Tumor detection using brain MRI and low-dimension co-occurrence feature approach

Research in medical imaging focuses on methods useful in computer-aided diagnosis systems. In modern times, these systems often have automatic detection of regions of interest, and imaging technologies offer numerous advantages, like the possibility of developing reliable assisting algorithms. Magnetic Resonance Imaging (MRI) provides compelling features for brain tumor detection due to good soft tissue contrast and has important clinical value. To help clinicians in making diagnoses, current algorithms for processing and medical image classification may depend on intricate deep learning designs that demand large hardware resources and lengthy execution times. This is with no doubt helpful in understanding disease mechanisms and in labeling difficult instances for brain tumor identification. On the other hand, statistical low-dimension feature sets including co-occurrence-based ones could be useful in dealing with tumor detection avoiding possible complexity. In this paper, statistical approaches for feature extraction and reduction are analyzed for MRI brain tumor classification, and the evaluation of the results is presented on one of the publicly available brain tumor detection database commonly used for machine learning tasks. Bayes and kNN classifiers are applied for the analysis, as well as four distance metrics, and two methods for feature reduction. The results seem promising in developing a simple and less hardware-demanding procedure.