Identification of Polycystic Ovary Syndrome in ultrasound images of Ovaries using Distinct Threshold based Image Segmentation

Polycystic Ovary Syndrome (PCOS) is a common hormonal disorder among women of reproductive age and it can lead to infertility, metabolic disorders and other health problems. Ultrasound is an important tool for the diagnosis of PCOS. In medical image processing, the threshold segmentation plays a critical role in the identification of PCOS by isolating and accurately analyzing the cysts. In this paper, the PCOMorphology is extracted from the ultrasound images using three threshold-based segmentation algorithms: Adaptive Mean Threshold, Adaptive Gaussian Threshold, and Otsu Threshold. The performance of these algorithms is evaluated based on several metrics such as accuracy, sensitivity, specificity, and F1 score. The results show that the Otsu Threshold algorithm provides the best performance in terms of follicle detection and accuracy, followed by Adaptive Gaussian Threshold and Adaptive Mean Threshold. In conclusion, the comparison of these three algorithms shows that Otsu Threshold algorithm is the most suitable for the identification of PCOS using ultrasound images. The results of this study have important implications for the diagnosis of PCOS and further research is needed to improve the accuracy of the diagnosis. The proposed algorithms can be integrated into the existing clinical diagnosis systems to improve the accuracy and efficiency of the diagnosis process. This study provides a promising direction for future research in the field of medical image processing and PCOS diagnosis