Jieun Byun1,2, Seongkeun Park3, Ji Su Ko4, Ji Young Woo4. 1. Department of Radiology, Hallym University College of Medicine, Kangnam Sacred Heart Hospital, Seoul, Republic of Korea. sueno54@naver.com. 2. Department of Radiology, College of Medicine, Ewha Womans University, Seoul, Republic of Korea. sueno54@naver.com. 3. Machine Intelligence Laboratory, Department of Smart Automobile, Soonchunhyang University, Asan, Chungcheongnamdo, Republic of Korea. 4. Department of Radiology, Hallym University College of Medicine, Kangnam Sacred Heart Hospital, Seoul, Republic of Korea.
Abstract
PURPOSE: The purpose of this study was to reveal the usefulness of machine learning classifier and feature selection algorithms for prediction of insufficient hepatic enhancement in the HBP. METHODS: We retrospectively assessed 214 patients with chronic liver disease or liver cirrhosis who underwent MRI enhanced with Gd-EOB-DTPA. Various liver function tests, Child-Pugh score (CPS) and Model for End-stage Liver Disease Sodium (MELD-Na) score were collected as candidate predictors for insufficient hepatic enhancement. Insufficient hepatic enhancement was assessed using liver-to-portal vein signal intensity ratio and 5-level visual grading. The clinico-laboratory findings were compared using Student's t-test and Mann-Whitney U test. Relationships between the laboratory tests and insufficient hepatic enhancement were assessed using Pearson's and Spearman's rank correlation coefficient. Feature importance was assessed by Random UnderSampling boosting algorithms. The predictive models were constructed using decision tree(DT), k-nearest neighbor(KNN), random forest(RF), and support-vector machine(SVM) classifier algorithms. The performances of the prediction models were analyzed by calculating the area under the receiver operating characteristic curve(AUC). RESULTS: Among four machine learning classifier algorithms using various feature combinations, SVM using total bilirubin(TB) and albumin(Alb) showed excellent predictive ability for insufficient hepatic enhancement(AUC = 0.93, [95% CI: 0.93-0.94]) and higher AUC value than conventional logistic regression(LR) model (AUC = 0.92, [95% CI; 0.92-0.93], predictive models using the MELD-Na (AUC = 0.90 [95% CI: 0.89-0.91]) and CPS (AUC = 0.89 [95% CI: 0.88-0.90]). CONCLUSION: Machine learning-based classifier (i.e. SVM) and feature selection algorithms can be used to predict insufficient hepatic enhancement in the HBP before performing MRI.
PURPOSE: The purpose of this study was to reveal the usefulness of machine learning classifier and feature selection algorithms for prediction of insufficient hepatic enhancement in the HBP. METHODS: We retrospectively assessed 214 patients with chronic liver disease or liver cirrhosis who underwent MRI enhanced with Gd-EOB-DTPA. Various liver function tests, Child-Pugh score (CPS) and Model for End-stage Liver Disease Sodium (MELD-Na) score were collected as candidate predictors for insufficient hepatic enhancement. Insufficient hepatic enhancement was assessed using liver-to-portal vein signal intensity ratio and 5-level visual grading. The clinico-laboratory findings were compared using Student's t-test and Mann-Whitney U test. Relationships between the laboratory tests and insufficient hepatic enhancement were assessed using Pearson's and Spearman's rank correlation coefficient. Feature importance was assessed by Random UnderSampling boosting algorithms. The predictive models were constructed using decision tree(DT), k-nearest neighbor(KNN), random forest(RF), and support-vector machine(SVM) classifier algorithms. The performances of the prediction models were analyzed by calculating the area under the receiver operating characteristic curve(AUC). RESULTS: Among four machine learning classifier algorithms using various feature combinations, SVM using total bilirubin(TB) and albumin(Alb) showed excellent predictive ability for insufficient hepatic enhancement(AUC = 0.93, [95% CI: 0.93-0.94]) and higher AUC value than conventional logistic regression(LR) model (AUC = 0.92, [95% CI; 0.92-0.93], predictive models using the MELD-Na (AUC = 0.90 [95% CI: 0.89-0.91]) and CPS (AUC = 0.89 [95% CI: 0.88-0.90]). CONCLUSION: Machine learning-based classifier (i.e. SVM) and feature selection algorithms can be used to predict insufficient hepatic enhancement in the HBP before performing MRI.
Authors: N Verloh; M Haimerl; J Rennert; R Müller-Wille; C Nießen; G Kirchner; M N Scherer; A G Schreyer; C Stroszczynski; C Fellner; P Wiggermann Journal: Eur J Radiol Date: 2013-06-25 Impact factor: 3.528
Authors: B Hamm; T Staks; A Mühler; M Bollow; M Taupitz; T Frenzel; K J Wolf; H J Weinmann; L Lange Journal: Radiology Date: 1995-06 Impact factor: 11.105
Authors: Ah Yeong Kim; Young Kon Kim; Min Woo Lee; Min Jung Park; Jiyoung Hwang; Mi Hee Lee; Jae Won Lee Journal: Acta Radiol Date: 2012-07-30 Impact factor: 1.990