Impact Factor 2.635 | CiteScore 2.99
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Neurol. | doi: 10.3389/fneur.2019.01018

Machine Learning Assisted MRI Characterization for Diagnosis of Neonatal Bilirubin Encephalopathy

 Zhou Liu1, 2,  Bing Ji2,  Yuzhong Zhang3, Ge Cui4,  Lijian Liu1, 5, Shuai Man6, Ling Ding3,  Xiaofeng Yang4,  Hui Mao2* and  Liya Wang1, 2, 3*
  • 1Graduate school, Nanchang University School of Medicine, China
  • 2Department of Radiology and Imaging Sciences, Emory University School of Medicine, United States
  • 3Department of Radiology, The People’s Hospital of Longhua, Southern Medical University, China
  • 4Department of Radiation Oncology, Emory University School of Medicine, United States
  • 5Department of Radiology, National Cancer Center/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, China
  • 6Department of Pediatrics, The People’s Hospital of Longhua, Southern Medical University, China

Background: The use of magnetic resonance imaging (MRI) in diagnosis of neonatal acute bilirubin encephalopathy (ABE) in newborns has been limited by its difficulty in differentiating confounding image contrast changes associated with normal myelination. This study is to demonstrate the feasibility of building a machine-learning prediction model based on radiomics features derived from MRI to better characterize and distinguish ABE from normal myelination.
Methods: In this retrospective study, we included 32 neonates with clinically confirmed ABE and 29 age-matched controls with normal myelination. Radiomics features were extracted from the manually segmented region of interest (ROI) on T1-weighted spin echo images, followed by the feature selection using two-sample independent t-test, least absolute shrinkage and selection operator (Lasso) regression and Pearson’s correlation matrix. Additional feature quantifying the relative mean intensity of ROI was defined and calculated. A prediction model based on the selected features was built to classify ABE and normal myelination using multiple machine learning classifiers and a leave-one-out cross-validation scheme. Receiver operating characteristics (ROC) analysis was used to evaluate the prediction performance with the area under the curve (AUC) and feature importance ranked based on the Fisher score.
Results: Among 1319 radiomics features, one radiologist-defined intensity-based feature and 12 texture features were selected as the most discriminative features. Based on these features, decision trees had the best classification performance with the largest AUC of 0.946, followed by support vector machine (SVM), tree-bagger, logistic regression, Naïve Bayes, discriminant analysis, k-nearest neighborhood (KNN), which have an AUC of 0.931, 0.925, 0.905, 0.891, 0.883, and 0.817, respectively. The relative mean intensity outperformed other 12 texture features in differentiating ABE from controls.
Conclusions: The results from this study demonstrated a new strategy of characterizing ABE-induced intensity changes and morphological changes in MRI, which are difficult to be recognized, interpreted or quantified by the routine experience and visual-based reading strategy. With more quantitative and objective measurements, the reported machine learning assisted radiomics features-based approach can improve the diagnosis and support clinical decision-making.

Keywords: Magnetic Resonance Imaging, neonate, Bilirubin encephalopathy, Normal Myelination, machine learning, Radiomics

Received: 12 Mar 2019; Accepted: 09 Sep 2019.

Copyright: © 2019 Liu, Ji, Zhang, Cui, Liu, Man, Ding, Yang, Mao and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
PhD. Hui Mao, Emory University School of Medicine, Department of Radiology and Imaging Sciences, Atlanta, 30322, Georgia, United States, hmao@emory.edu
MD. Liya Wang, Nanchang University School of Medicine, Graduate school, Nanchang, China, 2718377613@qq.com