Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients

Yi Shen; Xiaoqiu Dong; Chunhui Zhu; Qiang Wang; Jiasheng Hao; Naizhang Feng

doi:10.1109/IMTC.2009.5168570

Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients

Yi Shen^*
, Xiaoqiu Dong
, Chunhui Zhu
, Qiang Wang
, Jiasheng Hao
, Naizhang Feng

^*Corresponding author for this work

School of Astronautics

Harbin Institute of Technology
Harbin Medical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

For 3D medical images with strong similarities of interfacial gradients, a method is presented to bring local regional characteristics of segmented sections into adjacent sections waiting for segmentation and to guide the contour curves of the later to converge to actual boundary. The proposed method improves the stopping criterion of curve evolution through introduction of adjacent layer's prior information into edge detection function, so that introduces similarities of interfacial gradients into geodesic geometric flow as prior information to modify the leakage phenomena that exists in geometric active contour model when disconnected or weak edges appear in layers and improves the precision and stability of segmentation for 3D medical images.

Original language	English
Title of host publication	2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009
Publisher	IEEE Computer Society
Pages	856-859
Number of pages	4
ISBN (Print)	9781424433537
DOIs	https://doi.org/10.1109/IMTC.2009.5168570
State	Published - 2009
Event	2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009 - Singapore, Singapore Duration: 5 May 2009 → 7 May 2009

Publication series

Name	2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009

Conference

Conference	2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009
Country/Territory	Singapore
City	Singapore
Period	5/05/09 → 7/05/09

Keywords

2D image sequences
3D image
Geometric flow
Medical image segmentation
Prior information

Access to Document

10.1109/IMTC.2009.5168570

Cite this

Shen, Y., Dong, X., Zhu, C., Wang, Q., Hao, J., & Feng, N. (2009). Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients. In 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009 (pp. 856-859). Article 5168570 (2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009). IEEE Computer Society. https://doi.org/10.1109/IMTC.2009.5168570

@inproceedings{bb48b7a9e690411fb158e193d3b1cce2,

title = "Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients",

abstract = "For 3D medical images with strong similarities of interfacial gradients, a method is presented to bring local regional characteristics of segmented sections into adjacent sections waiting for segmentation and to guide the contour curves of the later to converge to actual boundary. The proposed method improves the stopping criterion of curve evolution through introduction of adjacent layer's prior information into edge detection function, so that introduces similarities of interfacial gradients into geodesic geometric flow as prior information to modify the leakage phenomena that exists in geometric active contour model when disconnected or weak edges appear in layers and improves the precision and stability of segmentation for 3D medical images.",

keywords = "2D image sequences, 3D image, Geometric flow, Medical image segmentation, Prior information",

author = "Yi Shen and Xiaoqiu Dong and Chunhui Zhu and Qiang Wang and Jiasheng Hao and Naizhang Feng",

year = "2009",

doi = "10.1109/IMTC.2009.5168570",

language = "英语",

isbn = "9781424433537",

series = "2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009",

publisher = "IEEE Computer Society",

pages = "856--859",

booktitle = "2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009",

address = "美国",

note = "2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009 ; Conference date: 05-05-2009 Through 07-05-2009",

}

Shen, Y, Dong, X, Zhu, C, Wang, Q, Hao, J & Feng, N 2009, Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients. in 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009., 5168570, 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009, IEEE Computer Society, pp. 856-859, 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009, Singapore, Singapore, 5/05/09. https://doi.org/10.1109/IMTC.2009.5168570

Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients. / Shen, Yi; Dong, Xiaoqiu; Zhu, Chunhui et al.
2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009. IEEE Computer Society, 2009. p. 856-859 5168570 (2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients

AU - Shen, Yi

AU - Dong, Xiaoqiu

AU - Zhu, Chunhui

AU - Wang, Qiang

AU - Hao, Jiasheng

AU - Feng, Naizhang

PY - 2009

Y1 - 2009

N2 - For 3D medical images with strong similarities of interfacial gradients, a method is presented to bring local regional characteristics of segmented sections into adjacent sections waiting for segmentation and to guide the contour curves of the later to converge to actual boundary. The proposed method improves the stopping criterion of curve evolution through introduction of adjacent layer's prior information into edge detection function, so that introduces similarities of interfacial gradients into geodesic geometric flow as prior information to modify the leakage phenomena that exists in geometric active contour model when disconnected or weak edges appear in layers and improves the precision and stability of segmentation for 3D medical images.

AB - For 3D medical images with strong similarities of interfacial gradients, a method is presented to bring local regional characteristics of segmented sections into adjacent sections waiting for segmentation and to guide the contour curves of the later to converge to actual boundary. The proposed method improves the stopping criterion of curve evolution through introduction of adjacent layer's prior information into edge detection function, so that introduces similarities of interfacial gradients into geodesic geometric flow as prior information to modify the leakage phenomena that exists in geometric active contour model when disconnected or weak edges appear in layers and improves the precision and stability of segmentation for 3D medical images.

KW - 2D image sequences

KW - 3D image

KW - Geometric flow

KW - Medical image segmentation

KW - Prior information

UR - https://www.scopus.com/pages/publications/70450093630

U2 - 10.1109/IMTC.2009.5168570

DO - 10.1109/IMTC.2009.5168570

M3 - 会议稿件

AN - SCOPUS:70450093630

SN - 9781424433537

T3 - 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009

SP - 856

EP - 859

BT - 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009

PB - IEEE Computer Society

T2 - 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009

Y2 - 5 May 2009 through 7 May 2009

ER -

Shen Y, Dong X, Zhu C, Wang Q, Hao J, Feng N. Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients. In 2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009. IEEE Computer Society. 2009. p. 856-859. 5168570. (2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009). doi: 10.1109/IMTC.2009.5168570

Geodesic geometric flow for medical image segmentation based on similarities of interfacial gradients

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this