Purpose: This study evaluated volumetric analysis using automatic whole-brain segmentation as a potential tool to enhance diagnostic accuracy alongside traditional magnetic resonance imaging (MRI) markers in the diagnosis of idiopathic normal pressure hydrocephalus (INPH). Materials and Methods: Twenty-six patients diagnosed with INPH exhibited progressive symptoms, including gait dysfunction and cognitive impairment, confirmed by MRI evidence of enlarged ventricles and normal cerebrospinal fluid pressure. Automatic segmentation was performed on sagittal T1-weighted volumetric images using LesionQuant. Age- and sex-matched groups with Alzheimer’s disease (AD) and normal control (NC) groups were included. Multinomial logistic regression was applied to predict diagnoses (NC, INPH, or AD) based on volumetric parameters. Results: Compared to the AD and NC groups, enlarged inferior lateral ventricles were observed in the INPH group. The inferior lateral ventricle volume showed a positive linear correlation with the Evans’ index (R2 = 0.639) and a negative linear correlation with the callosal angle (R2 = 0.482). High classification accuracy was achieved, with 87.5% of NC cases, 88.5% of INPH cases, and 76% of AD cases correctly identified. Conclusion Automated volumetric markers appear valuable for diagnosing INPH and distinguishing it from other neurodegenerative diseases.

Purpose: This study evaluated volumetric analysis using automatic whole-brain segmentation as a potential tool to enhance diagnostic accuracy alongside traditional magnetic resonance imaging (MRI) markers in the diagnosis of idiopathic normal pressure hydrocephalus (INPH). Materials and Methods: Twenty-six patients diagnosed with INPH exhibited progressive symptoms, including gait dysfunction and cognitive impairment, confirmed by MRI evidence of enlarged ventricles and normal cerebrospinal fluid pressure. Automatic segmentation was performed on sagittal T1-weighted volumetric images using LesionQuant. Age- and sex-matched groups with Alzheimer’s disease (AD) and normal control (NC) groups were included. Multinomial logistic regression was applied to predict diagnoses (NC, INPH, or AD) based on volumetric parameters. Results: Compared to the AD and NC groups, enlarged inferior lateral ventricles were observed in the INPH group. The inferior lateral ventricle volume showed a positive linear correlation with the Evans’ index (R2 = 0.639) and a negative linear correlation with the callosal angle (R2 = 0.482). High classification accuracy was achieved, with 87.5% of NC cases, 88.5% of INPH cases, and 76% of AD cases correctly identified. Conclusion Automated volumetric markers appear valuable for diagnosing INPH and distinguishing it from other neurodegenerative diseases.

Purpose: This study evaluated volumetric analysis using automatic whole-brain segmentation as a potential tool to enhance diagnostic accuracy alongside traditional magnetic resonance imaging (MRI) markers in the diagnosis of idiopathic normal pressure hydrocephalus (INPH). Materials and Methods: Twenty-six patients diagnosed with INPH exhibited progressive symptoms, including gait dysfunction and cognitive impairment, confirmed by MRI evidence of enlarged ventricles and normal cerebrospinal fluid pressure. Automatic segmentation was performed on sagittal T1-weighted volumetric images using LesionQuant. Age- and sex-matched groups with Alzheimer’s disease (AD) and normal control (NC) groups were included. Multinomial logistic regression was applied to predict diagnoses (NC, INPH, or AD) based on volumetric parameters. Results: Compared to the AD and NC groups, enlarged inferior lateral ventricles were observed in the INPH group. The inferior lateral ventricle volume showed a positive linear correlation with the Evans’ index (R2 = 0.639) and a negative linear correlation with the callosal angle (R2 = 0.482). High classification accuracy was achieved, with 87.5% of NC cases, 88.5% of INPH cases, and 76% of AD cases correctly identified. Conclusion Automated volumetric markers appear valuable for diagnosing INPH and distinguishing it from other neurodegenerative diseases.