Unknown

Dataset Information

0

Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy.


ABSTRACT: A fully automatic method for detection and quantification of ischemic lesions in diffusion-weighted MR images of neonatal hypoxic ischemic encephalopathy (HIE) is presented. Ischemic lesions are manually segmented by two independent observers in 1.5 T data from 20 subjects and an automatic algorithm using a random forest classifier is developed and trained on the annotations of observer 1. The algorithm obtains a median sensitivity and specificity of 0.72 and 0.99 respectively. F1-scores are calculated per subject for algorithm performance (median = 0.52) and observer 2 performance (median = 0.56). A paired t-test on the F1-scores shows no statistical difference between the algorithm and observer 2 performances. The method is applied to a larger dataset including 54 additional subjects scanned at both 1.5 T and 3.0 T. The algorithm findings are shown to correspond well with the injury pattern noted by clinicians in both 1.5 T and 3.0 T data and to have a strong relationship with outcome. The results of the automatic method are condensed to a single score for each subject which has significant correlation with an MR score assigned by experienced clinicians (p < 0.0001). This work represents a quantitative method of evaluating diffusion-weighted MR images in neonatal HIE and a first step in the development of an automatic system for more in-depth analysis and prognostication.

SUBMITTER: Murphy K 

PROVIDER: S-EPMC5288491 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

altmetric image

Publications

Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy.

Murphy Keelin K   van der Aa Niek E NE   Negro Simona S   Groenendaal Floris F   de Vries Linda S LS   Viergever Max A MA   Boylan Geraldine B GB   Benders Manon J N L MJ   Išgum Ivana I  

NeuroImage. Clinical 20170111


A fully automatic method for detection and quantification of ischemic lesions in diffusion-weighted MR images of neonatal hypoxic ischemic encephalopathy (HIE) is presented. Ischemic lesions are manually segmented by two independent observers in 1.5 T data from 20 subjects and an automatic algorithm using a random forest classifier is developed and trained on the annotations of observer 1. The algorithm obtains a median sensitivity and specificity of 0.72 and 0.99 respectively. F1-scores are cal  ...[more]

Similar Datasets

| S-EPMC6219383 | biostudies-literature
| S-EPMC4613313 | biostudies-literature
| S-EPMC9771796 | biostudies-literature
| S-EPMC4297029 | biostudies-other
| S-EPMC5509506 | biostudies-literature
| S-EPMC3299861 | biostudies-other
| S-EPMC5960435 | biostudies-literature
| S-EPMC9768655 | biostudies-literature
| S-EPMC9290624 | biostudies-literature
| S-EPMC8797213 | biostudies-literature