The following table or figure may be downloaded to PowerPoint for personal use in teaching and presentations. This feature is available to all subscribers to the journal.

You MUST read and follow the guidelines at Request to Reproduce AJR Content if you are distributing or using AJR content beyond academic use (limited distribution, non-revenue producing, or educational purposes).

(Downloading may take up to 30 seconds.
If the slide opens in your browser, select File -> Save As to save it.)
Click on image to view larger version.

Fig. 1 —Scheme shows texture feature analysis performed by artificial neural network program with three-layer learning algorithm of back propagation comprising seven-unit input layer, six-unit hidden layer, and one-unit output layer. Seven numeric parameters by finite difference method in 10 regions of interest placed in liver parenchyma were inputted into artificial neural network program, and probability value for presence of hepatic fibrosis in region of interest was outputted as continuous number between 0 (absent) and 1 (present).