Abstract
Background: The known primary radiological diagnosis of Chiari
Malformation-I (CM-I) is based on the degree of tonsillar herniation (
TH) below the Foramen Magnum (FM). However, recent data also shows the
association of such malformation with smaller posterior cranial fossa
(PCF) volume and the anatomical issues regarding the Odontoid. This
study presents the achieved result regarding some detected potential
radiological findings that may aid
CM-I diagnosis using several
machine learning (ML) algorithms.
Materials and Methods: Between 2011 and 2020, radiological
examinations of 100 clinically/radiologically proved symptomatic CM-I
cases and 100 control were evaluated by matching age and gender. A team
of Neuroradiologists had reviewed the MR images of the study population.
A total of 11 different radiological parameters were assessed for CM-I
diagnosis. The parameters were defined and examined in 5 designed
different ML algorithms. Statistical analysis was conducted for data
analysis.
Results: The mean age of patients was 29.92 ± 15.03 years. The
primary presenting symptoms were headaches (62%). Syringomyelia and
retrocurved-odontoid were detected in 34% and 8% of patients,
respectively. All of the morphometric measures were significantly
different between the groups, except for the distance from the dens axis
to the posterior margin of FM. The Radom Forest model is found to have
the best 1.0 (14 of 14) ratio of accuracy in regard to 14 different
combinations of morphometric features.
Conclusion: This study indicates the potential usefulness of
ML-guided PCF measurements, other than TH, that may be used to predict
and diagnose CM-I accurately. Our results support the view of TH as a
single radiological parameter may fail during the diagnosis of CM-I.
Combining two or three preferable osseous structure-based parameters may
increase the accuracy of radiological diagnosis of CM-I.
Key Words: Chiari Malformation; Machine Learning; posterior
fossa; tonsillar herniation.