Intelligence techniques for prostate ultrasound image analysis

Abstract

In this paper we present an intelligent scheme, employing a combination of fuzzy logic, pulse coupled neural networks (PCNNs), wavelets and rough sets, for analysing prostrate ultrasound images in order diagnose prostate cancer. Image noise is a principal factor which hampers the visual quality of ultrasound images and can therefore lead to misdiagnosis. To address this issue we first utilise an algorithm based on type-II fuzzy sets to enhance the contrast of the image. This is followed by performing PCNN-based segmentation in order to identify the region of interest and to detect the boundary of the prostate pattern. Then, a wavelet features are extracted and normalised, followed by application of a rough set analysis to discover the dependency between the attributes, and to generate a set of reducts consisting of a minimal number of attributes. Finally, a rough set classifier is designed for discrimination of different regions of interest to determine whether they represent cancer or not. To evaluate the performance of our approach, we present tests on different prostate ultrasound images. The experimental results obtained, show that the overall classification accuracy offered by the employed rough set approach is high compared with other intelligent techniques including decision trees, discriminant analysis, rough neural networks, fuzzy ARTMAP, and neural networks.

State-of-the-Art Neural Networks Applications in Biology

“…The procedure consists of four main steps, the first of which is the preprocessing of the images with fuzzy type-II sets, obtained by blurring a type-I membership function, in order to improve the quality of the images. Type-II fuzzy sets are an extension of type-I fuzzy sets with an additional dimension that represents the uncertainty about the degrees of membership (Ensafi & Tizhoosh, 2005;Hassanien, 2009). The second step is the segmentation of the breast images using an adaptive ant-based segmentation technique, which is an improvement of the ant-based clustering algorithm.…”