Automated estimation of number of implanted iodine-125 seeds for prostate brachytherapy based on two-view analysis of pelvic radiographs.

Hidemichi Kawata, Hidetaka Arimura, Hiroaki Suefuji, Sunao Ohkura, Yoshifumi Saida, Kazutaka Nashiki, Kazuya Hayashida, Tomomi Kawahara, Ayumu Ohishi, Naofumi Hayabuchi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Digital pelvic radiographs are used to identify the locations of implanted iodine-125 seeds and their numbers after insertion. However, it is difficult and laborious to visually identify and count all implanted seeds on the pelvic radiographs within a short time. Therefore, our purpose in this research was to develop an automated method for estimation of the number of implanted seeds based on two-view analysis of pelvic radiographs. First, the images of the seed candidates on the pelvic image were enhanced using a difference of Gaussian filter, and were identified by binarizing the enhanced image with a threshold value determined by multiple-gray level thresholding. Second, a simple rule-base method using ten image features was applied for false positive removal. Third, the candidates for the likely number of a multiply overlapping seed region, which may include one or more seeds, were estimated by a seed area histogram analysis and calculation of the probability of the likely number of overlapping seeds. As a result, the proposed method detected 99.9% of implanted seeds with 0.71 false positives per image on average in a test for training cases, and 99.2% with 0.32 false positives in a validation test. Moreover, the number of implanted seeds was estimated correctly at an overall recognition rate of 100% in the validation test using the proposed method. Therefore, the verification time for the number of implanted seeds could be reduced by the provision of several candidates for the likely number of seeds.

Original languageEnglish
Pages (from-to)742-752
Number of pages11
JournalJournal of radiation research
Volume53
Issue number5
DOIs
Publication statusPublished - Jan 1 2012

Fingerprint

iodine 125
Brachytherapy
Iodine
seeds
Prostate
Seeds
histograms

All Science Journal Classification (ASJC) codes

  • Radiation
  • Radiology Nuclear Medicine and imaging
  • Health, Toxicology and Mutagenesis

Cite this

Automated estimation of number of implanted iodine-125 seeds for prostate brachytherapy based on two-view analysis of pelvic radiographs. / Kawata, Hidemichi; Arimura, Hidetaka; Suefuji, Hiroaki; Ohkura, Sunao; Saida, Yoshifumi; Nashiki, Kazutaka; Hayashida, Kazuya; Kawahara, Tomomi; Ohishi, Ayumu; Hayabuchi, Naofumi.

In: Journal of radiation research, Vol. 53, No. 5, 01.01.2012, p. 742-752.

Research output: Contribution to journalArticle

Kawata, H, Arimura, H, Suefuji, H, Ohkura, S, Saida, Y, Nashiki, K, Hayashida, K, Kawahara, T, Ohishi, A & Hayabuchi, N 2012, 'Automated estimation of number of implanted iodine-125 seeds for prostate brachytherapy based on two-view analysis of pelvic radiographs.', Journal of radiation research, vol. 53, no. 5, pp. 742-752. https://doi.org/10.1093/jrr/rrs018
Kawata, Hidemichi ; Arimura, Hidetaka ; Suefuji, Hiroaki ; Ohkura, Sunao ; Saida, Yoshifumi ; Nashiki, Kazutaka ; Hayashida, Kazuya ; Kawahara, Tomomi ; Ohishi, Ayumu ; Hayabuchi, Naofumi. / Automated estimation of number of implanted iodine-125 seeds for prostate brachytherapy based on two-view analysis of pelvic radiographs. In: Journal of radiation research. 2012 ; Vol. 53, No. 5. pp. 742-752.
@article{46a24c8234e448959c75fdfe257075ef,
title = "Automated estimation of number of implanted iodine-125 seeds for prostate brachytherapy based on two-view analysis of pelvic radiographs.",
abstract = "Digital pelvic radiographs are used to identify the locations of implanted iodine-125 seeds and their numbers after insertion. However, it is difficult and laborious to visually identify and count all implanted seeds on the pelvic radiographs within a short time. Therefore, our purpose in this research was to develop an automated method for estimation of the number of implanted seeds based on two-view analysis of pelvic radiographs. First, the images of the seed candidates on the pelvic image were enhanced using a difference of Gaussian filter, and were identified by binarizing the enhanced image with a threshold value determined by multiple-gray level thresholding. Second, a simple rule-base method using ten image features was applied for false positive removal. Third, the candidates for the likely number of a multiply overlapping seed region, which may include one or more seeds, were estimated by a seed area histogram analysis and calculation of the probability of the likely number of overlapping seeds. As a result, the proposed method detected 99.9{\%} of implanted seeds with 0.71 false positives per image on average in a test for training cases, and 99.2{\%} with 0.32 false positives in a validation test. Moreover, the number of implanted seeds was estimated correctly at an overall recognition rate of 100{\%} in the validation test using the proposed method. Therefore, the verification time for the number of implanted seeds could be reduced by the provision of several candidates for the likely number of seeds.",
author = "Hidemichi Kawata and Hidetaka Arimura and Hiroaki Suefuji and Sunao Ohkura and Yoshifumi Saida and Kazutaka Nashiki and Kazuya Hayashida and Tomomi Kawahara and Ayumu Ohishi and Naofumi Hayabuchi",
year = "2012",
month = "1",
day = "1",
doi = "10.1093/jrr/rrs018",
language = "English",
volume = "53",
pages = "742--752",
journal = "Journal of Radiation Research",
issn = "0449-3060",
publisher = "Japan Radiation Research Society",
number = "5",

}

TY - JOUR

T1 - Automated estimation of number of implanted iodine-125 seeds for prostate brachytherapy based on two-view analysis of pelvic radiographs.

AU - Kawata, Hidemichi

AU - Arimura, Hidetaka

AU - Suefuji, Hiroaki

AU - Ohkura, Sunao

AU - Saida, Yoshifumi

AU - Nashiki, Kazutaka

AU - Hayashida, Kazuya

AU - Kawahara, Tomomi

AU - Ohishi, Ayumu

AU - Hayabuchi, Naofumi

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Digital pelvic radiographs are used to identify the locations of implanted iodine-125 seeds and their numbers after insertion. However, it is difficult and laborious to visually identify and count all implanted seeds on the pelvic radiographs within a short time. Therefore, our purpose in this research was to develop an automated method for estimation of the number of implanted seeds based on two-view analysis of pelvic radiographs. First, the images of the seed candidates on the pelvic image were enhanced using a difference of Gaussian filter, and were identified by binarizing the enhanced image with a threshold value determined by multiple-gray level thresholding. Second, a simple rule-base method using ten image features was applied for false positive removal. Third, the candidates for the likely number of a multiply overlapping seed region, which may include one or more seeds, were estimated by a seed area histogram analysis and calculation of the probability of the likely number of overlapping seeds. As a result, the proposed method detected 99.9% of implanted seeds with 0.71 false positives per image on average in a test for training cases, and 99.2% with 0.32 false positives in a validation test. Moreover, the number of implanted seeds was estimated correctly at an overall recognition rate of 100% in the validation test using the proposed method. Therefore, the verification time for the number of implanted seeds could be reduced by the provision of several candidates for the likely number of seeds.

AB - Digital pelvic radiographs are used to identify the locations of implanted iodine-125 seeds and their numbers after insertion. However, it is difficult and laborious to visually identify and count all implanted seeds on the pelvic radiographs within a short time. Therefore, our purpose in this research was to develop an automated method for estimation of the number of implanted seeds based on two-view analysis of pelvic radiographs. First, the images of the seed candidates on the pelvic image were enhanced using a difference of Gaussian filter, and were identified by binarizing the enhanced image with a threshold value determined by multiple-gray level thresholding. Second, a simple rule-base method using ten image features was applied for false positive removal. Third, the candidates for the likely number of a multiply overlapping seed region, which may include one or more seeds, were estimated by a seed area histogram analysis and calculation of the probability of the likely number of overlapping seeds. As a result, the proposed method detected 99.9% of implanted seeds with 0.71 false positives per image on average in a test for training cases, and 99.2% with 0.32 false positives in a validation test. Moreover, the number of implanted seeds was estimated correctly at an overall recognition rate of 100% in the validation test using the proposed method. Therefore, the verification time for the number of implanted seeds could be reduced by the provision of several candidates for the likely number of seeds.

UR - http://www.scopus.com/inward/record.url?scp=84872806121&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872806121&partnerID=8YFLogxK

U2 - 10.1093/jrr/rrs018

DO - 10.1093/jrr/rrs018

M3 - Article

VL - 53

SP - 742

EP - 752

JO - Journal of Radiation Research

JF - Journal of Radiation Research

SN - 0449-3060

IS - 5

ER -