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 Lorne Ehman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

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.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8672
DOIs
StatePublished - 2013
EventMedical Imaging 2013: Biomedical Applications in Molecular, Structural, and Functional Imaging - Lake Buena Vista, FL, United States
Duration: Feb 10 2013Feb 13 2013

Other

OtherMedical Imaging 2013: Biomedical Applications in Molecular, Structural, and Functional Imaging
CountryUnited States
CityLake Buena Vista, FL
Period2/10/132/13/13

Fingerprint

Elasticity Imaging Techniques
liver
Liver
stiffness
Stiffness
Magnetic resonance
magnetic resonance
Masks
readers
Artifacts
artifacts
inhomogeneity
masks
Tissue
fibrosis
anatomy
blood vessels
Blood vessels
ratings
Liver Cirrhosis

Keywords

  • Automation
  • Hepatic fibrosis
  • Liver
  • Mr elastography
  • Segmentation

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Dzyubak, B., Venkatesh, S. K., Glaser, K., Yin, M., Talwalkar, J., Chen, J., ... Ehman, R. L. (2013). Stable automated segmentation of liver MR elastography images for clinical stiffness measurement. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 8672). [86721I] https://doi.org/10.1117/12.2006943

Stable automated segmentation of liver MR elastography images for clinical stiffness measurement. / Dzyubak, Bogdan; Venkatesh, Sudhakar K; Glaser, Kevin; Yin, Meng; Talwalkar, Jayant; Chen, Jun; Manduca, Armando; Ehman, Richard Lorne.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8672 2013. 86721I.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dzyubak, B, Venkatesh, SK, Glaser, K, Yin, M, Talwalkar, J, Chen, J, Manduca, A & Ehman, RL 2013, Stable automated segmentation of liver MR elastography images for clinical stiffness measurement. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 8672, 86721I, Medical Imaging 2013: Biomedical Applications in Molecular, Structural, and Functional Imaging, Lake Buena Vista, FL, United States, 2/10/13. https://doi.org/10.1117/12.2006943
Dzyubak B, Venkatesh SK, Glaser K, Yin M, Talwalkar J, Chen J et al. Stable automated segmentation of liver MR elastography images for clinical stiffness measurement. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8672. 2013. 86721I https://doi.org/10.1117/12.2006943
Dzyubak, Bogdan ; Venkatesh, Sudhakar K ; Glaser, Kevin ; Yin, Meng ; Talwalkar, Jayant ; Chen, Jun ; Manduca, Armando ; Ehman, Richard Lorne. / Stable automated segmentation of liver MR elastography images for clinical stiffness measurement. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8672 2013.
@inproceedings{cf54b272b70e4d659f83bb9f7e27292b,
title = "Stable automated segmentation of liver MR elastography images for clinical stiffness measurement",
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.",
keywords = "Automation, Hepatic fibrosis, Liver, Mr elastography, Segmentation",
author = "Bogdan Dzyubak and Venkatesh, {Sudhakar K} and Kevin Glaser and Meng Yin and Jayant Talwalkar and Jun Chen and Armando Manduca and Ehman, {Richard Lorne}",
year = "2013",
doi = "10.1117/12.2006943",
language = "English (US)",
isbn = "9780819494467",
volume = "8672",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Stable automated segmentation of liver MR elastography images for clinical stiffness measurement

AU - Dzyubak, Bogdan

AU - Venkatesh, Sudhakar K

AU - Glaser, Kevin

AU - Yin, Meng

AU - Talwalkar, Jayant

AU - Chen, Jun

AU - Manduca, Armando

AU - Ehman, Richard Lorne

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - Automation

KW - Hepatic fibrosis

KW - Liver

KW - Mr elastography

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84878273898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878273898&partnerID=8YFLogxK

U2 - 10.1117/12.2006943

DO - 10.1117/12.2006943

M3 - Conference contribution

AN - SCOPUS:84878273898

SN - 9780819494467

VL - 8672

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -