Automatic cystocele severity grading in transperineal ultrasound by random forest regression

Dong Ni, Xing Ji, Min Wu, Wenlei Wang, Xiaoshuang Deng, Zhongyi Hu, Tianfu Wang, Dinggang Shen, Jie Zhi Cheng, Huifang Wang

Research output: Contribution to journalArticle

  • 3 Citations

Abstract

Cystocele is a woman disease that bladder herniates into vagina. Women with cystocele may have problem in urinating and higher risk of bladder infection. The treatment of cystocele highly depends on the severity. The cystocele severity is usually evaluated with the manual transperineal ultrasound measurement for the maximal distance between the bladder and the lower tip of symphysis pubis in the Valsalva maneuver. To improve the efficiency of the measurement, we propose a fully automatic scheme that can measure the distance between the two anatomic structures in each ultrasound image. The whole measurement scheme is realized with a two-phase random forest regression to infer the locations of the two structures in the images for the support of distance measurement. The experimental results suggest automatic distance measurements and the final grading by our random forest regression method are comparable to the measurements and grading scores from three medical doctors, and thus corroborate the efficacy of our method.

LanguageEnglish (US)
Pages551-560
Number of pages10
JournalPattern Recognition
Volume63
DOIs
StatePublished - Mar 1 2017

Fingerprint

Ultrasonics
Distance measurement

Keywords

  • Auto-context
  • Bladder boundary segmentation
  • Cystocele grading
  • Regression forest
  • Symphysis pubis detection

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Ni, D., Ji, X., Wu, M., Wang, W., Deng, X., Hu, Z., ... Wang, H. (2017). Automatic cystocele severity grading in transperineal ultrasound by random forest regression. Pattern Recognition, 63, 551-560. DOI: 10.1016/j.patcog.2016.09.033

Automatic cystocele severity grading in transperineal ultrasound by random forest regression. / Ni, Dong; Ji, Xing; Wu, Min; Wang, Wenlei; Deng, Xiaoshuang; Hu, Zhongyi; Wang, Tianfu; Shen, Dinggang; Cheng, Jie Zhi; Wang, Huifang.

In: Pattern Recognition, Vol. 63, 01.03.2017, p. 551-560.

Research output: Contribution to journalArticle

Ni, D, Ji, X, Wu, M, Wang, W, Deng, X, Hu, Z, Wang, T, Shen, D, Cheng, JZ & Wang, H 2017, 'Automatic cystocele severity grading in transperineal ultrasound by random forest regression' Pattern Recognition, vol 63, pp. 551-560. DOI: 10.1016/j.patcog.2016.09.033
Ni D, Ji X, Wu M, Wang W, Deng X, Hu Z et al. Automatic cystocele severity grading in transperineal ultrasound by random forest regression. Pattern Recognition. 2017 Mar 1;63:551-560. Available from, DOI: 10.1016/j.patcog.2016.09.033
Ni, Dong ; Ji, Xing ; Wu, Min ; Wang, Wenlei ; Deng, Xiaoshuang ; Hu, Zhongyi ; Wang, Tianfu ; Shen, Dinggang ; Cheng, Jie Zhi ; Wang, Huifang. / Automatic cystocele severity grading in transperineal ultrasound by random forest regression. In: Pattern Recognition. 2017 ; Vol. 63. pp. 551-560
@article{1d2659612fd941e29988f44836361416,
title = "Automatic cystocele severity grading in transperineal ultrasound by random forest regression",
abstract = "Cystocele is a woman disease that bladder herniates into vagina. Women with cystocele may have problem in urinating and higher risk of bladder infection. The treatment of cystocele highly depends on the severity. The cystocele severity is usually evaluated with the manual transperineal ultrasound measurement for the maximal distance between the bladder and the lower tip of symphysis pubis in the Valsalva maneuver. To improve the efficiency of the measurement, we propose a fully automatic scheme that can measure the distance between the two anatomic structures in each ultrasound image. The whole measurement scheme is realized with a two-phase random forest regression to infer the locations of the two structures in the images for the support of distance measurement. The experimental results suggest automatic distance measurements and the final grading by our random forest regression method are comparable to the measurements and grading scores from three medical doctors, and thus corroborate the efficacy of our method.",
keywords = "Auto-context, Bladder boundary segmentation, Cystocele grading, Regression forest, Symphysis pubis detection",
author = "Dong Ni and Xing Ji and Min Wu and Wenlei Wang and Xiaoshuang Deng and Zhongyi Hu and Tianfu Wang and Dinggang Shen and Cheng, {Jie Zhi} and Huifang Wang",
year = "2017",
month = "3",
day = "1",
doi = "10.1016/j.patcog.2016.09.033",
language = "English (US)",
volume = "63",
pages = "551--560",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Automatic cystocele severity grading in transperineal ultrasound by random forest regression

AU - Ni,Dong

AU - Ji,Xing

AU - Wu,Min

AU - Wang,Wenlei

AU - Deng,Xiaoshuang

AU - Hu,Zhongyi

AU - Wang,Tianfu

AU - Shen,Dinggang

AU - Cheng,Jie Zhi

AU - Wang,Huifang

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Cystocele is a woman disease that bladder herniates into vagina. Women with cystocele may have problem in urinating and higher risk of bladder infection. The treatment of cystocele highly depends on the severity. The cystocele severity is usually evaluated with the manual transperineal ultrasound measurement for the maximal distance between the bladder and the lower tip of symphysis pubis in the Valsalva maneuver. To improve the efficiency of the measurement, we propose a fully automatic scheme that can measure the distance between the two anatomic structures in each ultrasound image. The whole measurement scheme is realized with a two-phase random forest regression to infer the locations of the two structures in the images for the support of distance measurement. The experimental results suggest automatic distance measurements and the final grading by our random forest regression method are comparable to the measurements and grading scores from three medical doctors, and thus corroborate the efficacy of our method.

AB - Cystocele is a woman disease that bladder herniates into vagina. Women with cystocele may have problem in urinating and higher risk of bladder infection. The treatment of cystocele highly depends on the severity. The cystocele severity is usually evaluated with the manual transperineal ultrasound measurement for the maximal distance between the bladder and the lower tip of symphysis pubis in the Valsalva maneuver. To improve the efficiency of the measurement, we propose a fully automatic scheme that can measure the distance between the two anatomic structures in each ultrasound image. The whole measurement scheme is realized with a two-phase random forest regression to infer the locations of the two structures in the images for the support of distance measurement. The experimental results suggest automatic distance measurements and the final grading by our random forest regression method are comparable to the measurements and grading scores from three medical doctors, and thus corroborate the efficacy of our method.

KW - Auto-context

KW - Bladder boundary segmentation

KW - Cystocele grading

KW - Regression forest

KW - Symphysis pubis detection

UR - http://www.scopus.com/inward/record.url?scp=84998979411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84998979411&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2016.09.033

DO - 10.1016/j.patcog.2016.09.033

M3 - Article

VL - 63

SP - 551

EP - 560

JO - Pattern Recognition

T2 - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -