AUTHOR=Zhuang Xiamei , Jin Ke , Li Junwei , Yin Yan , Dong Xiao , Lin Huashan 

TITLE=A radiomics-based study of deep medullary veins in infants: Evaluation of neonatal brain injury with hypoxic-ischemic encephalopathy via susceptibility-weighted imaging

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.1093499

DOI=10.3389/fnins.2022.1093499

ISSN=1662-453X

ABSTRACT=Abstract
Objective: The deep medullary veins (DMVs) can be evaluated using susceptibility-weighted imaging (SWI). This study aimed to apply radiomic analysis of the DMVs to evaluate brain injury in neonatal patients with hypoxic-ischemic encephalopathy (HIE) using SWI.
Methods: This study included brain magnetic resonance imaging of 190 infants with HIE and 89 controls. All neonates were born at full-term (37+weeks gestation). To include the DMVs in the regions of interest, manual drawings were performed. A Rad-score was constructed using least absolute shrinkage and selection operator (LASSO) regression to identify the optimal radiomic features. Nomograms were constructed by combining the Rad-score with a clinically independent factor. Receiver operating characteristic curve analysis was applied to evaluate the performance of the different models. Clinical utility was evaluated using a decision curve analysis.
Results: The combined nomogram model incorporating the Rad-score and clinical independent predictors  a better to predict of HIE (in the training cohort, the area under the curve was 0.97, and in the validation cohort, it was 0.95) and the neurologic outcomes after hypoxic-ischemic (in the training cohort, the area under the curve was 0.91, and in the validation cohort, it was 0.88).
Conclusion: Based on radiomic signatures and clinical indicators, we developed a combined nomogram model for evaluating neonatal brain injury associated with perinatal asphyxia.