Automatic classification of focal liver lesions based on MRI and risk factors

Mariëlle J.A. Jansen (Corresponding author), Hugo J. Kuijf, Wouter B. Veldhuis, Frank J. Wessels, Max A. Viergever, Josien P.W. Pluim

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

OBJECTIVES: Accurate classification of focal liver lesions is an important part of liver disease diagnostics. In clinical practice, the lesion type is often determined from the abdominal MR examination, which includes T2-weighted and dynamic contrast enhanced (DCE) MR images. To date, only T2-weighted images are exploited for automatic classification of focal liver lesions. In this study additional MR sequences and risk factors are used for automatic classification to improve the results and to make a step forward to a clinically useful aid for radiologists.

MATERIALS AND METHODS: Clinical MRI data sets of 95 patients with in total 125 benign lesions (40 adenomas, 29 cysts and 56 hemangiomas) and 88 malignant lesions (30 hepatocellular carcinomas (HCC) and 58 metastases) were included in this study. Contrast curve, gray level histogram, and gray level co-occurrence matrix texture features were extracted from the DCE-MR and T2-weighted images. In addition, risk factors including the presence of steatosis, cirrhosis, and a known primary tumor were used as features. Fifty features with the highest ANOVA F-score were selected and fed to an extremely randomized trees classifier. The classifier evaluation was performed using the leave-one-out principle and receiver operating characteristic (ROC) curve analysis.

RESULTS: The overall accuracy for the classification of the five major focal liver lesion types is 0.77. The sensitivity/specificity is 0.80/0.78, 0.93/0.93, 0.84/0.82, 0.73/0.56, and 0.62/0.77 for adenoma, cyst, hemangioma, HCC, and metastasis, respectively.

CONCLUSION: The proposed classification system using features derived from clinical DCE-MR and T2-weighted images, with additional risk factors is able to differentiate five common types of lesions and is a step forward to a clinically useful aid for focal liver lesion diagnosis.

LanguageEnglish
Article numbere0217053
Number of pages13
JournalPLoS ONE
Volume14
Issue number5
DOIs
StatePublished - 2019

Fingerprint

lesions (animal)
Liver
Magnetic resonance imaging
risk factors
liver
Hemangioma
Adenoma
Cysts
hemangioma
Hepatocellular Carcinoma
Classifiers
adenoma
Neoplasm Metastasis
hepatoma
metastasis
Analysis of variance (ANOVA)
ROC Curve
Liver Diseases
Tumors
Analysis of Variance

Cite this

Jansen, M. J. A., Kuijf, H. J., Veldhuis, W. B., Wessels, F. J., Viergever, M. A., & Pluim, J. P. W. (2019). Automatic classification of focal liver lesions based on MRI and risk factors. PLoS ONE, 14(5), [e0217053]. DOI: 10.1371/journal.pone.0217053
Jansen, Mariëlle J.A. ; Kuijf, Hugo J. ; Veldhuis, Wouter B. ; Wessels, Frank J. ; Viergever, Max A. ; Pluim, Josien P.W./ Automatic classification of focal liver lesions based on MRI and risk factors. In: PLoS ONE. 2019 ; Vol. 14, No. 5.
@article{f1cbd00291364aea92de1b6745b4d118,
title = "Automatic classification of focal liver lesions based on MRI and risk factors",
abstract = "OBJECTIVES: Accurate classification of focal liver lesions is an important part of liver disease diagnostics. In clinical practice, the lesion type is often determined from the abdominal MR examination, which includes T2-weighted and dynamic contrast enhanced (DCE) MR images. To date, only T2-weighted images are exploited for automatic classification of focal liver lesions. In this study additional MR sequences and risk factors are used for automatic classification to improve the results and to make a step forward to a clinically useful aid for radiologists.MATERIALS AND METHODS: Clinical MRI data sets of 95 patients with in total 125 benign lesions (40 adenomas, 29 cysts and 56 hemangiomas) and 88 malignant lesions (30 hepatocellular carcinomas (HCC) and 58 metastases) were included in this study. Contrast curve, gray level histogram, and gray level co-occurrence matrix texture features were extracted from the DCE-MR and T2-weighted images. In addition, risk factors including the presence of steatosis, cirrhosis, and a known primary tumor were used as features. Fifty features with the highest ANOVA F-score were selected and fed to an extremely randomized trees classifier. The classifier evaluation was performed using the leave-one-out principle and receiver operating characteristic (ROC) curve analysis.RESULTS: The overall accuracy for the classification of the five major focal liver lesion types is 0.77. The sensitivity/specificity is 0.80/0.78, 0.93/0.93, 0.84/0.82, 0.73/0.56, and 0.62/0.77 for adenoma, cyst, hemangioma, HCC, and metastasis, respectively.CONCLUSION: The proposed classification system using features derived from clinical DCE-MR and T2-weighted images, with additional risk factors is able to differentiate five common types of lesions and is a step forward to a clinically useful aid for focal liver lesion diagnosis.",
author = "Jansen, {Mari{\"e}lle J.A.} and Kuijf, {Hugo J.} and Veldhuis, {Wouter B.} and Wessels, {Frank J.} and Viergever, {Max A.} and Pluim, {Josien P.W.}",
year = "2019",
doi = "10.1371/journal.pone.0217053",
language = "English",
volume = "14",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "5",

}

Jansen, MJA, Kuijf, HJ, Veldhuis, WB, Wessels, FJ, Viergever, MA & Pluim, JPW 2019, 'Automatic classification of focal liver lesions based on MRI and risk factors' PLoS ONE, vol. 14, no. 5, e0217053. DOI: 10.1371/journal.pone.0217053

Automatic classification of focal liver lesions based on MRI and risk factors. / Jansen, Mariëlle J.A. (Corresponding author); Kuijf, Hugo J.; Veldhuis, Wouter B.; Wessels, Frank J.; Viergever, Max A.; Pluim, Josien P.W.

In: PLoS ONE, Vol. 14, No. 5, e0217053, 2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automatic classification of focal liver lesions based on MRI and risk factors

AU - Jansen,Mariëlle J.A.

AU - Kuijf,Hugo J.

AU - Veldhuis,Wouter B.

AU - Wessels,Frank J.

AU - Viergever,Max A.

AU - Pluim,Josien P.W.

PY - 2019

Y1 - 2019

N2 - OBJECTIVES: Accurate classification of focal liver lesions is an important part of liver disease diagnostics. In clinical practice, the lesion type is often determined from the abdominal MR examination, which includes T2-weighted and dynamic contrast enhanced (DCE) MR images. To date, only T2-weighted images are exploited for automatic classification of focal liver lesions. In this study additional MR sequences and risk factors are used for automatic classification to improve the results and to make a step forward to a clinically useful aid for radiologists.MATERIALS AND METHODS: Clinical MRI data sets of 95 patients with in total 125 benign lesions (40 adenomas, 29 cysts and 56 hemangiomas) and 88 malignant lesions (30 hepatocellular carcinomas (HCC) and 58 metastases) were included in this study. Contrast curve, gray level histogram, and gray level co-occurrence matrix texture features were extracted from the DCE-MR and T2-weighted images. In addition, risk factors including the presence of steatosis, cirrhosis, and a known primary tumor were used as features. Fifty features with the highest ANOVA F-score were selected and fed to an extremely randomized trees classifier. The classifier evaluation was performed using the leave-one-out principle and receiver operating characteristic (ROC) curve analysis.RESULTS: The overall accuracy for the classification of the five major focal liver lesion types is 0.77. The sensitivity/specificity is 0.80/0.78, 0.93/0.93, 0.84/0.82, 0.73/0.56, and 0.62/0.77 for adenoma, cyst, hemangioma, HCC, and metastasis, respectively.CONCLUSION: The proposed classification system using features derived from clinical DCE-MR and T2-weighted images, with additional risk factors is able to differentiate five common types of lesions and is a step forward to a clinically useful aid for focal liver lesion diagnosis.

AB - OBJECTIVES: Accurate classification of focal liver lesions is an important part of liver disease diagnostics. In clinical practice, the lesion type is often determined from the abdominal MR examination, which includes T2-weighted and dynamic contrast enhanced (DCE) MR images. To date, only T2-weighted images are exploited for automatic classification of focal liver lesions. In this study additional MR sequences and risk factors are used for automatic classification to improve the results and to make a step forward to a clinically useful aid for radiologists.MATERIALS AND METHODS: Clinical MRI data sets of 95 patients with in total 125 benign lesions (40 adenomas, 29 cysts and 56 hemangiomas) and 88 malignant lesions (30 hepatocellular carcinomas (HCC) and 58 metastases) were included in this study. Contrast curve, gray level histogram, and gray level co-occurrence matrix texture features were extracted from the DCE-MR and T2-weighted images. In addition, risk factors including the presence of steatosis, cirrhosis, and a known primary tumor were used as features. Fifty features with the highest ANOVA F-score were selected and fed to an extremely randomized trees classifier. The classifier evaluation was performed using the leave-one-out principle and receiver operating characteristic (ROC) curve analysis.RESULTS: The overall accuracy for the classification of the five major focal liver lesion types is 0.77. The sensitivity/specificity is 0.80/0.78, 0.93/0.93, 0.84/0.82, 0.73/0.56, and 0.62/0.77 for adenoma, cyst, hemangioma, HCC, and metastasis, respectively.CONCLUSION: The proposed classification system using features derived from clinical DCE-MR and T2-weighted images, with additional risk factors is able to differentiate five common types of lesions and is a step forward to a clinically useful aid for focal liver lesion diagnosis.

U2 - 10.1371/journal.pone.0217053

DO - 10.1371/journal.pone.0217053

M3 - Article

VL - 14

JO - PLoS ONE

T2 - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 5

M1 - e0217053

ER -

Jansen MJA, Kuijf HJ, Veldhuis WB, Wessels FJ, Viergever MA, Pluim JPW. Automatic classification of focal liver lesions based on MRI and risk factors. PLoS ONE. 2019;14(5). e0217053. Available from, DOI: 10.1371/journal.pone.0217053