Remote Detection of Cerebral Pathologies in Magnetic Resonance Imagery: an Unsupervised Heuristic Approach.

In this work, the attention has been focused to the field of “medical imaging”. The problem of pattern recognition in remote sensing with medical application has been discussed in order to detect significant lesions in encephalic non-invasive diagnostics. In particular, Nuclear Magnetic Resonance analysis have been considered. The aim is to propose an automatic way to recognize encephalic pathologies in real imagery by using computer abilities. Because of problem solution has remarkable difficulties, proposed approach is based on heuristic unsupervised techniques. In this case, imagery have been evaluated by implementation of a particular Self-Organizing Map Neural Network with diagnostic purposes. The Self-Organizing Map receives as input different images of pathological encephala; the aim is to conjugate sensibility of medical imaging techniques with pattern recognition flexibility of Artificial Neural Networks. Retrieved results confirm reliability of proposed heuristic approach in medical application of remote sensing and imagery segmentation.