Benchmarking Deep Vision Architectures: From Controlled Datasets to Real-World Clinical Validation

Abstract: Stroke is a leading cause of mortality and long-term disability, making rapid and reliable detection from non-contrast computed tomography (CT) scans essential for timely clinical intervention. This study introduces NeuroCT-Bench, a unified and reproducible benchmark for evaluating deep learning architectures for automated stroke classification from brain CT images. The benchmark systematically compares five Convolutional Neural Networks (VGG16, ResNet50, DenseNet121, EfficientNetB0, MobileNetV2) and four Vision Transformers (Swin Transformer, ViT, DeiT, PVT-Small) under identical preprocessing, augmentation, and evaluation protocols using the Brain Stroke CT Image dataset from Kaggle, comprising 1,551 normal and 950 stroke slices. Internal validation using a deterministic 80/20 stratified split (seed = 42) demonstrated near-perfect performance for Transformer-based models, with PVT-Small and Swin Transformer achieving ROC-AUCs of 99.96% and 99.98%, respectively, while DenseNet121, VGG16, and EfficientNetB0 achieved strong CNN baselines with ROC-AUCs of 99.93%, 99.67%, and 99.05%. To evaluate robustness under real-world domain shift, the top-performing models were further assessed on an external patient-level clinical dataset containing 530 CT studies. EfficientNetB0 demonstrated the strongest generalization capability (accuracy: 76.92%, precision: 83.85%, ROC-AUC = 88.0%), whereas high-capacity Transformer models exhibited substantially larger performance degradation (ROC-AUCs of 75.0% for PVT-Small and 67.0% for Swin Transformer). These findings highlight the discrepancy between curated public datasets and heterogeneous clinical imaging conditions, emphasizing that high internal performance does not necessarily guarantee clinical robustness. In addition, an ablation study was conducted to evaluate a lightweight CNN–Transformer gated fusion strategy. Results demonstrate that adaptive fusion improves robustness and generalization compared with individual CNN or Transformer models and static feature concatenation. Overall, NeuroCT-Bench provides a transparent and reproducible framework for evaluating deep learning models for stroke analysis and supports future development of clinically deployable hybrid CNN–Transformer systems.

Raghda Essam Ali, Noha Ahmed Saad El-Dien and Magi Hossam Eldin Mahfouz. “Benchmarking Deep Vision Architectures: From Controlled Datasets to Real-World Clinical Validation”. International Journal of Advanced Computer Science and Applications (IJACSA) 17.5 (2026). http://dx.doi.org/10.14569/IJACSA.2026.01705102

@article{Ali2026,
title = {Benchmarking Deep Vision Architectures: From Controlled Datasets to Real-World Clinical Validation},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2026.01705102},
url = {http://dx.doi.org/10.14569/IJACSA.2026.01705102},
year = {2026},
publisher = {The Science and Information Organization},
volume = {17},
number = {5},
author = {Raghda Essam Ali and Noha Ahmed Saad El-Dien and Magi Hossam Eldin Mahfouz}
}