King's College London

Research portal

Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool: Evaluation in 1204 healthy adults using unenhanced CT as a reference standard

Research output: Contribution to journalArticlepeer-review

Standard

Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool : Evaluation in 1204 healthy adults using unenhanced CT as a reference standard. / Pickhardt, Perry J.; Blake, Glen M.; Graffy, Peter M. et al.

In: American Journal of Roentgenology, Vol. 217, No. 2, 08.2021, p. 359-367.

Research output: Contribution to journalArticlepeer-review

Harvard

Pickhardt, PJ, Blake, GM, Graffy, PM, Sandfort, V, Elton, DC, Perez, AA & Summers, RM 2021, 'Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool: Evaluation in 1204 healthy adults using unenhanced CT as a reference standard', American Journal of Roentgenology, vol. 217, no. 2, pp. 359-367. https://doi.org/10.2214/AJR.20.24415

APA

Pickhardt, P. J., Blake, G. M., Graffy, P. M., Sandfort, V., Elton, D. C., Perez, A. A., & Summers, R. M. (2021). Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool: Evaluation in 1204 healthy adults using unenhanced CT as a reference standard. American Journal of Roentgenology, 217(2), 359-367. https://doi.org/10.2214/AJR.20.24415

Vancouver

Pickhardt PJ, Blake GM, Graffy PM, Sandfort V, Elton DC, Perez AA et al. Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool: Evaluation in 1204 healthy adults using unenhanced CT as a reference standard. American Journal of Roentgenology. 2021 Aug;217(2):359-367. https://doi.org/10.2214/AJR.20.24415

Author

Pickhardt, Perry J. ; Blake, Glen M. ; Graffy, Peter M. et al. / Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool : Evaluation in 1204 healthy adults using unenhanced CT as a reference standard. In: American Journal of Roentgenology. 2021 ; Vol. 217, No. 2. pp. 359-367.

Bibtex Download

@article{b8b88a7cba6c47cf8548e34a1ca6eb84,
title = "Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool: Evaluation in 1204 healthy adults using unenhanced CT as a reference standard",
abstract = "BACKGROUND. Hepatic attenuation at unenhanced CT is linearly correlated with the MRI proton density fat fraction (PDFF). Liver fat quantification at contrast-enhanced CT is more challenging. OBJECTIVE. The purpose of this article is to evaluate liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric hepatosplenic segmentation algorithm and unenhanced CT as the reference standard. METHODS. A fully automated volumetric hepatosplenic segmentation algorithm using 3D convolutional neural networks was applied to unenhanced and contrast-enhanced series from a sample of 1204 healthy adults (mean age, 45.2 years; 726 women, 478 men) undergoing CT evaluation for renal donation. The mean volumetric attenuation was computed from all designated liver and spleen voxels. PDFF was estimated from unenhanced CT attenuation and served as the reference standard. Contrast-enhanced attenuations were evaluated for detecting PDFF thresholds of 5% (mild steatosis, 10% and 15% (moderate steatosis); PDFF less than 5% was considered normal. RESULTS. Using unenhanced CT as reference, estimated PDFF was ≥ 5% (mild steatosis), ≥ 10%, and ≥ 15% (moderate steatosis) in 50.1% (n = 603), 12.5% (n = 151) and 4.8% (n = 58) of patients, respectively. ROC AUC values for predicting PDFF thresholds of 5%, 10%, and 15% using contrast-enhanced liver attenuation were 0.669, 0.854, and 0.962, respectively, and using contrast-enhanced liver-spleen attenuation difference were 0.662, 0.866, and 0.986, respectively. A total of 96.8% (90/93) of patients with contrast-enhanced liver attenuation less than 90 HU had steatosis (PDFF ≥ 5%); this threshold of less than 90 HU achieved sensitivity of 75.9% and specificity of 95.7% for moderate steatosis (PDFF ≥ 15%). Liver attenuation less than 100 HU achieved sensitivity of 34.0% and specificity of 94.2% for any steatosis (PDFF ≥ 5%). A total of 93.8% (30/32) of patients with contrast-enhanced liver-spleen attenuation difference 10 HU or less had moderate steatosis (PDFF ≥ 15%); a liver-spleen difference less than 5 HU achieved sensitivity of 91.4% and specificity of 95.0% for moderate steatosis. Liver-spleen difference less than 10 HU achieved sensitivity of 29.5% and specificity of 95.5% for any steatosis (PDFF ≥ 5%). CONCLUSION. Contrast-enhanced volumetric hepatosplenic attenuation derived using a fully automated deep learning CT tool may allow objective categoric assessment of hepatic steatosis. Accuracy was better for moderate than mild steatosis. Further confirmation using different scanning protocols and vendors is warranted. CLINICAL IMPACT. If these results are confirmed in independent patient samples, this automated approach could prove useful for both individualized and population-based steatosis assessment.",
keywords = "Artificial intelligence, CT, Deep learning, NAFLD, Steatosis",
author = "Pickhardt, {Perry J.} and Blake, {Glen M.} and Graffy, {Peter M.} and Veit Sandfort and Elton, {Daniel C.} and Perez, {Alberto A.} and Summers, {Ronald M.}",
note = "Funding Information: Supported in part by the Intramural Research Program of the National Institutes of Health (NIH) Clinical Center and conducted using the high performance computing capabilities of the NIH Biowulf cluster. Publisher Copyright: {\textcopyright} American Roentgen Ray Society Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",
year = "2021",
month = aug,
doi = "10.2214/AJR.20.24415",
language = "English",
volume = "217",
pages = "359--367",
journal = "American Journal of Roentgenology",
issn = "0361-803X",
publisher = "American Roentgen Ray Society (ARRS)",
number = "2",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric segmentation tool

T2 - Evaluation in 1204 healthy adults using unenhanced CT as a reference standard

AU - Pickhardt, Perry J.

AU - Blake, Glen M.

AU - Graffy, Peter M.

AU - Sandfort, Veit

AU - Elton, Daniel C.

AU - Perez, Alberto A.

AU - Summers, Ronald M.

N1 - Funding Information: Supported in part by the Intramural Research Program of the National Institutes of Health (NIH) Clinical Center and conducted using the high performance computing capabilities of the NIH Biowulf cluster. Publisher Copyright: © American Roentgen Ray Society Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/8

Y1 - 2021/8

N2 - BACKGROUND. Hepatic attenuation at unenhanced CT is linearly correlated with the MRI proton density fat fraction (PDFF). Liver fat quantification at contrast-enhanced CT is more challenging. OBJECTIVE. The purpose of this article is to evaluate liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric hepatosplenic segmentation algorithm and unenhanced CT as the reference standard. METHODS. A fully automated volumetric hepatosplenic segmentation algorithm using 3D convolutional neural networks was applied to unenhanced and contrast-enhanced series from a sample of 1204 healthy adults (mean age, 45.2 years; 726 women, 478 men) undergoing CT evaluation for renal donation. The mean volumetric attenuation was computed from all designated liver and spleen voxels. PDFF was estimated from unenhanced CT attenuation and served as the reference standard. Contrast-enhanced attenuations were evaluated for detecting PDFF thresholds of 5% (mild steatosis, 10% and 15% (moderate steatosis); PDFF less than 5% was considered normal. RESULTS. Using unenhanced CT as reference, estimated PDFF was ≥ 5% (mild steatosis), ≥ 10%, and ≥ 15% (moderate steatosis) in 50.1% (n = 603), 12.5% (n = 151) and 4.8% (n = 58) of patients, respectively. ROC AUC values for predicting PDFF thresholds of 5%, 10%, and 15% using contrast-enhanced liver attenuation were 0.669, 0.854, and 0.962, respectively, and using contrast-enhanced liver-spleen attenuation difference were 0.662, 0.866, and 0.986, respectively. A total of 96.8% (90/93) of patients with contrast-enhanced liver attenuation less than 90 HU had steatosis (PDFF ≥ 5%); this threshold of less than 90 HU achieved sensitivity of 75.9% and specificity of 95.7% for moderate steatosis (PDFF ≥ 15%). Liver attenuation less than 100 HU achieved sensitivity of 34.0% and specificity of 94.2% for any steatosis (PDFF ≥ 5%). A total of 93.8% (30/32) of patients with contrast-enhanced liver-spleen attenuation difference 10 HU or less had moderate steatosis (PDFF ≥ 15%); a liver-spleen difference less than 5 HU achieved sensitivity of 91.4% and specificity of 95.0% for moderate steatosis. Liver-spleen difference less than 10 HU achieved sensitivity of 29.5% and specificity of 95.5% for any steatosis (PDFF ≥ 5%). CONCLUSION. Contrast-enhanced volumetric hepatosplenic attenuation derived using a fully automated deep learning CT tool may allow objective categoric assessment of hepatic steatosis. Accuracy was better for moderate than mild steatosis. Further confirmation using different scanning protocols and vendors is warranted. CLINICAL IMPACT. If these results are confirmed in independent patient samples, this automated approach could prove useful for both individualized and population-based steatosis assessment.

AB - BACKGROUND. Hepatic attenuation at unenhanced CT is linearly correlated with the MRI proton density fat fraction (PDFF). Liver fat quantification at contrast-enhanced CT is more challenging. OBJECTIVE. The purpose of this article is to evaluate liver steatosis categorization on contrast-enhanced CT using a fully automated deep learning volumetric hepatosplenic segmentation algorithm and unenhanced CT as the reference standard. METHODS. A fully automated volumetric hepatosplenic segmentation algorithm using 3D convolutional neural networks was applied to unenhanced and contrast-enhanced series from a sample of 1204 healthy adults (mean age, 45.2 years; 726 women, 478 men) undergoing CT evaluation for renal donation. The mean volumetric attenuation was computed from all designated liver and spleen voxels. PDFF was estimated from unenhanced CT attenuation and served as the reference standard. Contrast-enhanced attenuations were evaluated for detecting PDFF thresholds of 5% (mild steatosis, 10% and 15% (moderate steatosis); PDFF less than 5% was considered normal. RESULTS. Using unenhanced CT as reference, estimated PDFF was ≥ 5% (mild steatosis), ≥ 10%, and ≥ 15% (moderate steatosis) in 50.1% (n = 603), 12.5% (n = 151) and 4.8% (n = 58) of patients, respectively. ROC AUC values for predicting PDFF thresholds of 5%, 10%, and 15% using contrast-enhanced liver attenuation were 0.669, 0.854, and 0.962, respectively, and using contrast-enhanced liver-spleen attenuation difference were 0.662, 0.866, and 0.986, respectively. A total of 96.8% (90/93) of patients with contrast-enhanced liver attenuation less than 90 HU had steatosis (PDFF ≥ 5%); this threshold of less than 90 HU achieved sensitivity of 75.9% and specificity of 95.7% for moderate steatosis (PDFF ≥ 15%). Liver attenuation less than 100 HU achieved sensitivity of 34.0% and specificity of 94.2% for any steatosis (PDFF ≥ 5%). A total of 93.8% (30/32) of patients with contrast-enhanced liver-spleen attenuation difference 10 HU or less had moderate steatosis (PDFF ≥ 15%); a liver-spleen difference less than 5 HU achieved sensitivity of 91.4% and specificity of 95.0% for moderate steatosis. Liver-spleen difference less than 10 HU achieved sensitivity of 29.5% and specificity of 95.5% for any steatosis (PDFF ≥ 5%). CONCLUSION. Contrast-enhanced volumetric hepatosplenic attenuation derived using a fully automated deep learning CT tool may allow objective categoric assessment of hepatic steatosis. Accuracy was better for moderate than mild steatosis. Further confirmation using different scanning protocols and vendors is warranted. CLINICAL IMPACT. If these results are confirmed in independent patient samples, this automated approach could prove useful for both individualized and population-based steatosis assessment.

KW - Artificial intelligence

KW - CT

KW - Deep learning

KW - NAFLD

KW - Steatosis

UR - http://www.scopus.com/inward/record.url?scp=85111217753&partnerID=8YFLogxK

U2 - 10.2214/AJR.20.24415

DO - 10.2214/AJR.20.24415

M3 - Article

C2 - 32936018

AN - SCOPUS:85111217753

VL - 217

SP - 359

EP - 367

JO - American Journal of Roentgenology

JF - American Journal of Roentgenology

SN - 0361-803X

IS - 2

ER -

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454