Medical image segmentation with transform and moment based features and incremental supervised neural network

被引：28

作者：

Iscan, Zafer ^{[1
]}

Yuksel, Ayhan ^{[1
]}

Dokur, Zuemray ^{[1
]}

Korurek, Mehmet ^{[1
]}

Olmez, Tamer ^{[1
]}

机构：

[1] Istanbul Tech Univ, Dept Elect & Commun Engn, TR-34469 Istanbul, Turkey

来源：

DIGITAL SIGNAL PROCESSING | 2009年 / 19卷 / 05期

关键词：

Medical image segmentation; Incremental neural networks; Supervised learning; Statistical moments; Continuous wavelet transform; FEATURE-EXTRACTION; WAVELET TRANSFORM; CLASSIFICATION; SOUNDS; SYSTEM;

D O I：

10.1016/j.dsp.2009.03.001

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this study, a novel incremental supervised neural network (ISNN) is proposed for the segmentation of medical images. Performance of the ISNN is investigated for tissue segmentation in medical images obtained from various imaging modalities. Two feature extraction methods based on transform and moments are comparatively investigated to segment the tissues in medical images. Two-dimensional (2D) continuous wavelet transform (CWT) and the moments of the gray-level histogram (MGH) are computed in order to form the feature vectors of ultrasound (US) bladder and phantom images, X-ray computerized tomography (CT) and magnetic resonance (MR) head images. In the 2D-CWT method, feature vectors are formed by the intensity of one pixel of each wavelet-plane of different energy bands. The MGH represents the tissues within the sub-windows by using the spatial variation of image intensities. In this study, the ISNN and Grow and Learn (GAL) network are employed for the segmentation task. It is observed that the ISNN has significantly eliminated the disadvantages of the GAL network in the segmentation of the medical images. (C) 2009 Elsevier Inc. All rights reserved.

引用

页码：890 / 901

页数：12

共 25 条

[1]

ALPAYDIN E, 1990, THESIS ECOLE POLYTEC

[2]

[Anonymous], BIOMED SIGNAL PROCES

[3] IMAGE CHARACTERIZATIONS BASED ON JOINT GRAY LEVEL RUN LENGTH DISTRIBUTIONS [J].

DASARATHY, BV ;

HOLDER, EB .

PATTERN RECOGNITION LETTERS, 1991, 12 (08) :497-502

[4] Classification of respiratory sounds by using an artificial neural network [J].

Dokur, Z ;

Ölmez, T .

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2003, 17 (04) :567-580

[5]

DOKUR Z, 2000, IEEE EMBS AS PAC C B

[6]

Dokur Z, 2006, LECT NOTES ARTIF INT, V4293, P800

[7] Image processing with neural networks - a review [J].

Egmont-Petersen, M ;

de Ridder, D ;

Handels, H .

PATTERN RECOGNITION, 2002, 35 (10) :2279-2301

[8] Typing of prostate tissue by ultrasonic spectrum analysis [J].

Feleppa, EJ ;

Kalisz, A ;

SokilMelgar, JB ;

Lizzi, FL ;

Liu, T ;

Rosado, AL ;

Shao, MC ;

Fair, WR ;

Wang, Y ;

Cookson, MS ;

Reuter, VE ;

Heston, WDW .

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 1996, 43 (04) :609-619

[9] Features and classification methods to locate deciduous trees in images [J].

Haering, N ;

Lobo, ND .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1999, 75 (1-2) :133-149

[10]

Iscan Z, 2006, NEURAL INF PROCESS L, V10, P183

← 1 2 3 →