Follicle Segmentation Using K-Means Clustering from Ultrasound Image of Ovary
Detection of number, shape and size of follicles in the ovary can play an important role in the diagnosis and monitoring of different diseases like infertility, PCOS (Polycystic Ovarian Syndrome), ovarian cancer, etc. Nowadays the identification of these
- PDF / 528,775 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 78 Downloads / 170 Views
Abstract Detection of number, shape and size of follicles in the ovary can play an important role in the diagnosis and monitoring of different diseases like infertility, PCOS (Polycystic Ovarian Syndrome), ovarian cancer, etc. Nowadays the identification of these characteristics of follicles is done manually by radiologists and doctors from the Ultrasound Images of ovaries. Sometimes manual analysis can be tedious and thus may lead to erroneous results. In this paper, a method is proposed for automatic segmentation of follicles from Ultrasound Images using the K-means clustering technique. Keywords Follicle detection · Ultrasound images · Ovary · Segmentation · K-means clustering
1 Introduction For diagnosis of different diseases like PCOS (Polycystic Ovarian Syndrome), ovarian cancer, infertility, etc., in woman’s body, it is important to determine the ovarian status. Ovary is the reproductive organ of female body. Ova or eggs are produced in the ovary. Inside the ovary, there are some spherical fluid-filled structures which are called follicles. The number of follicles present in the ovary plays an important role in these diagnosis processes [1]. Thus, ovary is frequently scanned by ultrasound A. Mandal · D. Saha (B) · M. Sarkar Department of Computer Science and Application, University of North Bengal, Siliguri 734013, West Bengal, India e-mail: [email protected] A. Mandal e-mail: [email protected]; [email protected] M. Sarkar e-mail: [email protected] D. Saha Department of Computer Science, University of Gour Banga, Malda 732103, West Bengal, India © Springer Nature Singapore Pte Ltd. 2021 D. Bhattacharjee et al. (eds.), Proceedings of International Conference on Frontiers in Computing and Systems, Advances in Intelligent Systems and Computing 1255, https://doi.org/10.1007/978-981-15-7834-2_51
545
546
A. Mandal et al.
imaging. Nowadays in most of the cases the analysis of these Ultrasound Images are done by medical experts manually, which is sometimes a tedious and error-prone job. Thus, there is a need of making the process of detecting the number of follicles from ultrasound images automatically, so that the monotonous work of medical experts can be reduced, as well as the detection accuracy can be improved. Many researchers have tried different approaches to automatically segment follicles from ultrasound images such as active contour method [2], edge-based method [3], object growing method [4], morphology [5], etc. Still, there is a lot of scope to explore in this field of detection of follicles automatically from ultrasound images of ovaries. Thus, in this paper, another method is proposed in this direction mainly based on the clustering technique called K-means clustering. Image segmentation can be described as the method of dividing a digital image into different regions such that each region contains pixels which has similar attributes. The resulting images obtained from image segmentation are more meaningful and can be analyzed easily to reach to some decisions. Thus, it can be
Data Loading...
