论文信息 - Automated ovarian follicle segmentation using region growing

Automated ovarian follicle segmentation using region growing

An improved algorithm for ovarian follicle detection in ultrasound images is presented. This fully automated recognition algorithm is composed of three successive steps. First, the initial homogeneous regions are determined. Then, these initial regions are grown. Growing is controlled by the average grey-level and by a newly introduced weighted gradient of the image. In the last step, the regions that are probably follicles are extracted. The algorithm has been tested on 50 ovarian ultrasound images. The recognition rate of follicles was around 88%.

B. Potocnik | D. Zazula

[1] Damjan Zazula,et al. Cellular automata and follicle recognition problem and possibilities of using cellular automata for image recognition purposes , 1998, Int. J. Medical Informatics.

[2] Milan Sonka,et al. Ovarian ultrasound image analysis: follicle segmentation , 1998, IEEE Transactions on Medical Imaging.

[3] W. Liang,et al. Semiautomated segmentation of ovarian follicular ultrasound images using a knowledge-based algorithm. , 1998, Ultrasound in medicine & biology.

[4] Michael G. Strintzis,et al. Nonlinear ultrasonic image processing based on signal-adaptive filters and self-organizing neural networks , 1994, IEEE Trans. Image Process..

[5] S. Pizer,et al. The Image Processing Handbook , 1994 .

[6] Danilo Korze,et al. Automated Computer-Assisted Detection of Follicles in Ultrasound Images of Ovary , 1997, Proceedings of Computer Based Medical Systems.