A DEEP LEARNING APPROACH FOR OVARIAN CYSTS DETECTION AND CLASSIFICATION (OCD-FCNN) USING FUZZY CONVOLUTIONAL NEURAL NETWORK
Abstract
Most women, in general, have an ovarian cyst and it is causing the disorder. Pregnant cysts occur when many water-packed tumours appear in the womb. This is especially the case for women with an excellent cause for childbearing. Women are related to menstrual problems and cyst problems during pregnancy. Recently, ultrasound imaging and machine learning techniques have been used to detect ovarian cysts. Different domain experts provide their own decisions on finding out what kind of ovarian cyst it is from ultrasound images. However, a most accurate and uniform decision-making system is necessary for the early detection of cysts. To aid physicians, an automated detection system has been proposed in this paper to make it more effective for physicians to eliminate these problems. In this system, the extracted features from the image are used for cysts detection and classification. Automatic ovary cyst detection (OCD) and classification are implemented in this work using a fuzzy rule-based Convolutional Neural Network (FCNN). The proposed system (OCD-FCNN) has yielded 98.37% accurate results when tested with benchmark datasets.
Keywords
Ultrasound image; ovarian cyst; fuzzy rules; Convolutional Neural Network