[Skip to Content]
[Skip to Content Landing]
Original Investigation
February 2018

Use of Fetal Magnetic Resonance Image Analysis and Machine Learning to Predict the Need for Postnatal Cerebrospinal Fluid Diversion in Fetal Ventriculomegaly

Author Affiliations
  • 1Department of Neurosurgery, University of Pennsylvania, Philadelphia
  • 2Center for Biomedical Image Computing and Analytics, University of Pennsylvania, Philadelphia
  • 3Department of Neurosurgery, Columbia University Medical Center, New York, New York
  • 4Center for Fetal Diagnosis and Treatment, Special Delivery Unit, Children’s Hospital of Philadelphia, Philadelphia, Pennsylvania
  • 5Division of Neurosurgery, Children’s Hospital of Philadelphia, Philadelphia, Pennsylvania
  • 6Division of Neuroradiology, Children’s Hospital of Philadelphia, Philadelphia, Pennsylvania
JAMA Pediatr. 2018;172(2):128-135. doi:10.1001/jamapediatrics.2017.3993
Key Points

Question  Can fetal magnetic resonance imaging be used to predict the need for postnatal cerebrospinal fluid diversion in patients with fetal ventriculomegaly?

Findings  In this case-control study of 50 patients with fetal ventriculomegaly, multiple imaging features were extracted from fetal magnetic resonance imaging and integrated by machine learning to yield a model that correctly classified postnatal cerebrospinal fluid diversion status with 82% accuracy. In an independent replication cohort study, the model achieved 91% accuracy.

Meaning  An image-based predictive model with high accuracy and generalizability may provide prenatal prognostic information and help guide postnatal clinical management in fetal ventriculomegaly.

Abstract

Importance  Which children with fetal ventriculomegaly, or enlargement of the cerebral ventricles in utero, will develop hydrocephalus requiring treatment after birth is unclear.

Objective  To determine whether extraction of multiple imaging features from fetal magnetic resonance imaging (MRI) and integration using machine learning techniques can predict which patients require postnatal cerebrospinal fluid (CSF) diversion after birth.

Design, Setting, and Patients  This retrospective case-control study used an institutional database of 253 patients with fetal ventriculomegaly from January 1, 2008, through December 31, 2014, to generate a predictive model. Data were analyzed from January 1, 2008, through December 31, 2015. All 25 patients who required postnatal CSF diversion were selected and matched by gestational age with 25 patients with fetal ventriculomegaly who did not require CSF diversion (discovery cohort). The model was applied to a sample of 24 consecutive patients with fetal ventriculomegaly who underwent evaluation at a separate institution (replication cohort) from January 1, 1998, through December 31, 2007. Data were analyzed from January 1, 1998, through December 31, 2009.

Exposures  To generate the model, linear measurements, area, volume, and morphologic features were extracted from the fetal MRI, and a machine learning algorithm analyzed multiple features simultaneously to find the combination that was most predictive of the need for postnatal CSF diversion.

Main Outcomes and Measures  Accuracy, sensitivity, and specificity of the model in correctly classifying patients requiring postnatal CSF diversion.

Results  A total of 74 patients (41 girls [55%] and 33 boys [45%]; mean [SD] gestational age, 27.0 [5.6] months) were included from both cohorts. In the discovery cohort, median time to CSF diversion was 6 days (interquartile range [IQR], 2-51 days), and patients with fetal ventriculomegaly who did not develop symptoms were followed up for a median of 29 months (IQR, 9-46 months). The model correctly classified patients who required CSF diversion with 82% accuracy, 80% sensitivity, and 84% specificity. In the replication cohort, the model achieved 91% accuracy, 75% sensitivity, and 95% specificity.

Conclusion and Relevance  Image analysis and machine learning can be applied to fetal MRI findings to predict the need for postnatal CSF diversion. The model provides prognostic information that may guide clinical management and select candidates for potential fetal surgical intervention.

×