Follicle Detection on the USG Images to Support Determination of Polycystic Ovary Syndrome

3rd International Conference on Science & Engineering in Mathematics, Chemistry and Physics 2015

数学;化学;物理学

Adiwijaya^1 ; Purnama, B.^1 ; Hasyim, A.^1 ; Septiani, M.D.^1 ; Wisesty, U.N.^1 ; Astuti, W.^1

School of Computing, Telkom University, Bandung, Indonesia^1

关键词: Endocrine disorders;    Euclidean distance;    Homogeneous regions;    Polycystic ovary syndromes;    Region growing;    Reproducibilities;    Reproductive cycle;    Stereology;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/622/1/012027/pdf
DOI  :  10.1088/1742-6596/622/1/012027

来源: IOP

【 摘 要 】

Polycystic Ovary Syndrome(PCOS) is the most common endocrine disorders affected to female in their reproductive cycle. This has gained the attention from married couple which affected by infertility. One of the diagnostic criteria considereded by the doctor is analysing manually the ovary USG image to detect the number and size of ovary's follicle. This analysis may affect low varibilites, reproducibility, and efficiency. To overcome this problems. automatic scheme is suggested to detect the follicle on USG image in supporting PCOS diagnosis. The first scheme is determining the initial homogeneous region which will be segmented into real follicle form The next scheme is selecting the appropriate regions to follicle criteria. then measuring the segmented region attribute as the follicle. The measurement remains the number and size that aimed at categorizing the image into the PCOS or non-PCOS. The method used is region growing which includes region-based and seed-based. To measure the follicle diameter. there will be the different method including stereology and euclidean distance. The most optimum system plan to detect PCO is by using region growing and by using euclidean distance on quantification of follicle.