Detection of Polycystic Ovary Syndrome from Ultrasound Images Using SIFT Descriptors

Polycystic Ovary Syndrome (PCOS) is a reproductive metabolic complexity described by the quantity of follicles present in the ovary. Ultrasound imaging of the ovary contains basic data about the size, number of follicles and its position. Continuously, the discovery of PCOS is a troublesome undertaking for radiologists because of the different sizes of follicles and is very associated with veins and tissues. In this paper, ultrasound images of ovary are analyzed using various image processing techniques. For preprocessing different standard methodologies are applied on ovary images to enhance the quality of the image. Canny edge detection method is used to detect the edges of the follicles from the ultrasound image. Feature Extraction is an important phase in detection of objects. A robust feature descriptor identification algorithm called Scale-Invariant Feature Transform is adopted in this work to detect the presence of the syndrome from the image. Support Vector Machine is deployed for training and classification of the data. The proposed system outperforms other state-of-art methods and proved its efficacy.