Brain and Ventricle Volume Alterations in Idiopathic Normal Pressure Hydrocephalus Determined by Artificial Intelligence-Based MRI Volumetry

Abstract

The aim of this study was to employ artificial intelligence (AI)-based magnetic resonance imaging (MRI) brain volumetry to potentially distinguish between idiopathic normal pressure hydrocephalus (iNPH), Alzheimer's disease (AD), and age- and sex-matched healthy controls (CG) by evaluating cortical, subcortical, and ventricular volumes. Additionally, correlations between the measured brain and ventricle volumes and two established semi-quantitative radiologic markers for iNPH were examined. An IRB-approved retrospective analysis was conducted on 123 age- and sex-matched subjects (41 iNPH, 41 AD, and 41 controls), with all of the iNPH patients undergoing routine clinical brain MRI prior to ventriculoperitoneal shunt implantation. Automated AI-based determination of different cortical and subcortical brain and ventricular volumes in mL, as well as calculation of population-based normalized percentiles according to an embedded database, was performed; the CE-certified software mdbrain v4.4.1 or above was used with a standardized T1-weighted 3D magnetization-prepared rapid gradient echo (MPRAGE) sequence. Measured brain volumes and percentiles were analyzed for between-group differences and correlated with semi-quantitative measurements of the Evans' index and corpus callosal angle: iNPH patients exhibited ventricular enlargement and changes in gray and white matter compared to AD patients and controls, with the most significant differences observed in total ventricular volume (+67%) and the lateral (+68%), third (+38%), and fourth (+31%) ventricles compared to controls. Global ventriculomegaly and marked white matter reduction with concomitant preservation of gray matter compared to AD and CG were characteristic of iNPH, whereas global and frontoparietally accentuated gray matter reductions were characteristic of AD. Evans' index and corpus callosal angle differed significantly between the three groups and moderately correlated with the lateral ventricular volumes in iNPH patients [Evans' index (r > 0.83, p ≤ 0.001), corpus callosal angle (r < -0.74, p ≤ 0.001)]. AI-based MRI volumetry in iNPH patients revealed global ventricular enlargement and focal brain atrophy, which, in contrast to healthy controls and AD patients, primarily involved the supratentorial white matter and was marked temporomesially and in the midbrain, while largely preserving gray matter. Integrating AI volumetry in conjunction with traditional radiologic measures could enhance iNPH identification and differentiation, potentially improving patient management and therapy response assessment.

Keywords: automated volumetrization; brain atrophy; normal pressure hydrocephalus; quantitative neuroimaging.

Figure 1

Manual measurements of the Evans’ index: (A) The ratio between the maximum width of the frontal horns of the lateral ventricles (line from A to B) and the greatest internal diameter of the skull (line from C to D) on the same axial plane, in an MRI image. The corpus callosal angle (B) measured on a coronal image perpendicular to the anterior commissure–posterior commissure (AC-PC) plane at the level of the posterior commissure.

Figure 2

Sample excerpt of the software output (headings modified by the authors for translation from German) of two exemplary patients. The black dot within the percentile image indicates the patient’s individual percentile in the corresponding brain area. Abbreviations: A = anterior, P = posterior, R = right and L = left. It is noteworthy that volume measurements for symmetrical structures were conducted individually for each counterpart. The analyzed cortical and subcortical brain structures and ventricles included the following: whole brain volume, whole brain white matter, whole brain gray matter, cortical gray matter, frontal volume right and left, parietal volume right and left, precuneus volume right and left, occipital volume right and left, temporal volume right and left, hippocampus volume right and left, parahippocampal gyrus volume right and left, regio entorhinalis volume right and left, nucleus caudatus volume right and left, putamen volume right and left, pallidum volume right and left, thalamus volume right and left, brainstem volume, mesencephalon volume, pons volume, cerebellar gray matter volume, left and right ventricle, third and fourth ventricle.

Figure 3

Proportion of subjects with volume deviations among iNPH patients (A) and AD patients (B) is presented. The incidence of these deviations, either by 2 (illustrated in blue) or 4 (in orange) standard deviations, is compared with a healthy, population-based control group embedded in the AI-based volumetric software. The deviations of the supratentorial volumes are provided separately for each side of the brain. Deviations in cortical and subcortical volumes indicate atrophy, whereas deviations in ventricular volumes suggest enlargement.

Figure 4

Scatterplot of the right (A,C) and left (B,D) ventricle volumes and the values of the Evans’ index (A,B) and corpus callosum angle (C,D).

Figure 5

ROC curve with total ventricle volume, Evans’ index, corpus callosum angle, white matter, total brain volume, and total temporal volume.