AI Based System to Detect Uterine Cancer using Ultrasound Images
S. Uma Maheswari, M. Ponnibala, Shashank Govindaraj, S. Priyadharshini, T. Shobika, D. Swetha · 2024
Uterine cancers are the most common gynaecologic malignancies in developed countries and the second most common in developing countries. The vast majority of women with endometrial cancer are diagnosed with early stage tumors that are associated with a good prognosis. However, a subgroup of women with early stage uterine cancer face recurrence and are at an increased risk of death. This poses a significant global health challenge, affecting approximately 382,000 women worldwide each year and contributing to a concerning mortality rate of approximately 90,000 annually. By addressing the global challenge of uterine cancer detection, here this project not only contributes to advancing healthcare technology but also holds the promise of saving lives on a global scale. This project addresses the urgent need for improved uterine cancer detection by introducing a novel machine learning-based system for the analysis of ultrasound images. This system leverages state-of-the-art deep learning techniques and image processing methods to automatically identify suspicious regions within ultrasound images. By extracting relevant features and patterns, the model distinguishes between normal and cancerous tissue, aiding in the early diagnosis and timely intervention. The outcomes of the project hold the promise of improving the early detection of uterine cancer and classifying it as benign, malignant and sub classified the benign as fibroid, water molecules, normal cells and malignant with their substages based on their features, leading to more effective treatments and ultimately saving lives. Furthermore, the methodology developed can serve as a foundation for similar applications in medical imaging and computer-aided diagnosis, advancing the field of healthcare technology.