THE AUTOMATIZED LAPAROSCOPIC DIAGNOSTICS OF THE LIVER PATHOLOGY

The effectiveness of the laparoscopic video-images of the surface of the liver is described. The automatic diagnostic technology was developed on the basis of Haar-like features usage. The classification of images was performed using cascade classificator usage, and 1000 positive images along with 500 negative ones have been used. It was established that the sensitivity of cirrhosis of the liver diagnostics was 68.8% and exceeded that one which was determined after expert analysis (31.0%) (P<0,01). The sensitivity of metastatic damage was 80.0% and 46.7 % after developed and expert diagnostics were performed correspondently (P<0.02). Besides, the specificity was also elevated — from 52.5% after expert diagnostics up to 85.0% (P<0.01) after developed method. The net increasing of both positive prognostic index (from 42.4 up to 80.0 %, P<0.01), and negative one (from 56.8% up to 87.2%, P<0.01) was also observed.