Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort: evaluation of initial results

Avan Suinesiaputra, Mihir M. Sanghvi, Nay Aung, Jose Miguel Paiva, Filip Zemrak, Kenneth Fung, Elena Lukaschuk, Aaron M. Lee, Valentina Carapella, Youngjin Kim, Jane Francis, Stefan K. Piechnik, Stefan Neubauer, Andreas Greiser, Marie Pierre Jolly, Carmel Hayes, Alistair A. Young, Steffen E. Petersen

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

UK Biobank, a large cohort study, plans to acquire 100,000 cardiac MRI studies by 2020. Although fully-automated left ventricular (LV) analysis was performed in the original acquisition, this was not designed for unsupervised incorporation into epidemiological studies. We sought to evaluate automated LV mass and volume (Siemens syngo InlineVF versions D13A and E11C), against manual analysis in a substantial sub-cohort of UK Biobank participants. Eight readers from two centers, trained to give consistent results, manually analyzed 4874 UK Biobank cases for LV end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF) and LV mass (LVM). Agreement between manual and InlineVF automated analyses were evaluated using Bland–Altman analysis and the intra-class correlation coefficient (ICC). Tenfold cross-validation was used to establish a linear regression calibration between manual and InlineVF results. InlineVF D13A returned results in 4423 cases, whereas InlineVF E11C returned results in 4775 cases and also reported LVM. Rapid visual assessment of the E11C results found 178 cases (3.7%) with grossly misplaced contours or landmarks. In the remaining 4597 cases, LV function showed good agreement: ESV −6.4 ± 9.0 ml, 0.853 (mean ± SD of the differences, ICC) EDV −3.0 ± 11.6 ml, 0.937; SV 3.4 ± 9.8 ml, 0.855; and EF 3.5 ± 5.1%, 0.586. Although LV mass was consistently overestimated (29.9 ± 17.0 g, 0.534) due to larger epicardial contours on all slices, linear regression could be used to correct the bias and improve accuracy. Automated InlineVF results can be used for case-control studies in UK Biobank, provided visual quality control and linear bias correction are performed. Improvements between InlineVF D13A and InlineVF E11C show the field is rapidly advancing, with further improvements expected in the near future.

Original languageEnglish
Pages (from-to)281-291
Number of pages11
JournalInternational Journal of Cardiovascular Imaging
Volume34
Issue number2
DOIs
Publication statusPublished - 2018 Feb 1

Fingerprint

Stroke Volume
Population
Linear Models
Left Ventricular Function
Quality Control
Calibration
Case-Control Studies
Epidemiologic Studies
Cohort Studies

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine

Cite this

Suinesiaputra, Avan ; Sanghvi, Mihir M. ; Aung, Nay ; Paiva, Jose Miguel ; Zemrak, Filip ; Fung, Kenneth ; Lukaschuk, Elena ; Lee, Aaron M. ; Carapella, Valentina ; Kim, Youngjin ; Francis, Jane ; Piechnik, Stefan K. ; Neubauer, Stefan ; Greiser, Andreas ; Jolly, Marie Pierre ; Hayes, Carmel ; Young, Alistair A. ; Petersen, Steffen E. / Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort : evaluation of initial results. In: International Journal of Cardiovascular Imaging. 2018 ; Vol. 34, No. 2. pp. 281-291.
@article{0e648bef18224663afc5e3fde0aea899,
title = "Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort: evaluation of initial results",
abstract = "UK Biobank, a large cohort study, plans to acquire 100,000 cardiac MRI studies by 2020. Although fully-automated left ventricular (LV) analysis was performed in the original acquisition, this was not designed for unsupervised incorporation into epidemiological studies. We sought to evaluate automated LV mass and volume (Siemens syngo InlineVF versions D13A and E11C), against manual analysis in a substantial sub-cohort of UK Biobank participants. Eight readers from two centers, trained to give consistent results, manually analyzed 4874 UK Biobank cases for LV end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF) and LV mass (LVM). Agreement between manual and InlineVF automated analyses were evaluated using Bland–Altman analysis and the intra-class correlation coefficient (ICC). Tenfold cross-validation was used to establish a linear regression calibration between manual and InlineVF results. InlineVF D13A returned results in 4423 cases, whereas InlineVF E11C returned results in 4775 cases and also reported LVM. Rapid visual assessment of the E11C results found 178 cases (3.7{\%}) with grossly misplaced contours or landmarks. In the remaining 4597 cases, LV function showed good agreement: ESV −6.4 ± 9.0 ml, 0.853 (mean ± SD of the differences, ICC) EDV −3.0 ± 11.6 ml, 0.937; SV 3.4 ± 9.8 ml, 0.855; and EF 3.5 ± 5.1{\%}, 0.586. Although LV mass was consistently overestimated (29.9 ± 17.0 g, 0.534) due to larger epicardial contours on all slices, linear regression could be used to correct the bias and improve accuracy. Automated InlineVF results can be used for case-control studies in UK Biobank, provided visual quality control and linear bias correction are performed. Improvements between InlineVF D13A and InlineVF E11C show the field is rapidly advancing, with further improvements expected in the near future.",
author = "Avan Suinesiaputra and Sanghvi, {Mihir M.} and Nay Aung and Paiva, {Jose Miguel} and Filip Zemrak and Kenneth Fung and Elena Lukaschuk and Lee, {Aaron M.} and Valentina Carapella and Youngjin Kim and Jane Francis and Piechnik, {Stefan K.} and Stefan Neubauer and Andreas Greiser and Jolly, {Marie Pierre} and Carmel Hayes and Young, {Alistair A.} and Petersen, {Steffen E.}",
year = "2018",
month = "2",
day = "1",
doi = "10.1007/s10554-017-1225-9",
language = "English",
volume = "34",
pages = "281--291",
journal = "International Journal of Cardiovascular Imaging",
issn = "1569-5794",
publisher = "Springer Netherlands",
number = "2",

}

Suinesiaputra, A, Sanghvi, MM, Aung, N, Paiva, JM, Zemrak, F, Fung, K, Lukaschuk, E, Lee, AM, Carapella, V, Kim, Y, Francis, J, Piechnik, SK, Neubauer, S, Greiser, A, Jolly, MP, Hayes, C, Young, AA & Petersen, SE 2018, 'Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort: evaluation of initial results', International Journal of Cardiovascular Imaging, vol. 34, no. 2, pp. 281-291. https://doi.org/10.1007/s10554-017-1225-9

Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort : evaluation of initial results. / Suinesiaputra, Avan; Sanghvi, Mihir M.; Aung, Nay; Paiva, Jose Miguel; Zemrak, Filip; Fung, Kenneth; Lukaschuk, Elena; Lee, Aaron M.; Carapella, Valentina; Kim, Youngjin; Francis, Jane; Piechnik, Stefan K.; Neubauer, Stefan; Greiser, Andreas; Jolly, Marie Pierre; Hayes, Carmel; Young, Alistair A.; Petersen, Steffen E.

In: International Journal of Cardiovascular Imaging, Vol. 34, No. 2, 01.02.2018, p. 281-291.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fully-automated left ventricular mass and volume MRI analysis in the UK Biobank population cohort

T2 - evaluation of initial results

AU - Suinesiaputra, Avan

AU - Sanghvi, Mihir M.

AU - Aung, Nay

AU - Paiva, Jose Miguel

AU - Zemrak, Filip

AU - Fung, Kenneth

AU - Lukaschuk, Elena

AU - Lee, Aaron M.

AU - Carapella, Valentina

AU - Kim, Youngjin

AU - Francis, Jane

AU - Piechnik, Stefan K.

AU - Neubauer, Stefan

AU - Greiser, Andreas

AU - Jolly, Marie Pierre

AU - Hayes, Carmel

AU - Young, Alistair A.

AU - Petersen, Steffen E.

PY - 2018/2/1

Y1 - 2018/2/1

N2 - UK Biobank, a large cohort study, plans to acquire 100,000 cardiac MRI studies by 2020. Although fully-automated left ventricular (LV) analysis was performed in the original acquisition, this was not designed for unsupervised incorporation into epidemiological studies. We sought to evaluate automated LV mass and volume (Siemens syngo InlineVF versions D13A and E11C), against manual analysis in a substantial sub-cohort of UK Biobank participants. Eight readers from two centers, trained to give consistent results, manually analyzed 4874 UK Biobank cases for LV end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF) and LV mass (LVM). Agreement between manual and InlineVF automated analyses were evaluated using Bland–Altman analysis and the intra-class correlation coefficient (ICC). Tenfold cross-validation was used to establish a linear regression calibration between manual and InlineVF results. InlineVF D13A returned results in 4423 cases, whereas InlineVF E11C returned results in 4775 cases and also reported LVM. Rapid visual assessment of the E11C results found 178 cases (3.7%) with grossly misplaced contours or landmarks. In the remaining 4597 cases, LV function showed good agreement: ESV −6.4 ± 9.0 ml, 0.853 (mean ± SD of the differences, ICC) EDV −3.0 ± 11.6 ml, 0.937; SV 3.4 ± 9.8 ml, 0.855; and EF 3.5 ± 5.1%, 0.586. Although LV mass was consistently overestimated (29.9 ± 17.0 g, 0.534) due to larger epicardial contours on all slices, linear regression could be used to correct the bias and improve accuracy. Automated InlineVF results can be used for case-control studies in UK Biobank, provided visual quality control and linear bias correction are performed. Improvements between InlineVF D13A and InlineVF E11C show the field is rapidly advancing, with further improvements expected in the near future.

AB - UK Biobank, a large cohort study, plans to acquire 100,000 cardiac MRI studies by 2020. Although fully-automated left ventricular (LV) analysis was performed in the original acquisition, this was not designed for unsupervised incorporation into epidemiological studies. We sought to evaluate automated LV mass and volume (Siemens syngo InlineVF versions D13A and E11C), against manual analysis in a substantial sub-cohort of UK Biobank participants. Eight readers from two centers, trained to give consistent results, manually analyzed 4874 UK Biobank cases for LV end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF) and LV mass (LVM). Agreement between manual and InlineVF automated analyses were evaluated using Bland–Altman analysis and the intra-class correlation coefficient (ICC). Tenfold cross-validation was used to establish a linear regression calibration between manual and InlineVF results. InlineVF D13A returned results in 4423 cases, whereas InlineVF E11C returned results in 4775 cases and also reported LVM. Rapid visual assessment of the E11C results found 178 cases (3.7%) with grossly misplaced contours or landmarks. In the remaining 4597 cases, LV function showed good agreement: ESV −6.4 ± 9.0 ml, 0.853 (mean ± SD of the differences, ICC) EDV −3.0 ± 11.6 ml, 0.937; SV 3.4 ± 9.8 ml, 0.855; and EF 3.5 ± 5.1%, 0.586. Although LV mass was consistently overestimated (29.9 ± 17.0 g, 0.534) due to larger epicardial contours on all slices, linear regression could be used to correct the bias and improve accuracy. Automated InlineVF results can be used for case-control studies in UK Biobank, provided visual quality control and linear bias correction are performed. Improvements between InlineVF D13A and InlineVF E11C show the field is rapidly advancing, with further improvements expected in the near future.

UR - http://www.scopus.com/inward/record.url?scp=85027983046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027983046&partnerID=8YFLogxK

U2 - 10.1007/s10554-017-1225-9

DO - 10.1007/s10554-017-1225-9

M3 - Article

C2 - 28836039

AN - SCOPUS:85027983046

VL - 34

SP - 281

EP - 291

JO - International Journal of Cardiovascular Imaging

JF - International Journal of Cardiovascular Imaging

SN - 1569-5794

IS - 2

ER -