THE DEVELOPMENT OF A DECISION-SUPPORT SYSTEM FOR THE PATHOLOGICAL DIAGNOSIS OF HUMAN CEREBRAL-TUMORS BASED ON A NEURAL-NETWORK CLASSIFIER

This study describes the use of a topological mapping system in the cl assification of cerebral tumours and the development of a decision sup port system based upon that classifier. Fourteen pathological paramete rs from two hundred primary cerebral tumours are presented as vectors to a topological map. The map, consisting of a grid of neurones, learn s the features of each tumour by means of a shortest Euclidean distanc e algorithm, after which self adaptation of the neurones occurs. An LV Q algorithm performs the final classification. Study of the map reveal s that it can correctly classify tumours following their malignancy po tential and their cytogenesis. The decision support system uses the ne twork at its core and helps not only in reaching a diagnosis but also in finding the optimal way to reach that diagnosis. The usefulness of such a mapping system lies in the field of education, clinical researc h and medically acceptable cost reduction.