Automatic Liver Segmentation Method Featuring a Novel Filter for Multiphase Multidetector-Row Helical Computed Tomography

作者：Hirose Tomohiro^*; Nitta Norihisa; Tsudagawa Masaru; Takahashi Masashi; Murata Kiyoshi

来源：Journal of Computer Assisted Tomography, 2011, 35(3): 347-350.

DOI：10.1097/RCT.0b013e31821065a5

• computer-aided diagnosis (CAD)
• automatic liver segmentation
• multidetector-row computed tomography (MDCT)
• liver tumors

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.

• 出版日期2011-6