Automated interpretation of ventilation-perfusion lung scintigrams for thediagnosis of pulmonary embolism using artificial neural networks

The purpose of this study was to develop a completely automated method for the interpretation of ventilation-perfusion (V-P) lung scintigrams used in the diagnosis of pulmonary embolism, An artificial neural network was train ed for the diagnosis of pulmonary embolism using 18 automatically obtained features from each set of V-P scintigrams. The techniques used to process t he images included their alignment to templates, the construction of quotie nt images based on the ventilation and perfusion images, and the calculatio n of measures describing V-P mismatches in the quotient images. The templat es represented lungs of normal size and shape without any pathological chan ges. Images that could not be properly aligned to the templates: were detec ted and excluded automatically. After exclusion of those V-P scintigrams no t properly aligned to the templates, 478 V-P scintigrams remained in a trai ning group of consecutive patients with suspected pulmonary embolism, and a further 87 V-P scintigrams formed a separate test group comprising patient s who had undergone pulmonary angiography. The performance of the neural ne twork, measured as the area under the receiver operating characteristic cur ve, was 0.87 (95% confidence limits 0.82-0.92) in the training group and 0. 79 (0.69-0.88) in the test group, It is concluded that a completely automat ed method can be used for the interpretation of V-P scintigrams. The perfor mance of this method is similar to others previously presented, whereby fea tures were extracted manually.