Image texture features predict renal function decline in patients with autosomal dominant polycystic kidney disease

Timothy Kline, Panagiotis Korfiatis, Marie E. Edwards, Kyongtae T. Bae, Alan Yu, Arlene B. Chapman, Michal Mrug, Jared J. Grantham, Douglas Landsittel, William M. Bennett, Bernard Francis King, Peter C Harris, Vicente Torres, Bradley J Erickson

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Magnetic resonance imaging (MRI) examinations provide high-resolution information about the anatomic structure of the kidneys and are used to measure total kidney volume (TKV) in patients with Autosomal Dominant Polycystic Kidney Disease (ADPKD). Height-adjusted TKV (HtTKV) has become the gold-standard imaging biomarker for ADPKD progression at early stages of the disease when estimated glomerular filtration rate (eGFR) is still normal. However, HtTKV does not take advantage of the wealth of information provided by MRI. Here we tested whether image texture features provide additional insights into the ADPKD kidney that may be used as complementary information to existing biomarkers. A retrospective cohort of 122 patients from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study was identified who had T2-weighted MRIs and eGFR values over 70 mL/min/1.73m2 at the time of their baseline scan. We computed nine distinct image texture features for each patient. The ability of each feature to predict subsequent progression to CKD stage 3A, 3B, and 30% reduction in eGFR at eight-year follow-up was assessed. A multiple linear regression model was developed incorporating age, baseline eGFR, HtTKV, and three image texture features identified by stability feature selection (Entropy, Correlation, and Energy). Including texture in a multiple linear regression model (predicting percent change in eGFR) improved Pearson correlation coefficient from -0.51 (using age, eGFR, and HtTKV) to -0.70 (adding texture). Thus, texture analysis offers an approach to refine ADPKD prognosis and should be further explored for its utility in individualized clinical decision making and outcome prediction.

Original languageEnglish (US)
JournalKidney International
DOIs
StateAccepted/In press - Jul 12 2016

Fingerprint

Autosomal Dominant Polycystic Kidney
Glomerular Filtration Rate
Kidney
Linear Models
Biomarkers
Magnetic Resonance Imaging
Polycystic Kidney Diseases
Entropy
Gold
Disease Progression

Keywords

  • Gray-level co-occurrence matrix
  • Magnetic resonance imaging
  • Multiple linear regression
  • Polycystic kidney disease
  • Total kidney volume

ASJC Scopus subject areas

  • Medicine(all)
  • Nephrology

Cite this

Image texture features predict renal function decline in patients with autosomal dominant polycystic kidney disease. / Kline, Timothy; Korfiatis, Panagiotis; Edwards, Marie E.; Bae, Kyongtae T.; Yu, Alan; Chapman, Arlene B.; Mrug, Michal; Grantham, Jared J.; Landsittel, Douglas; Bennett, William M.; King, Bernard Francis; Harris, Peter C; Torres, Vicente; Erickson, Bradley J.

In: Kidney International, 12.07.2016.

Research output: Contribution to journalArticle

@article{cc5f446a4b9a46508daa1ce13af41979,
title = "Image texture features predict renal function decline in patients with autosomal dominant polycystic kidney disease",
abstract = "Magnetic resonance imaging (MRI) examinations provide high-resolution information about the anatomic structure of the kidneys and are used to measure total kidney volume (TKV) in patients with Autosomal Dominant Polycystic Kidney Disease (ADPKD). Height-adjusted TKV (HtTKV) has become the gold-standard imaging biomarker for ADPKD progression at early stages of the disease when estimated glomerular filtration rate (eGFR) is still normal. However, HtTKV does not take advantage of the wealth of information provided by MRI. Here we tested whether image texture features provide additional insights into the ADPKD kidney that may be used as complementary information to existing biomarkers. A retrospective cohort of 122 patients from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study was identified who had T2-weighted MRIs and eGFR values over 70 mL/min/1.73m2 at the time of their baseline scan. We computed nine distinct image texture features for each patient. The ability of each feature to predict subsequent progression to CKD stage 3A, 3B, and 30{\%} reduction in eGFR at eight-year follow-up was assessed. A multiple linear regression model was developed incorporating age, baseline eGFR, HtTKV, and three image texture features identified by stability feature selection (Entropy, Correlation, and Energy). Including texture in a multiple linear regression model (predicting percent change in eGFR) improved Pearson correlation coefficient from -0.51 (using age, eGFR, and HtTKV) to -0.70 (adding texture). Thus, texture analysis offers an approach to refine ADPKD prognosis and should be further explored for its utility in individualized clinical decision making and outcome prediction.",
keywords = "Gray-level co-occurrence matrix, Magnetic resonance imaging, Multiple linear regression, Polycystic kidney disease, Total kidney volume",
author = "Timothy Kline and Panagiotis Korfiatis and Edwards, {Marie E.} and Bae, {Kyongtae T.} and Alan Yu and Chapman, {Arlene B.} and Michal Mrug and Grantham, {Jared J.} and Douglas Landsittel and Bennett, {William M.} and King, {Bernard Francis} and Harris, {Peter C} and Vicente Torres and Erickson, {Bradley J}",
year = "2016",
month = "7",
day = "12",
doi = "10.1016/j.kint.2017.03.026",
language = "English (US)",
journal = "Kidney International",
issn = "0085-2538",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Image texture features predict renal function decline in patients with autosomal dominant polycystic kidney disease

AU - Kline, Timothy

AU - Korfiatis, Panagiotis

AU - Edwards, Marie E.

AU - Bae, Kyongtae T.

AU - Yu, Alan

AU - Chapman, Arlene B.

AU - Mrug, Michal

AU - Grantham, Jared J.

AU - Landsittel, Douglas

AU - Bennett, William M.

AU - King, Bernard Francis

AU - Harris, Peter C

AU - Torres, Vicente

AU - Erickson, Bradley J

PY - 2016/7/12

Y1 - 2016/7/12

N2 - Magnetic resonance imaging (MRI) examinations provide high-resolution information about the anatomic structure of the kidneys and are used to measure total kidney volume (TKV) in patients with Autosomal Dominant Polycystic Kidney Disease (ADPKD). Height-adjusted TKV (HtTKV) has become the gold-standard imaging biomarker for ADPKD progression at early stages of the disease when estimated glomerular filtration rate (eGFR) is still normal. However, HtTKV does not take advantage of the wealth of information provided by MRI. Here we tested whether image texture features provide additional insights into the ADPKD kidney that may be used as complementary information to existing biomarkers. A retrospective cohort of 122 patients from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study was identified who had T2-weighted MRIs and eGFR values over 70 mL/min/1.73m2 at the time of their baseline scan. We computed nine distinct image texture features for each patient. The ability of each feature to predict subsequent progression to CKD stage 3A, 3B, and 30% reduction in eGFR at eight-year follow-up was assessed. A multiple linear regression model was developed incorporating age, baseline eGFR, HtTKV, and three image texture features identified by stability feature selection (Entropy, Correlation, and Energy). Including texture in a multiple linear regression model (predicting percent change in eGFR) improved Pearson correlation coefficient from -0.51 (using age, eGFR, and HtTKV) to -0.70 (adding texture). Thus, texture analysis offers an approach to refine ADPKD prognosis and should be further explored for its utility in individualized clinical decision making and outcome prediction.

AB - Magnetic resonance imaging (MRI) examinations provide high-resolution information about the anatomic structure of the kidneys and are used to measure total kidney volume (TKV) in patients with Autosomal Dominant Polycystic Kidney Disease (ADPKD). Height-adjusted TKV (HtTKV) has become the gold-standard imaging biomarker for ADPKD progression at early stages of the disease when estimated glomerular filtration rate (eGFR) is still normal. However, HtTKV does not take advantage of the wealth of information provided by MRI. Here we tested whether image texture features provide additional insights into the ADPKD kidney that may be used as complementary information to existing biomarkers. A retrospective cohort of 122 patients from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study was identified who had T2-weighted MRIs and eGFR values over 70 mL/min/1.73m2 at the time of their baseline scan. We computed nine distinct image texture features for each patient. The ability of each feature to predict subsequent progression to CKD stage 3A, 3B, and 30% reduction in eGFR at eight-year follow-up was assessed. A multiple linear regression model was developed incorporating age, baseline eGFR, HtTKV, and three image texture features identified by stability feature selection (Entropy, Correlation, and Energy). Including texture in a multiple linear regression model (predicting percent change in eGFR) improved Pearson correlation coefficient from -0.51 (using age, eGFR, and HtTKV) to -0.70 (adding texture). Thus, texture analysis offers an approach to refine ADPKD prognosis and should be further explored for its utility in individualized clinical decision making and outcome prediction.

KW - Gray-level co-occurrence matrix

KW - Magnetic resonance imaging

KW - Multiple linear regression

KW - Polycystic kidney disease

KW - Total kidney volume

UR - http://www.scopus.com/inward/record.url?scp=85019847342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019847342&partnerID=8YFLogxK

U2 - 10.1016/j.kint.2017.03.026

DO - 10.1016/j.kint.2017.03.026

M3 - Article

C2 - 28532709

AN - SCOPUS:85019847342

JO - Kidney International

JF - Kidney International

SN - 0085-2538

ER -