A Novel Pigeon Inspired Optimization in Ovarian Cyst Detection

Follicular cyst is characterized by the fluid filled sac presence in the female ovary. Ultrasound imaging system is the one commonly used for this cyst diagnosis. In this system, transvaginal ultrasound is used to take a look into women's reproductive system, the uterus and ovaries. Presently, while scanning, the radiologists manually trace the details of the follicular cysts, its number and size which is painful for the patients. In this paper, a novel optimization technique called Pigeon Inspired Optimization (PIO) algorithm is proposed to obtain the optimal threshold value for automatic detection of follicular cyst from the ovarian image and extract it features. The proposed method effectively obtains the threshold value by maximizing the between class variance of the modified Otsu method. The automatic follicular cyst detection system proposed in this paper reduces the error in manual detection and time taken for diagnosis. The proposed PIO algorithm has been compared with Invasive Weed Optimization (IWO). The experimental results show that the proposed method finds the better solution and converges faster than the IWO.