Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Disease

Maatje D.A. van Gastel, Marie E. Edwards, Vicente Torres, Bradley J Erickson, Ron T. Gansevoort, Timothy Kline

Research output: Contribution to journalArticle

Abstract

BACKGROUND: The formation and growth of cysts in kidneys, and often liver, in autosomal dominant polycystic kidney disease (ADPKD) cause progressive increases in total kidney volume (TKV) and liver volume (TLV). Laborious and time-consuming manual tracing of kidneys and liver is the current gold standard. We developed a fully automated segmentation method for TKV and TLV measurement that uses a deep learning network optimized to perform semantic segmentation of kidneys and liver. METHODS: We used 80% of a set of 440 abdominal magnetic resonance images (T2-weighted HASTE coronal sequences) from patients with ADPKD to train the network and the remaining 20% for validation. Both kidneys and liver were also segmented manually. To evaluate the method's performance, we used an additional test set of images from 100 patients, 45 of whom were also involved in longitudinal analyses. RESULTS: TKV and TLV measured by the automated approach correlated highly with manually traced TKV and TLV (intraclass correlation coefficients, 0.998 and 0.996, respectively), with low bias and high precision (<0.1%±2.7% for TKV and -1.6%±3.1% for TLV); this was comparable with inter-reader variability of manual tracing (<0.1%±3.5% for TKV and -1.5%±4.8% for TLV). For longitudinal analysis, bias and precision were <0.1%±3.2% for TKV and 1.4%±2.9% for TLV growth. CONCLUSIONS: These findings demonstrate a fully automated segmentation method that measures TKV, TLV, and changes in these parameters as accurately as manual tracing. This technique may facilitate future studies in which automated and reproducible TKV and TLV measurements are needed to assess disease severity, disease progression, and treatment response.

Original languageEnglish (US)
Pages (from-to)1514-1522
Number of pages9
JournalJournal of the American Society of Nephrology : JASN
Volume30
Issue number8
DOIs
StatePublished - Aug 1 2019

Fingerprint

Autosomal Dominant Polycystic Kidney
Kidney
Liver
Growth
Semantics
Disease Progression
Cysts

Keywords

  • deep learning
  • liver volume
  • magnetic resonance imaging
  • polycystic kidney disease
  • segmentation
  • total kidney volume

ASJC Scopus subject areas

  • Nephrology

Cite this

Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Disease. / van Gastel, Maatje D.A.; Edwards, Marie E.; Torres, Vicente; Erickson, Bradley J; Gansevoort, Ron T.; Kline, Timothy.

In: Journal of the American Society of Nephrology : JASN, Vol. 30, No. 8, 01.08.2019, p. 1514-1522.

Research output: Contribution to journalArticle

@article{960760bd01d741fca8f5413314dd89f3,
title = "Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Disease",
abstract = "BACKGROUND: The formation and growth of cysts in kidneys, and often liver, in autosomal dominant polycystic kidney disease (ADPKD) cause progressive increases in total kidney volume (TKV) and liver volume (TLV). Laborious and time-consuming manual tracing of kidneys and liver is the current gold standard. We developed a fully automated segmentation method for TKV and TLV measurement that uses a deep learning network optimized to perform semantic segmentation of kidneys and liver. METHODS: We used 80{\%} of a set of 440 abdominal magnetic resonance images (T2-weighted HASTE coronal sequences) from patients with ADPKD to train the network and the remaining 20{\%} for validation. Both kidneys and liver were also segmented manually. To evaluate the method's performance, we used an additional test set of images from 100 patients, 45 of whom were also involved in longitudinal analyses. RESULTS: TKV and TLV measured by the automated approach correlated highly with manually traced TKV and TLV (intraclass correlation coefficients, 0.998 and 0.996, respectively), with low bias and high precision (<0.1{\%}±2.7{\%} for TKV and -1.6{\%}±3.1{\%} for TLV); this was comparable with inter-reader variability of manual tracing (<0.1{\%}±3.5{\%} for TKV and -1.5{\%}±4.8{\%} for TLV). For longitudinal analysis, bias and precision were <0.1{\%}±3.2{\%} for TKV and 1.4{\%}±2.9{\%} for TLV growth. CONCLUSIONS: These findings demonstrate a fully automated segmentation method that measures TKV, TLV, and changes in these parameters as accurately as manual tracing. This technique may facilitate future studies in which automated and reproducible TKV and TLV measurements are needed to assess disease severity, disease progression, and treatment response.",
keywords = "deep learning, liver volume, magnetic resonance imaging, polycystic kidney disease, segmentation, total kidney volume",
author = "{van Gastel}, {Maatje D.A.} and Edwards, {Marie E.} and Vicente Torres and Erickson, {Bradley J} and Gansevoort, {Ron T.} and Timothy Kline",
year = "2019",
month = "8",
day = "1",
doi = "10.1681/ASN.2018090902",
language = "English (US)",
volume = "30",
pages = "1514--1522",
journal = "Journal of the American Society of Nephrology : JASN",
issn = "1046-6673",
publisher = "American Society of Nephrology",
number = "8",

}

TY - JOUR

T1 - Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Disease

AU - van Gastel, Maatje D.A.

AU - Edwards, Marie E.

AU - Torres, Vicente

AU - Erickson, Bradley J

AU - Gansevoort, Ron T.

AU - Kline, Timothy

PY - 2019/8/1

Y1 - 2019/8/1

N2 - BACKGROUND: The formation and growth of cysts in kidneys, and often liver, in autosomal dominant polycystic kidney disease (ADPKD) cause progressive increases in total kidney volume (TKV) and liver volume (TLV). Laborious and time-consuming manual tracing of kidneys and liver is the current gold standard. We developed a fully automated segmentation method for TKV and TLV measurement that uses a deep learning network optimized to perform semantic segmentation of kidneys and liver. METHODS: We used 80% of a set of 440 abdominal magnetic resonance images (T2-weighted HASTE coronal sequences) from patients with ADPKD to train the network and the remaining 20% for validation. Both kidneys and liver were also segmented manually. To evaluate the method's performance, we used an additional test set of images from 100 patients, 45 of whom were also involved in longitudinal analyses. RESULTS: TKV and TLV measured by the automated approach correlated highly with manually traced TKV and TLV (intraclass correlation coefficients, 0.998 and 0.996, respectively), with low bias and high precision (<0.1%±2.7% for TKV and -1.6%±3.1% for TLV); this was comparable with inter-reader variability of manual tracing (<0.1%±3.5% for TKV and -1.5%±4.8% for TLV). For longitudinal analysis, bias and precision were <0.1%±3.2% for TKV and 1.4%±2.9% for TLV growth. CONCLUSIONS: These findings demonstrate a fully automated segmentation method that measures TKV, TLV, and changes in these parameters as accurately as manual tracing. This technique may facilitate future studies in which automated and reproducible TKV and TLV measurements are needed to assess disease severity, disease progression, and treatment response.

AB - BACKGROUND: The formation and growth of cysts in kidneys, and often liver, in autosomal dominant polycystic kidney disease (ADPKD) cause progressive increases in total kidney volume (TKV) and liver volume (TLV). Laborious and time-consuming manual tracing of kidneys and liver is the current gold standard. We developed a fully automated segmentation method for TKV and TLV measurement that uses a deep learning network optimized to perform semantic segmentation of kidneys and liver. METHODS: We used 80% of a set of 440 abdominal magnetic resonance images (T2-weighted HASTE coronal sequences) from patients with ADPKD to train the network and the remaining 20% for validation. Both kidneys and liver were also segmented manually. To evaluate the method's performance, we used an additional test set of images from 100 patients, 45 of whom were also involved in longitudinal analyses. RESULTS: TKV and TLV measured by the automated approach correlated highly with manually traced TKV and TLV (intraclass correlation coefficients, 0.998 and 0.996, respectively), with low bias and high precision (<0.1%±2.7% for TKV and -1.6%±3.1% for TLV); this was comparable with inter-reader variability of manual tracing (<0.1%±3.5% for TKV and -1.5%±4.8% for TLV). For longitudinal analysis, bias and precision were <0.1%±3.2% for TKV and 1.4%±2.9% for TLV growth. CONCLUSIONS: These findings demonstrate a fully automated segmentation method that measures TKV, TLV, and changes in these parameters as accurately as manual tracing. This technique may facilitate future studies in which automated and reproducible TKV and TLV measurements are needed to assess disease severity, disease progression, and treatment response.

KW - deep learning

KW - liver volume

KW - magnetic resonance imaging

KW - polycystic kidney disease

KW - segmentation

KW - total kidney volume

UR - http://www.scopus.com/inward/record.url?scp=85070850763&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070850763&partnerID=8YFLogxK

U2 - 10.1681/ASN.2018090902

DO - 10.1681/ASN.2018090902

M3 - Article

VL - 30

SP - 1514

EP - 1522

JO - Journal of the American Society of Nephrology : JASN

JF - Journal of the American Society of Nephrology : JASN

SN - 1046-6673

IS - 8

ER -