Segmentation of ovarian ultrasound images using cellular neural networks

被引：26

作者：

Cigale, B ^{[1
]}

Zazula, D ^{[1
]}

机构：

[1] Univ Maribor, Fac Elect Engn & Comp Sci, SLO-2000 Maribor, Slovenia

来源：

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE | 2004年 / 18卷 / 04期

关键词：

cellular neural networks; ultrasound images; ovarian follicle segmentation; genetic algorithm;

D O I：

10.1142/S0218001404003368

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Segmentation of ovarian ultrasound images using cellular neural networks (CNNs) is studied in this paper. The segmentation method consists of five successive steps where the first four uses CNNs. In the first step, only rough position of follicles is determined. In the second step, the results are improved by expansion of detected follicles. In the third step, previously undetected inexpressive follicles are determined, while the fourth step detects the position of ovary. All results are joined in the fifth step. The templates for CNNs were obtained by applying genetic algorithm. The segmentation method has been tested on 50 ovarian ultrasound images. The recognition rate of follicles was around 60% and misidentification rate was around 30%.

引用

页码：563 / 581

页数：19

共 16 条

[1] The Quickhull algorithm for convex hulls [J].

Barber, CB ;

Dobkin, DP ;

Huhdanpaa, H .

ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 1996, 22 (04) :469-483

[2] CELLULAR NEURAL NETWORKS - THEORY [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272

[3]

CHUA LO, 1998, ANAL INTEGR CIRCUITS, V15

[4]

CIALE B, 2002, P 15 IEEE S COMP BAS, P165

[5]

CIGALE B, 1997, P COMP AID DAT AN ME, P56

[6] GENETIC ALGORITHM FOR CNN TEMPLATE LEARNING [J].

KOZEK, T ;

ROSKA, T ;

CHUA, LO .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1993, 40 (06) :392-402

[7] Ovarian ultrasound image analysis: Follicle segmentation [J].

Krivanek, A ;

Sonka, M .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 1998, 17 (06) :935-944

[8] The XUltra project - Automated analysis of ovarian ultrasound images [J].

Potocnik, B ;

Cigale, B ;

Zazula, D .

PROCEEDINGS OF THE 15TH IEEE SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, 2002, :262-267

[9] Automated analysis of a sequence of ovarian ultrasound images. Part I: segmentation of single 2D images [J].

Potocnik, B ;

Zazula, D .

IMAGE AND VISION COMPUTING, 2002, 20 (03) :217-225

[10] Automated analysis of a sequence of ovarian ultrasound images. Part II: prediction-based object recognition from a sequence of images [J].

Potocnik, B ;

Zazula, D .

IMAGE AND VISION COMPUTING, 2002, 20 (03) :227-235

← 1 2 →