COMPUTERIZED ANALYSIS OF TRANSRECTAL ULTRASONOGRAPHY IMAGES IN THE DETECTION OF PROSTATE CARCINOMA

Objective To report on the use of automated image analysis in the inte rpretation of transrectal ultrasonographic images of the prostate. Pat ients and methods During transrectal ultrasonography, images were reco rded from biopsies performed in 127 patients. Subsequently in the imag e, the puncture place was marked and analysed. Analysis of the images was performed with the Automated Urologic Diagnostic Expert (AUDEX) sy stem, consisting of a personal computer connected to the ultrasound ma chine. From the images collected, parameters can be calculated for ima ge classification. The parameters obtained with this procedure were co rrelated with the histological result. Results Evaluation showed a sen sitivity of 84.8% and specificity of 87.5%. The positive and negative predictive values, to predict prostate carcinoma, were 84.8% and 87.5% , respectively. Conclusion Automated image analysis can help in the di agnosis of prostate carcinoma. In patients with nonpalpable lesions or with poorly visualized tumours, image analysis is superior to the sta ndard current diagnostic techniques.