Published Paper Details:

The conventional method for classification and tumor detection of medical resonance brain tumor images is by human inspection, where in a lot of time and effort is put in by the specialists to analyze the problem area and to come up with a conclusion regarding the spread of the tumor region and its current stage. This paper proposes a fast and robust practical tool for segmentation of solid tumors with minimal user interaction to assist clinicians and researchers in radio surgery planning and assessment of the response to the therapy and classification of tumors using probabilistic neural network. Particularly, cellular automata (CA) based seeded tumor segmentation method on magnetic resonance (MR) images, and a standardized process called seed selection, is proposed. ANN with image and data processing techniques were employed to implement an automated brain tumor classification. Decision making was performed in two stages: feature extraction using the principal component analysis and the classification using Probabilistic Neural Network (PNN). The performance of the PNN classifier was evaluated in terms of training performance and classification accuracies.