Automatic PET volume analysis and classification based on ANN and BIC

Abstract

The increasing number of patient scans and the prevailing application of positron emission tomography (PET) in clinical oncology have led to a real need for efficient PET volume handling and the development of new volume analysis and classification approaches to aid clinicians in the diagnosis of diseases and planning of treatment. A novel automated approach for oncological PET volume classification is proposed in this paper. The proposed intelligent system deploys artificial neural networks (ANN) for classifying phantom and clinical PET volumes. Bayesian information criterion (BIC) has been used in this system to assess the optimal number of classes for each PET data set and assist the ANN block to achieve accurate automatic classification for the region of interest (ROI). ANN performance evaluation has been carried out using confusion matrix and receiver operating characteristic curve. The proposed classification methodology of phantom and clinical oncological PET data has shown promising results and can successfully classify patient lesion.