Abstract: Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine disorder affecting many women, characterized by various symptoms and ovarian irregularities. Accurate and timely diagnosis is crucial for appropriate treatment and management. This project proposes an innovative approach to PCOS detection that leverages both manual input data and advanced medical imaging techniques. The primary objective of this project is to develop an automated system for PCOS detection, enhancing diagnostic accuracy and streamlining the process. This approach combines manual input of some key features associated with PCOS, with the use of ultrasound imaging of the ovaries. It takes a patient-centered approach, ensuring that individuals suspected of having PCOS are provided with an accurate and efficient diagnosis. The process begins with the collection and preprocessing of patient data. Manual input data is collected, and based on predefined criteria, a decision is made to proceed with an ultrasound scan. If indicated, high-quality ultrasound images of the ovaries are obtained, which serve as input to a specialized Convolutional Neural Network (CNN). The CNN is trained on a labeled dataset of ultrasound images, enabling it to detect specific patterns associated with PCOS. By analyzing the ultrasound image, the CNN provides an assessment of the likelihood of PCOS.
Keywords: PCOS detection, Manual data analysis [physical symptoms], Image based analysis[ultrasound Image], Random Forest, Convolutional Neural Network.
Cite:
Gowri N, Jani Kalianpur, Shravya, Thanmayee N Shetty, Dr Babu Rao K,"DETECTION OF POLYCYSTIC OVARY SYNDROME USING DEEP LEARNING ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13371.
|
DOI:
10.17148/IJARCCE.2024.13371
