Hydrocephalus: Ventricular Volume Quantification Using Three-Dimensional Brain CT Data and Semiautomatic Three-Dimensional Threshold-Based Segmentation Approach

Automatic segmentation and quantitative analysis of brain CT volume in 2-year-olds using deep learning model

Objective

Our research aims to develop an automated method for segmenting brain CT images in healthy 2-year-old children using the ResU-Net deep learning model. Building on this model, we aim to quantify the volumes of specific brain regions and establish a normative reference database for clinical and research applications.

Methods

In this retrospective study, we included 1,487 head CT scans of 2-year-old children showing normal radiological findings, which were divided into training (n = 1,041) and testing (n = 446) sets. We preprocessed the Brain CT images by resampling, intensity normalization, and skull stripping. Then, we trained the ResU-Net model on the training set and validated it on the testing set. In addition, we compared the performance of the ResU-Net model with different kernel sizes (3 × 3 × 3 and 1 × 3 × 3 convolution kernels) against the baseline model, which was the standard 3D U-Net. The performance of the model was evaluated using the Dice similarity score. Once the segmentation model was established, we derived the regional volume parameters. We then conducted statistical analyses to evaluate differences in brain volumes by sex and hemisphere, and performed a Spearman correlation analysis to assess the relationship between brain volume and age.

Results

The ResU-Net model we proposed achieved a Dice coefficient of 0.94 for the training set and 0.96 for the testing set, demonstrating robust segmentation performance. When comparing different models, ResU-Net (3,3,3) model achieved the highest Dice coefficient of 0.96 in the testing set, followed by ResU-Net (1,3,3) model with 0.92, and the baseline 3D U-Net with 0.88. Statistical analysis showed that the brain volume of males was significantly larger than that of females in all brain regions (p < 0.05), and age was positively correlated with the volume of each brain region. In addition, specific structural asymmetries were observed between the right and left hemispheres.

Conclusion

This study highlights the effectiveness of deep learning for automatic brain segmentation in pediatric CT imaging, providing a reliable reference for normative brain volumes in 2-year-old children. The findings may serve as a benchmark for clinical assessment and research, complementing existing MRI-based reference data and addressing the need for accessible, population-based standards in pediatric neuroimaging.

Head computed tomography examination as a factor of radiation exposure in children treated for hydrocephalus

OBJECTIVES

Computed tomography (CT) in children with hydrocephalus is a procedure often performed from the first days of the child's life. It is important in diagnosing and monitoring treatment progress.

MATERIAL AND METHODS

Based on a retrospective analysis of CT scans, the level of exposure to ionizing radiation in children with hydrocephalus subjected to this study was calculated. The probability of induction and death from leukemia or other cancers as a result of CT scans was also calculated.

RESULTS

The highest exposure is observed in children <1 year of age: M±SD 4.2±0.9 mSv/year. In the following years, this exposure decreases, reaching the level of 0.7±0.1 mSv/year at the age ≥11 years. This is correlated with the probability of induction of leukemia and other cancers, which is highest in the first year of life. In subsequent years, the probability decreases. The probability of dying from these cancers remains at a similar level all the time. By the age of 17 years, a patient with hydrocephalus diagnosed in infancy may receive a total effective dose of almost 21 mSv.

CONCLUSIONS

After analyzing exposure over the years, a significant reduction in the num- ber of CT examinations performed and a reduction in the radiation dose received by children was found through the introduction of pediatric CT examination protocols. Int J Occup Med Environ Health. 2025;38(2):163-9.

Endoscopic management of pediatric complex hydrocephalus-a procedure survival analysis and clinico-radiological outcome study using ventricular volumetry

OBJECTIVES

To evaluate the survival of endoscopic procedures performed for complex hydrocephalus, quantify clinical outcomes in standardized scales, and assess correlation with radiological outcomes using ventricular volumetry.

METHODS

A retrospective analysis of patients with complex hydrocephalus, managed with neuroendoscopic procedures at a tertiary neurosurgical center over 20 years, was performed. In addition to demographic and clinical details, pre-operative and follow-up clinical status (using the Pediatric Functional Status Score (FSS) and Pediatric Cerebral Performance Category (PCPC) Scales) was assessed. Procedure failure was defined as any subsequent surgical procedure for the management of hydrocephalus and survival as time from the first endoscopic procedure to failure or last available follow-up. Ventricular volume and ventricle:brain volume ratio was calculated using serial imaging.

RESULTS

We analyzed 40 pediatric patients who met the study criteria with a mean age of 19 months, the most common subtype being post-meningitic multiloculated hydrocephalus (70%). The median survival of an endoscopic procedure was 24 months (5.7-33.6 months). Over a median follow-up duration of 15 months, 28 days (2.2-111 months), median FSS improved by 5 points, and median PCPC score improved from 4 (severe disability) to 3 (moderate disability). Over a median radiological follow-up of 5.9 months, the median percentage decrease in ventricle size was 27.14%, and the ventricle:brain volume ratio was 30.57%. A strong positive correlation (r = 0.58-0.75) was noted between the decrease in ventricular volume and ventricle:brain ratio with improvement in FSS and PCPC scores.

CONCLUSIONS

Endoscopic procedures, although effective in managing complex hydrocephalus, may not be a one-stop long-term solution, which we have described in terms of procedure survival. Objective scales and ventricular volumetry to quantify clinical and radiological improvement demonstrated a significant correlation, even in complex hydrocephalus. The potential of ventricular volumetry as a prognostic factor in complex hydrocephalus is postulated.

Automated segmentation of ventricular volumes and subarachnoid hemorrhage from computed tomography images: Evaluation of a rule-based pipeline approach

Changes in ventricular size, related to brain edema and hydrocephalus, as well as the extent of hemorrhage are associated with adverse outcomes in patients with subarachnoid hemorrhage (SAH). Frequently, these are measured manually using consecutive non-contrast computed tomography scans. Here, we developed a rule-based approach which incorporates both intensity and spatial normalization and utilizes user-defined thresholds and anatomical templates to segment both lateral ventricle (LV) and SAH blood volumes automatically from CT images. The algorithmic segmentations were evaluated against two expert neuroradiologists on representative slices from 20 admission scans from aneurysmal SAH patients. Previous methods have been developed to automate this time-consuming task, but they lack user feedback and are hard to implement due to large-scale data and complex design processes. Our results using automatic ventricular segmentation aligned well with expert reviewers with a median Dice coefficient of 0.81, AUC of 0.91, sensitivity of 81%, and precision of 84%. Automatic segmentation of SAH blood was most reliable near the base of the brain with a median Dice coefficient of 0.51, an AUC of 0.75, precision of 68%, and sensitivity of 50%. Ultimately, we developed a rule-based method that is easily adaptable through user feedback, generates spatially normalized segmentations that are comparable regardless of brain morphology or acquisition conditions, and automatically segments LV with good overall reliability and basal SAH blood with good precision. Our approach could benefit longitudinal studies in patients with SAH by streamlining assessment of edema and hydrocephalus progression, as well as blood resorption.

A Review of Cerebrospinal Fluid Circulation and the Pathogenesis of Congenital Hydrocephalus

The brain's ventricles are filled with a colorless fluid known as cerebrospinal fluid (CSF). When there is an excessive accumulation of CSF in the ventricles, it can result in high intracranial pressure, ventricular enlargement, and compression of the surrounding brain tissue, leading to potential damage. This condition is referred to as hydrocephalus. Hydrocephalus is classified into two categories: congenital and acquired. Congenital hydrocephalus (CH) poses significant challenges for affected children and their families, particularly in resource-poor countries. Recognizing the psychological and economic impacts is crucial for developing interventions and support systems that can help alleviate the distress and burden faced by these families. As our understanding of CSF production and circulation improves, we are gaining clearer insights into the causes of CH. In this article, we will summarize the current knowledge regarding CSF circulation pathways and the underlying causes of CH. The main causes of CH include abnormalities in the FoxJ1 pathway of ventricular cilia, dysfunctions in the choroid plexus transporter Na+-K+-2Cl- contransporter isoform 1, developmental abnormalities in the cerebral cortex, and structural abnormalities within the brain. Understanding the causes of CH is indeed crucial for advancing research and developing effective treatment strategies. In this review, we will summarize the findings from existing studies on the causes of CH and propose potential research directions to further our understanding of this condition.

Fast Quantitative Magnetic Resonance Imaging Evaluation of Hydrocephalus Using 3-Dimensional Fluid-Attenuated Inversion Recovery: Initial Experience

OBJECTIVE

This study aimed to demonstrate the initial experience of using fast quantitative magnetic resonance imaging (MRI) to evaluate hydrocephalus.

METHODS

A total of 109 brain MRI volumetry examinations (acquisition time, 7 minutes 30 seconds) were performed in 72 patients with hydrocephalus. From the measured ventricular system and brain volumes, ventricle-brain volume percentage was calculated to standardize hydrocephalus severity (processing time, <5 minutes). The obtained values were categorized into no, mild, and severe based on the fronto-occipital horn ratio (FOHR) and the ventricle-brain volume percentages reported in the literature. The measured volumes and percentages were compared between patients with mild hydrocephalus and those with severe hydrocephalus. The diagnostic performance of brain hydrocephalus MRI volumetry was evaluated using receiver operating characteristic curve analysis.

RESULTS

Ventricular volumes and ventricle-brain volume percentages were significantly higher in in patients with severe hydrocephalus than in those with mild hydrocephalus (FOHR-based severity: 352.6 ± 165.6 cm 3 vs 149.1 ± 78.5 cm 3 , P < 0.001, and 26.8% [20.8%-33.1%] vs 12.1% ± 6.0%, P < 0.001; percentage-based severity: 359.5 ± 143.3 cm 3 vs 137.0 ± 62.9 cm 3 , P < 0.001, and 26.8% [21.8%-33.1%] vs 11.3% ± 4.2%, P < 0.001, respectively), whereas brain volumes were significantly lower in patients with severe hydrocephalus than in those with mild hydrocephalus (FOHR-based severity: 878.1 ± 363.5 cm 3 vs 1130.1 cm 3 [912.1-1244.2 cm 3 ], P = 0.006; percentage-based severity: 896.2 ± 324.6 cm 3 vs 1142.3 cm 3 [944.2-1246.6 cm 3 ], P = 0.005, respectively). The ventricle-brain volume percentage was a good diagnostic parameter for evaluating the degree of hydrocephalus (area under the curve, 0.855; 95% confidence interval, 0.719-0.990; P < 0.001).

CONCLUSIONS

Brain MRI volumetry can be used to evaluate hydrocephalus severity and may provide guide interpretation because of its rapid acquisition and postprocessing times.

Increased risk for ex-vacuo ventriculomegaly with leukoencephalopathy (EVL) in whole brain radiation therapy and repeat radiosurgery treated brain metastasis patients

INTRODUCTION

Cerebral atrophy with leukoencephalopathy is a known morbidity after whole brain radiation therapy (WBRT), resulting in ex-vacuo ventriculomegaly with leukoencephalopathy (EVL). Here we studied the correlation between WBRT, stereotactic radiosurgery (SRS), and risk for EVL in brain metastases patients.

METHODS

In a retrospective study, we identified 195 patients (with 1,018 BM) who underwent SRS for BM (2007-2017) and had > 3 months of MRI follow-up. All patients who underwent ventriculoperitoneal shunting were excluded. Cerebral atrophy was measured by ex-vacuo-ventriculomegaly, defined based on Evans' criteria. Demographic and clinical variables were analyzed using logistic regression models.

RESULTS

Ex-vacuo ventriculomegaly was observed on pre-radiosurgery imaging in 29.7% (58/195) of the study cohort. On multivariate analysis, older age was the only variable associated with pre-radiosurgery ventriculomegaly. Of the 137 patients with normal ventricular size before radiosurgery, 27 (19.7 %) developed ex-vacuo ventriculomegaly and leukoencephalopathy (EVL) post-SRS. In univariate analysis, previous whole brain radiation therapy was the main factor associated with increased risk for developing EVL (OR = 5.08, p < 0.001). In bivariate models that included prior receipt of WBRT, both the number of SRS treatments (OR = 1.499, p = 0.025) and WBRT (OR = 11.321, p = 0.003 were independently associated with increased EVL risk.

CONCLUSIONS

While repeat radiosurgery contributes to the risk of EVL in BM patients, this risk is ∼20-fold lower than that associated with WBRT.

Prediction of shunt failure facilitated by rapid and accurate volumetric analysis: a single institution's preliminary experience

BACKGROUND

Shunt malfunction is a common complication and often presents with hydrocephalus. While the diagnosis is often supported by radiographic studies, subtle changes in CSF volume may not be detectable on routine evaluation. The purpose of this study was to develop a novel automated volumetric software for evaluation of shunt failure in pediatric patients, especially in patients who may not manifest a significant change in their ventricular size.

METHODS

A single-institution retrospective review of shunted patients was conducted. Ventricular volume measurements were performed using manual and automated methods by three independent analysts. Manual measurements were produced using OsiriX software, whereas automated measurements were produced using the proprietary software. A p value < 0.05 was considered statistically significant.

RESULTS

Twenty-two patients met the inclusion criteria (13 males, 9 females). Mean age of the cohort was 4.9 years (range 0.1-18 years). Average measured CSF volume was similar between the manual and automated methods (169.8 mL vs 172.5 mL, p = 0.56). However, the average time to generate results was significantly shorter with the automated algorithm compared to the manual method (2244 s vs 38.3 s, p < 0.01). In 3/5 symptomatic patients whose neuroimaging was interpreted as stable, the novel algorithm detected the otherwise radiographically undetectable CSF volume changes.

CONCLUSION

The automated software accurately measures the ventricular volumes in pediatric patients with hydrocephalus. The application of this technology is valuable in patients who present clinically without obvious radiographic changes. Future studies with larger cohorts are needed to validate our preliminary findings and further assess the utility of this technology.