A Broad Analysis of Ultrasound Imaging for Ovarian Cyst Detection using Advanced Artificial Intelligence Techniques

When it comes to the endocrine and reproductive systems of females, the ovaries are crucial. They emit vital hormones which are necessary for proper development of female and increase healthy fertility. As a gynecological cancer, ovarian cancer (OC) ranks first in terms of mortality rate and is the seventh most mutual cancer in women overall. It is also the eighth most common cancer killer in the world. Extra fluid-filled sacs, known as cysts, can develop in or on the ovaries on occasion. There are a lot of benign ovarian cysts. But a small percentage of these are cancerous, therefore early detection and treatment are crucial. Nearly 60% of OC cases are identified after they have progressed to a more advanced stage, even though modern technology has enabled more precise laboratory and radiographic diagnostic testing. The key prognostic factor is still early diagnosis because of the significant death rate in advanced stages of OC. The use of ultrasound, also known as sonography, has been a game-changer for the way doctors diagnose, care for, and treat their patients. Highlighting the significance of sonographic evaluation, the critical role of the operator's experience, potential visibility limits, the status and requirement of quality assurance protocols that health workers must shadow, and finally cumulative the positive predictive value are the main aims of this work, which primarily focuses on sonographic tasks in ovarian cancer screening. Furthermore, this study also reviews the topic of cyst detection using Deep Learning, an AI-based system. An overview of the current models is provided, followed by a discussion of potential future studies for detection.