Purpose: To introduce an automatic liver segmentation method that includes a novel filter for multiphase multidetector-row helical computed tomography.
Materials and Methods: We acquired 3-phase multidetector-row computed tomographic scans that included unenhanced, arterial, and portal phases. The liver was segmented using our novel adaptive linear prediction filter designed to reduce the difference between filter input and output values in the liver region and to increase these values outside the liver region.
Results: The segmentation algorithm produced a mean dice similarity coefficient (DSC) value of 91.4%.
Conclusion: The application of our adaptive linear prediction filter was effective in automatically extracting liver regions.
From the *Department of Radiology, Shiga University of Medical Science, Otsu City, Shiga, Japan; and †Department of Electrical and Electronic Engineering, Faculty of Science and Engineering, Ritsumeikan University, Biwako-Kusatsu Campus, Kusatsu, Shiga, Japan.
Received for publication November 17, 2010; accepted January 14, 2011.
Reprints: Tomohiro Hirose, MD, PhD, Department of Radiology, Shiga University of Medical Science (e-mail: firstname.lastname@example.org).