in one of the three images. This study confirms that partial volume effects on the size estimation can be compensated by using a gray scale averaging technique. When applied to the seed image identification process, it will improve the accuracy of seed image detection.",
keywords = "Brachytherapy, Segmentation, Size estimation",
author = "Yi Su and Davis, {Brian J.} and Robb, {Richard A.}",
year = "2004",
doi = "10.1117/12.535426",
language = "English (US)",
volume = "5370 III",
pages = "1679--1684",
editor = "J.M. Fitzpatrick and M. Sonka",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - A method for size estimation for small objects and its application in brachytherapy seed identification

AU - Su, Yi

AU - Davis, Brian J.

AU - Robb, Richard A.

PY - 2004

Y1 - 2004

N2 - This study compared the performance of four different object size estimation methods using numerically created experimental images with features relevant to the practice of prostate brachytherapy. The four methods are: 1) pixel count of objects in the segmented binary mask; 2) half peak thresholding based on the previously created binary mask from method 1 and the original image; 3) gray scale averaging of pixels in the binary mask and the surrounding area; and 4) a point spread function corrected version of method 3. The first method demonstrated a 16% error in object size estimation while the other three methods exhibited average errors near 4%. Methods 3 and 4 gave a more consistent estimation of the size for different image contrasts. The first three methods were also applied on three fluoroscopic images of a prostate phantom with 64 implanted seeds. In combination with a classification algorithm, the seed image number and location were determined. Again, method 3 showed superior performance, because it correctly identified 64 seeds in 2 of 3 fluoroscopic images, while 4 false positives appeared in one of the three images. This study confirms that partial volume effects on the size estimation can be compensated by using a gray scale averaging technique. When applied to the seed image identification process, it will improve the accuracy of seed image detection.

AB - This study compared the performance of four different object size estimation methods using numerically created experimental images with features relevant to the practice of prostate brachytherapy. The four methods are: 1) pixel count of objects in the segmented binary mask; 2) half peak thresholding based on the previously created binary mask from method 1 and the original image; 3) gray scale averaging of pixels in the binary mask and the surrounding area; and 4) a point spread function corrected version of method 3. The first method demonstrated a 16% error in object size estimation while the other three methods exhibited average errors near 4%. Methods 3 and 4 gave a more consistent estimation of the size for different image contrasts. The first three methods were also applied on three fluoroscopic images of a prostate phantom with 64 implanted seeds. In combination with a classification algorithm, the seed image number and location were determined. Again, method 3 showed superior performance, because it correctly identified 64 seeds in 2 of 3 fluoroscopic images, while 4 false positives appeared in one of the three images. This study confirms that partial volume effects on the size estimation can be compensated by using a gray scale averaging technique. When applied to the seed image identification process, it will improve the accuracy of seed image detection.

KW - Brachytherapy

KW - Segmentation

KW - Size estimation

UR - http://www.scopus.com/inward/record.url?scp=5644290753&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5644290753&partnerID=8YFLogxK

U2 - 10.1117/12.535426

DO - 10.1117/12.535426

M3 - Conference contribution

VL - 5370 III

SP - 1679

EP - 1684

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Fitzpatrick, J.M.

A2 - Sonka, M.

ER -