Explainable 3D VGG-style convolutional neural network for pediatric hydrocephalus detection on computed tomography: A segmentation-free and fully volumetric deep learning framework.
Authors
Affiliations (2)
Affiliations (2)
- Sciences and Engineering of Biomedicals, Biophysics and Health Laboratory, Higher Institute of Health Sciences, Hassan First University, Settat 26000, Morocco; Higher Institute of Nursing Professions and Health Techniques, Rabat, Morocco. Electronic address: [email protected].
- Sciences and Engineering of Biomedicals, Biophysics and Health Laboratory, Higher Institute of Health Sciences, Hassan First University, Settat 26000, Morocco.
Abstract
Pediatric hydrocephalus is commonly assessed on computed tomography (CT) using manual two-dimensional indices that incompletely reflect the ventricular system. We developed and evaluated an explainable, segmentation-free three-dimensional convolutional neural network (3D CNN) for automated hydrocephalus detection on pediatric CT. Ninety-eight pediatric CT scans were included (48 hydrocephalus, 50 normal), distributed across four age groups: <1 year (n = 24), 1-5 years (n = 24), 5-10 years (n = 19), and 10-15 years (n = 31). Diagnoses were established by experienced radiologists using Evans Index ≥ 0.30 with consensus resolution. A lightweight VGG-style 3D CNN was trained from scratch using five-fold StratifiedGroupKFold cross-validation. Performance was assessed using AUC-ROC, accuracy, sensitivity, specificity, F1-score, Matthews correlation coefficient (MCC), Cohen's κ, and Brier score. Explainability was evaluated using 3D Grad-CAM and four quantitative attention metrics. The model achieved high internal performance, with mean AUC-ROC 0.95 ± 0.06, accuracy 0.94 ± 0.06, F1-score 0.94 ± 0.06, and MCC 0.88 ± 0.11; the pooled fold-averaged ROC yielded AUC 0.944. Grad-CAM analyses showed progressively stronger, anatomically coherent ventricular activation from normal to severe cases. In preliminary external validation on 118 independent pediatric CT scans (56 hydrocephalus, 62 normal), AUC-ROC was 0.88 and AUC-PR was 0.85; accuracy, sensitivity, specificity, precision, and F1-score were 0.83, 0.84, 0.82, 0.81, and 0.82, respectively. This segmentation-free 3D CNN provides accurate, calibrated, and anatomically interpretable hydrocephalus detection directly from routine pediatric CT, although larger multicenter validation remains necessary before clinical deployment.