Pattern recognition in medical images using neural networks

Abstract

The proposal of this research line is the search for alternatives to the resolution of complex problems where human knowledge should be apprehended in a general fashion. In particular, the activities developed so far can be included in the area of Medical Diagnosis, even though similar applications in other fields are not discarded. In general, one of the greatest problems of medical diagnosis is the subjectivity of the specialist. The experience of the professional greatly affects the final diagnosis. This is due to the fact that the result does not depend on a systematized solution, but on the interpretation of the patient´s answer. The solution to this kind of problems can be found in the area of Adaptive Pattern Recognition, where the solution rests on the easiness with which the systems adapts to the information available, in this case coming from the patient. In this sense, neural networks are extremely useful, since they are not only capable of learning with the aid of an expert, but they can also make generalizations based on the information from the input data, thus showing relations that are a priori of a complex nature.