Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T

Takeshi Yokoo, Tanya Wolfson, Keiko Iwaisako, Michael R. Peterson, Haresh Mani, Zachary Goodman, Christopher Changchien, Michael S. Middleton, Anthony C. Gamst, Sameer M. Mazhar, Yuko Kono, Samuel B. Ho, Claude B. Sirlin

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Purpose. To noninvasively assess liver fibrosis using combined-contrast-enhanced (CCE) magnetic resonance imaging (MRI) and texture analysis. Materials and Methods. In this IRB-approved, HIPAA-compliant prospective study, 46 adults with newly diagnosed HCV infection and recent liver biopsy underwent CCE liver MRI following intravenous administration of superparamagnetic iron oxides (ferumoxides) and gadolinium DTPA (gadopentetate dimeglumine). The image texture of the liver was quantified in regions-of-interest by calculating 165 texture features. Liver biopsy specimens were stained with Masson trichrome and assessed qualitatively (METAVIR fibrosis score) and quantitatively (% collagen stained area). Using L1 regularization path algorithm, two texture-based multivariate linear models were constructed, one for quantitative and the other for quantitative histology prediction. The prediction performance of each model was assessed using receiver operating characteristics (ROC) and correlation analyses. Results. The texture-based predicted fibrosis score significantly correlated with qualitative (r=0.698, P<0.001) and quantitative (r=0.757, P<0.001) histology. The prediction model for qualitative histology had 0.814-0.976 areas under the curve (AUC), 0.659-1.000 sensitivity, 0.778-0.930 specificity, and 0.674-0.935 accuracy, depending on the binary classification threshold. The prediction model for quantitative histology had 0.742-0.950 AUC, 0.688-1.000 sensitivity, 0.679-0.857 specificity, and 0.696-0.848 accuracy, depending on the binary classification threshold. Conclusion. CCE MRI and texture analysis may permit noninvasive assessment of liver fibrosis.

Original languageEnglish (US)
Article number387653
JournalBioMed Research International
Volume2015
DOIs
StatePublished - 2015

Fingerprint

Magnetic resonance
Liver Cirrhosis
Liver
Histology
Magnetic Resonance Spectroscopy
Textures
Gadolinium DTPA
Magnetic Resonance Imaging
Area Under Curve
Fibrosis
Biopsy
Health Insurance Portability and Accountability Act
Imaging techniques
Research Ethics Committees
ROC Curve
Intravenous Administration
Image texture
Linear Models
Collagen
Prospective Studies

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)

Cite this

Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T. / Yokoo, Takeshi; Wolfson, Tanya; Iwaisako, Keiko; Peterson, Michael R.; Mani, Haresh; Goodman, Zachary; Changchien, Christopher; Middleton, Michael S.; Gamst, Anthony C.; Mazhar, Sameer M.; Kono, Yuko; Ho, Samuel B.; Sirlin, Claude B.

In: BioMed Research International, Vol. 2015, 387653, 2015.

Research output: Contribution to journalArticle

Yokoo, T, Wolfson, T, Iwaisako, K, Peterson, MR, Mani, H, Goodman, Z, Changchien, C, Middleton, MS, Gamst, AC, Mazhar, SM, Kono, Y, Ho, SB & Sirlin, CB 2015, 'Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T', BioMed Research International, vol. 2015, 387653. https://doi.org/10.1155/2015/387653
Yokoo, Takeshi ; Wolfson, Tanya ; Iwaisako, Keiko ; Peterson, Michael R. ; Mani, Haresh ; Goodman, Zachary ; Changchien, Christopher ; Middleton, Michael S. ; Gamst, Anthony C. ; Mazhar, Sameer M. ; Kono, Yuko ; Ho, Samuel B. ; Sirlin, Claude B. / Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T. In: BioMed Research International. 2015 ; Vol. 2015.
@article{49c5a92291b64387ac1cfaf97beca79f,
title = "Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T",
abstract = "Purpose. To noninvasively assess liver fibrosis using combined-contrast-enhanced (CCE) magnetic resonance imaging (MRI) and texture analysis. Materials and Methods. In this IRB-approved, HIPAA-compliant prospective study, 46 adults with newly diagnosed HCV infection and recent liver biopsy underwent CCE liver MRI following intravenous administration of superparamagnetic iron oxides (ferumoxides) and gadolinium DTPA (gadopentetate dimeglumine). The image texture of the liver was quantified in regions-of-interest by calculating 165 texture features. Liver biopsy specimens were stained with Masson trichrome and assessed qualitatively (METAVIR fibrosis score) and quantitatively ({\%} collagen stained area). Using L1 regularization path algorithm, two texture-based multivariate linear models were constructed, one for quantitative and the other for quantitative histology prediction. The prediction performance of each model was assessed using receiver operating characteristics (ROC) and correlation analyses. Results. The texture-based predicted fibrosis score significantly correlated with qualitative (r=0.698, P<0.001) and quantitative (r=0.757, P<0.001) histology. The prediction model for qualitative histology had 0.814-0.976 areas under the curve (AUC), 0.659-1.000 sensitivity, 0.778-0.930 specificity, and 0.674-0.935 accuracy, depending on the binary classification threshold. The prediction model for quantitative histology had 0.742-0.950 AUC, 0.688-1.000 sensitivity, 0.679-0.857 specificity, and 0.696-0.848 accuracy, depending on the binary classification threshold. Conclusion. CCE MRI and texture analysis may permit noninvasive assessment of liver fibrosis.",
author = "Takeshi Yokoo and Tanya Wolfson and Keiko Iwaisako and Peterson, {Michael R.} and Haresh Mani and Zachary Goodman and Christopher Changchien and Middleton, {Michael S.} and Gamst, {Anthony C.} and Mazhar, {Sameer M.} and Yuko Kono and Ho, {Samuel B.} and Sirlin, {Claude B.}",
year = "2015",
doi = "10.1155/2015/387653",
language = "English (US)",
volume = "2015",
journal = "BioMed Research International",
issn = "2314-6133",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T

AU - Yokoo, Takeshi

AU - Wolfson, Tanya

AU - Iwaisako, Keiko

AU - Peterson, Michael R.

AU - Mani, Haresh

AU - Goodman, Zachary

AU - Changchien, Christopher

AU - Middleton, Michael S.

AU - Gamst, Anthony C.

AU - Mazhar, Sameer M.

AU - Kono, Yuko

AU - Ho, Samuel B.

AU - Sirlin, Claude B.

PY - 2015

Y1 - 2015

N2 - Purpose. To noninvasively assess liver fibrosis using combined-contrast-enhanced (CCE) magnetic resonance imaging (MRI) and texture analysis. Materials and Methods. In this IRB-approved, HIPAA-compliant prospective study, 46 adults with newly diagnosed HCV infection and recent liver biopsy underwent CCE liver MRI following intravenous administration of superparamagnetic iron oxides (ferumoxides) and gadolinium DTPA (gadopentetate dimeglumine). The image texture of the liver was quantified in regions-of-interest by calculating 165 texture features. Liver biopsy specimens were stained with Masson trichrome and assessed qualitatively (METAVIR fibrosis score) and quantitatively (% collagen stained area). Using L1 regularization path algorithm, two texture-based multivariate linear models were constructed, one for quantitative and the other for quantitative histology prediction. The prediction performance of each model was assessed using receiver operating characteristics (ROC) and correlation analyses. Results. The texture-based predicted fibrosis score significantly correlated with qualitative (r=0.698, P<0.001) and quantitative (r=0.757, P<0.001) histology. The prediction model for qualitative histology had 0.814-0.976 areas under the curve (AUC), 0.659-1.000 sensitivity, 0.778-0.930 specificity, and 0.674-0.935 accuracy, depending on the binary classification threshold. The prediction model for quantitative histology had 0.742-0.950 AUC, 0.688-1.000 sensitivity, 0.679-0.857 specificity, and 0.696-0.848 accuracy, depending on the binary classification threshold. Conclusion. CCE MRI and texture analysis may permit noninvasive assessment of liver fibrosis.

AB - Purpose. To noninvasively assess liver fibrosis using combined-contrast-enhanced (CCE) magnetic resonance imaging (MRI) and texture analysis. Materials and Methods. In this IRB-approved, HIPAA-compliant prospective study, 46 adults with newly diagnosed HCV infection and recent liver biopsy underwent CCE liver MRI following intravenous administration of superparamagnetic iron oxides (ferumoxides) and gadolinium DTPA (gadopentetate dimeglumine). The image texture of the liver was quantified in regions-of-interest by calculating 165 texture features. Liver biopsy specimens were stained with Masson trichrome and assessed qualitatively (METAVIR fibrosis score) and quantitatively (% collagen stained area). Using L1 regularization path algorithm, two texture-based multivariate linear models were constructed, one for quantitative and the other for quantitative histology prediction. The prediction performance of each model was assessed using receiver operating characteristics (ROC) and correlation analyses. Results. The texture-based predicted fibrosis score significantly correlated with qualitative (r=0.698, P<0.001) and quantitative (r=0.757, P<0.001) histology. The prediction model for qualitative histology had 0.814-0.976 areas under the curve (AUC), 0.659-1.000 sensitivity, 0.778-0.930 specificity, and 0.674-0.935 accuracy, depending on the binary classification threshold. The prediction model for quantitative histology had 0.742-0.950 AUC, 0.688-1.000 sensitivity, 0.679-0.857 specificity, and 0.696-0.848 accuracy, depending on the binary classification threshold. Conclusion. CCE MRI and texture analysis may permit noninvasive assessment of liver fibrosis.

UR - http://www.scopus.com/inward/record.url?scp=84941662589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941662589&partnerID=8YFLogxK

U2 - 10.1155/2015/387653

DO - 10.1155/2015/387653

M3 - Article

VL - 2015

JO - BioMed Research International

JF - BioMed Research International

SN - 2314-6133

M1 - 387653

ER -