Autori: Lupsor M, Badea R, Nedevschi S, Vicas C, Tripon S, Stefanescu H, Radu C, Grigorescu M.

Editorial: Acta Electrotehnica , 18(4), p.245-250, 2007.

Rezumat:

Abstract — Liver chronic diseases constitute an important public health issue. When diagnosing diffuse hepatopathies, ultrasonography is a simple method bringing useful information but not safe enough when determining the difference between certain diseases (steatosis, chronic hepatitis or early cirrhosis) or quantifying their severity. Present study is focused on examining pure fibrosis tissues in order to get a clear overview on how the presence of the fibrosis affects the ultrasonographic aspect of the liver. We tried to assess the usefulness of the computerized texture image analysis in noninvasive fibrosis grade quantification. From over 350 with biopsies we’ve selected 58 chronic hepatitis C patients, which have pure fibrosis without any steatosis. On each image we established a Region of Interest and we extracted 166 features using 4 algorithms from it. We compared the mean values of each feature between medical significant fibrosis stages using Student’s test (p<0.05). We find that we can distinguish between close fibrosis stage with one or more relevant features, but there is no feature that has a relevance over 95% in each comparison case. Therefore, using only one parameter cannot distinguish between all liver fibrosis stage, and a combination of features must be used in order to successfully diagnose the fibrosis stage.

Cuvinte cheie: fibrosis, image processing, non-invasive, texture, ultrasonography

URL: http://ie.utcluj.ro/Contents_Acta_ET/2007/Number4/Papers/P30508.pdf