An Analysis For Early Diagnosis To Detect Ovarian Cancer

Abstract

Ovarian cancer stands as the primary cause of mortality among gynecological cancers, creating an urgent need for innovative therapies. Despite the established correlation between the presence of tumor-infiltrating lymphocytes and improved prognosis, the integration of immunotherapy into the ovarian cancer treatment arsenal has not yet occurred. Over the past decades, extensive research has been dedicated to identifying early signs of ovarian cancer. Recognized as the "silent killer," ovarian cancer often remains asymptomatic in its early stages, leading to late-stage discoveries and poor prognosis. Early detection is pivotal for timely intervention based on symptomatic manifestations. Various categorization systems have been employed for ovarian tumor diagnosis, encompassing non-molecular factors such as tumor tissue, clinical stage, and pathological characteristics. These factors contribute to a comprehensive understanding of the intricate nature of cancer, guiding the development of effective therapeutic approaches. This review paper briefly outlines the preprocessing, feature extraction, and classification methodologies employed in the analysis of ovarian cancer across various studies from 2018 to 2023, encompassing several research papers.