Improving the Diagnosis of Ischemic CVA's through CT Scan with Neural Networks

Technological and computing evolution promoted new opportunities to improve the quality of life, in particular, the quality of diagnostic evaluations. Computerized tomography is one of the imaging equipments of diagnosis which has most benefited from technological improvements. Because of that, and due to the quality of the diagnosis produced, it is one of the most employed equipments in clinical applications. The ischaemic cerebral vascular accident (ICVA) is the pathology that confirms the frequent use of the computerized tomography. The interest for this pathology, and in general for the encephalon image analysis as a preventive diagnosis, is mainly due to the frequent occurrence of ICV As in development countries and its social-economic impact. In this sense, we propose to evaluate the ability of artificial neural networks (ANN) for automatic identification of ICVA by means of tissue density images obtained by computerised tomography. This work employed cranioencephalon computerised tomography exams and their respective medical reports, to train ANNs classifiers. Features extracted from the images were used as inputs to the classifiers. Once the ANNs were trained, the neural classifiers were tested with data never seen by the network. At this stage we may conclude that the ANNs may significantly contribute as an ICV As computerised tomography diagnostic aid, since among the test cases the automatic identification of ischaemic lesions has been performed with no false negatives e very few false positives.