OBJECTIVE: The purpose of our study was to preliminarily evaluate the usefulness of a computer algorithm analysis using the finite difference method and an artificial neural network to diagnose hepatic fibrosis with MR images. MATERIALS AND METHODS: Liver parenchymal textures on the MR images of 52 patients who underwent partial hepatectomy were processed by the computer algorithm and reviewed by two radiologists. The texture features using the finite difference method were processed by an artificial neural network program containing a three-layer learning algorithm of the back propagation, composed of a seven-unit input layer, a six-unit hidden layer, and a one-unit output layer. The radiologists assigned confidence levels for the presence of hepatic fibrosis. Degrees of hepatic fibrosis were determined semiquantitatively by a pathologist. Algorithm outputs and radiologists' interpretations were correlated with degrees of fibrosis using Spearman's rank correlation analysis, and diagnostic performances were evaluated using receiver operating characteristic curve analysis. RESULTS: By the computer algorithm, the A(z) (area under the curve) value was greater for gadolinium-enhanced equilibrium phase images (A(z) = 0.801) than for T1-weighted (A(z) = 0.597) or T2-weighted (A(z) = 0.525) images (p < 0.05), and the outputs of equilibrium phase images showed a moderate correlation (r = 0.502, p = 0.001) with the pathologic grades. By the radiologists' interpretations, the A(z) value for all images combined (A(z) = 0.715) was greater than that of portal venous phase images (A(z) = 0.503) (p < 0.05), and the confidence levels of all images combined were moderately correlated (r = 0.473, p = 0.002) with pathologic grades. CONCLUSION: Computer algorithm analysis of equilibrium phase images was found to reflect the degree of fibrosis most accurately. MR image texture analysis performed using the computer algorithm was found to have a potential usefulness for the diagnosis of hepatic fibrosis.
OBJECTIVE: The purpose of our study was to preliminarily evaluate the usefulness of a computer algorithm analysis using the finite difference method and an artificial neural network to diagnose hepatic fibrosis with MR images. MATERIALS AND METHODS: Liver parenchymal textures on the MR images of 52 patients who underwent partial hepatectomy were processed by the computer algorithm and reviewed by two radiologists. The texture features using the finite difference method were processed by an artificial neural network program containing a three-layer learning algorithm of the back propagation, composed of a seven-unit input layer, a six-unit hidden layer, and a one-unit output layer. The radiologists assigned confidence levels for the presence of hepatic fibrosis. Degrees of hepatic fibrosis were determined semiquantitatively by a pathologist. Algorithm outputs and radiologists' interpretations were correlated with degrees of fibrosis using Spearman's rank correlation analysis, and diagnostic performances were evaluated using receiver operating characteristic curve analysis. RESULTS: By the computer algorithm, the A(z) (area under the curve) value was greater for gadolinium-enhanced equilibrium phase images (A(z) = 0.801) than for T1-weighted (A(z) = 0.597) or T2-weighted (A(z) = 0.525) images (p < 0.05), and the outputs of equilibrium phase images showed a moderate correlation (r = 0.502, p = 0.001) with the pathologic grades. By the radiologists' interpretations, the A(z) value for all images combined (A(z) = 0.715) was greater than that of portal venous phase images (A(z) = 0.503) (p < 0.05), and the confidence levels of all images combined were moderately correlated (r = 0.473, p = 0.002) with pathologic grades. CONCLUSION: Computer algorithm analysis of equilibrium phase images was found to reflect the degree of fibrosis most accurately. MR image texture analysis performed using the computer algorithm was found to have a potential usefulness for the diagnosis of hepatic fibrosis.
Authors: V Nardone; P Tini; S F Carbone; A Grassi; M Biondi; L Sebaste; T Carfagno; E Vanzi; G De Otto; G Battaglia; G Rubino; P Pastina; G Belmonte; L N Mazzoni; F Banci Buonamici; M A Mazzei; L Pirtoli Journal: Osteoporos Int Date: 2017-02-27 Impact factor: 4.507
Authors: Linda M Pak; Jayasree Chakraborty; Mithat Gonen; William C Chapman; Richard K G Do; Bas Groot Koerkamp; Kees Verhoef; Ser Yee Lee; Marco Massani; Eric P van der Stok; Amber L Simpson Journal: J Am Coll Surg Date: 2018-02-15 Impact factor: 6.113
Authors: Lara C V Harrison; Tiina Luukkaala; Hannu Pertovaara; Tuomas O Saarinen; Tomi T Heinonen; Ritva Järvenpää; Seppo Soimakallio; Pirkko-Liisa I Kellokumpu-Lehtinen; Hannu J Eskola; Prasun Dastidar Journal: J Exp Clin Cancer Res Date: 2009-06-22
Authors: Valerio Nardone; Paolo Tini; Stefania Croci; Salvatore Francesco Carbone; Lucio Sebaste; Tommaso Carfagno; Giuseppe Battaglia; Pierpaolo Pastina; Giovanni Rubino; Maria Antonietta Mazzei; Luigi Pirtoli Journal: Quant Imaging Med Surg Date: 2018-02
Authors: Doaa Mahmoud-Ghoneim; Mariam K Alkaabi; Jacques D de Certaines; Frank-M Goettsche Journal: BMC Med Imaging Date: 2008-12-23 Impact factor: 1.930