Certain investigations on performance improvement techniques for polycystic ovary syndrome with follicle identification in the ovary

Abstract

newline The advent of digital cameras and diverse image capturing methods has opened the doors for researchers to create automated algorithms for disease detection, specifically within the healthcare industry. These algorithms assist practitioners in screening, predicting, and diagnosing human diseases at earlier stages, thereby facilitating timely interventions. The effectiveness of diagnosis and treatment greatly depends on early and consistent detection through screening. However, the increasing population and shortage of expert gynaecologist have led to researchers to develop automated systems for screening and detecting ovarian cyst among women, eliminating human error and subjectivity associated with expert examination. A growing number of research scholars in this field are striving to enhance the effectiveness of these systems by improving their performance. Nevertheless, a literature review indicates that there is still ample opportunity to develop artificial intelligencebased algorithms and classifiers for more accurate diagnosis of cyst identification in the women ovary. Therefore, an endeavour has been undertaken to create an automated method that classifies polycystic ovary syndrome with improved performance.