Rapid and Automated Extraction of the Fourth Ventricle from MR Images

Yan Xia; Aamer Aziz; QingMao Hu; Wieslaw L. Nowinski

doi:10.1007/b93811

Rapid and Automated Extraction of the Fourth Ventricle from MR Images

Yan Xia, Aamer Aziz, QingMao Hu, Wieslaw L. Nowinski

Science and Health

Research output: Book chapter/Published conference paper › Conference paper › peer-review

1 Citation (Scopus)

Abstract

This paper describes a rapid and automated method that extracts the fourth ventricle from MR brain images in normal and pathological subjects. Anatomical knowledge of fourth ventricle has been incorporated into the method to define a region of interest (ROI), determine intensity thresholds in the histogram of ROI, locate the starting point for the 3D region growing, and extract all parts of the fourth ventricle and aqueduct (even if they are disconnected on images as well as to avoid inclusion of non-ventricular cerebrospinal fluid regions). The method was validated qualitatively on 30 MRI studies with variable parameters. The best overlap metric between a radiology expert and the method was 0.9988 and the worst 0.9621 on 10 quantitative studies. The mean and standard deviation of overlap metric were 0.9806 and 0.0105.

Original language	English
Title of host publication	International Conference, Medical Image Computing and Computer-Assisted Intervention (MICCAI)
Place of Publication	Berlin / Heidelberg
Publisher	Springer
Pages	635-643
Number of pages	9
Volume	2879/2003
DOIs	https://doi.org/10.1007/b93811
Publication status	Published - 2003
Event	MICCAI 2003: 6th International Conference - Montreal, Canada, Canada Duration: 15 Nov 2003 → 18 Nov 2003

Conference

Conference	MICCAI 2003: 6th International Conference
Country/Territory	Canada
Period	15/11/03 → 18/11/03

Access to Document

10.1007/b93811

Cite this

@inproceedings{14a92d2fac7547c9b0628ecda33caa3e,

title = "Rapid and Automated Extraction of the Fourth Ventricle from MR Images",

abstract = "This paper describes a rapid and automated method that extracts the fourth ventricle from MR brain images in normal and pathological subjects. Anatomical knowledge of fourth ventricle has been incorporated into the method to define a region of interest (ROI), determine intensity thresholds in the histogram of ROI, locate the starting point for the 3D region growing, and extract all parts of the fourth ventricle and aqueduct (even if they are disconnected on images as well as to avoid inclusion of non-ventricular cerebrospinal fluid regions). The method was validated qualitatively on 30 MRI studies with variable parameters. The best overlap metric between a radiology expert and the method was 0.9988 and the worst 0.9621 on 10 quantitative studies. The mean and standard deviation of overlap metric were 0.9806 and 0.0105.",

author = "Yan Xia and Aamer Aziz and QingMao Hu and Nowinski, {Wieslaw L.}",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = Berlin / Heidelberg: Springer, 2003. editor/s (773b) = Randy E Ellis , Terry M Peters ,; Event dates (773o) = 15-18 November 2003; Parent title (773t) = International Conference, Medical Image Computing and Computer-Assisted Intervention (MICCAI). ISSNs: 0302-9743; ; MICCAI 2003: 6th International Conference ; Conference date: 15-11-2003 Through 18-11-2003",

year = "2003",

doi = "10.1007/b93811",

language = "English",

volume = "2879/2003",

pages = "635--643",

booktitle = "International Conference, Medical Image Computing and Computer-Assisted Intervention (MICCAI)",

publisher = "Springer",

address = "United States",

}

TY - GEN

T1 - Rapid and Automated Extraction of the Fourth Ventricle from MR Images

AU - Xia, Yan

AU - Aziz, Aamer

AU - Hu, QingMao

AU - Nowinski, Wieslaw L.

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = Berlin / Heidelberg: Springer, 2003. editor/s (773b) = Randy E Ellis , Terry M Peters ,; Event dates (773o) = 15-18 November 2003; Parent title (773t) = International Conference, Medical Image Computing and Computer-Assisted Intervention (MICCAI). ISSNs: 0302-9743;

PY - 2003

Y1 - 2003

N2 - This paper describes a rapid and automated method that extracts the fourth ventricle from MR brain images in normal and pathological subjects. Anatomical knowledge of fourth ventricle has been incorporated into the method to define a region of interest (ROI), determine intensity thresholds in the histogram of ROI, locate the starting point for the 3D region growing, and extract all parts of the fourth ventricle and aqueduct (even if they are disconnected on images as well as to avoid inclusion of non-ventricular cerebrospinal fluid regions). The method was validated qualitatively on 30 MRI studies with variable parameters. The best overlap metric between a radiology expert and the method was 0.9988 and the worst 0.9621 on 10 quantitative studies. The mean and standard deviation of overlap metric were 0.9806 and 0.0105.

AB - This paper describes a rapid and automated method that extracts the fourth ventricle from MR brain images in normal and pathological subjects. Anatomical knowledge of fourth ventricle has been incorporated into the method to define a region of interest (ROI), determine intensity thresholds in the histogram of ROI, locate the starting point for the 3D region growing, and extract all parts of the fourth ventricle and aqueduct (even if they are disconnected on images as well as to avoid inclusion of non-ventricular cerebrospinal fluid regions). The method was validated qualitatively on 30 MRI studies with variable parameters. The best overlap metric between a radiology expert and the method was 0.9988 and the worst 0.9621 on 10 quantitative studies. The mean and standard deviation of overlap metric were 0.9806 and 0.0105.

U2 - 10.1007/b93811

DO - 10.1007/b93811

M3 - Conference paper

VL - 2879/2003

SP - 635

EP - 643

BT - International Conference, Medical Image Computing and Computer-Assisted Intervention (MICCAI)

PB - Springer

CY - Berlin / Heidelberg

T2 - MICCAI 2003: 6th International Conference

Y2 - 15 November 2003 through 18 November 2003

ER -

Rapid and Automated Extraction of the Fourth Ventricle from MR Images

Abstract

Conference

Access to Document

Fingerprint

Cite this