Bladder Cancer Recognition: A Comparative Study

Abstract

Medical Imaging technologies, such as magnetic resonance imaging (MRI), have been widely applied to various medical procedures. Daily growth of medical data volume leads to human mistakes in the manual analysis and increases the need of automatic analysis. Therefore, applying some tools to collect, classify, and analyze the medical data automatically is a must. Medical imaging issues are so complex owing to high importance of correct diagnosis and treatment of diseases in healthcare systems. For these reasons, algorithms of automatic medical image analysis are used to help in increasing reliability and accurate understanding of the medical images. AI methods such as digital image processing and its combinations with other techniques like machine learning, fuzzy logic, neural networks, and pattern recognition are so valuable in visualization and analysis of medical images. The objective of this paper is to investigate the use of artificial intelligence techniques like artificial neural networks (ANN) algorithms such as (multilayer perceptron (MLP), Jordan /Eleman, Self Organizing Feature Map and support vector machine (SVM)) to early detect bladder cancer (diagnosis), to determine tumor staging (for sake of prognosis), and to assess the accuracy of MRI in T staging bladder cancer. A set of functional images taken by magnetic resonance (MR) is to be used. It was found that, multilayer perceptron neural network (MLP) gives better result than other algorithms.