Stable automated segmentation of liver MR elastography images for clinical stiffness measurement

Bogdan Dzyubak; Sudhakar K. Venkatesh; Kevin Glaser; Meng Yin; Jayant Talwalkar; Jun Chen; Armando Manduca; Richard L. Ehman

doi:10.1117/12.2006943

29 March 2013 Stable automated segmentation of liver MR elastography images for clinical stiffness measurement

Bogdan Dzyubak, Sudhakar K. Venkatesh, Kevin Glaser, Meng Yin, Jayant Talwalkar, Jun Chen, Armando Manduca, Richard L. Ehman

Author Affiliations +

Proceedings Volume 8672, Medical Imaging 2013: Biomedical Applications in Molecular, Structural, and Functional Imaging; 86721I (2013) https://doi.org/10.1117/12.2006943
Event: SPIE Medical Imaging, 2013, Lake Buena Vista (Orlando Area), Florida, United States

Abstract

Magnetic Resonance Elastography (MRE) is an MRI-based technique that is used for the clinical diagnosis and staging of liver fibrosis by quantitatively measuring the stiffness of the liver. Due to the complexity of the signal characteristics and the presence of artifacts both in the acquired images and in the resulting stiffness images, the selection of the ROI for the stiffness measurement is currently performed manually, which may lead to significant inter- and intrareader variability. An algorithm has been developed to fully automate this analysis for liver MRE images. Automated segmentation of liver MRE images is challenging due to signal inhomogeneity, low contrast, and variability in patient anatomy. An initial liver contour is found by fitting Gaussian peaks to the image histogram and selecting the peak that comprises intensities in the expected range and produces a mask near the expected location of the liver. After correction to reduce intensity inhomogeneity, an active contour based on intensity, with morphology used to implicitly enforce smoothness, is used to segment liver tissue while avoiding blood vessels. The resulting mask is used to initialize another segmentation which splits the region of the elastogram belonging to the liver into homogeneous liver tissue and areas with inclusions, partial volume effects, and artifacts. In a set of 88 cases the algorithm had a -6.0 ± 14.2% stiffness difference from an experienced reader, which was superior to the 6.8 ± 22.8% difference between two readers. The segmentation was run on an additional 200 cases and the final ROIs were subjectively rated by a radiologist. The ROIs in 98% of cases received an average rating of “good” or “acceptable.”

Citation Download Citation

Bogdan Dzyubak, Sudhakar K. Venkatesh, Kevin Glaser, Meng Yin, Jayant Talwalkar, Jun Chen, Armando Manduca, and Richard L. Ehman "Stable automated segmentation of liver MR elastography images for clinical stiffness measurement", Proc. SPIE 8672, Medical Imaging 2013: Biomedical Applications in Molecular, Structural, and Functional Imaging, 86721I (29 March 2013); https://doi.org/10.1117/12.2006943

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available