CNN Based Determination of Polycystic Ovarian Syndrome using Automatic Follicle Detection Methods

English (OpenAlex)

The aim of this study was to determine the best method for follicle detection using ovarian ultrasound images and to classify the ultrasound images as pcos or normal ovaries using the proposed CNN architecture. Two different methods for follicle detection have been proposed to evaluate pcos. For this purpose, the Median, the Mean, the Wiener, and the Gaussian filters were tested using standard and adaptive thresholds. Second, Gaussian filtering, Discrete Wavelet Transform, and k-means clustering algorithms were tested. The Canny operator separates follicles from the background in the segmentation phase. In this study, a CNN architecture that classifies limited ultrasound ovary images was developed, and its success in the best follicle detection method was presented. The highest follicle detection accuracy of 97.63% was achieved with adaptive thresholding using a Wiener filter. Besides, the ultrasound images of the ovaries were classified as "normal" or "polycystic ovary syndrome" using CNN architecture with classification accuracy of 65.81% for unsegmented ovarian images and 77.81% for segmented images. In addition to the proposed method, classification was performed using SqueezeNet-based transfer learning, which was successful in limited datasets, and 74.18% classification accuracy was achieved for the unsegmented images and 75.54 % for segmented images . The results show that the combination of the Wiener filter with adaptive thresholding was quite successful in follicle detection and that the CNN can better classify ovaries using preprocessed ultrasound images.