University of Qom Journal of Engineering Management and Soft Computing 3116-0158 12 2 2026 04 01 Dual-branch hybrid-feature learning for imbalance-aware paediatric colonoscopy decision support with interpretable multi-scale networks 204 224 4302 10.22091/jemsc.2026.14688.1327 EN Khosro Rezaee Department of Biomedical Engineering, Meybod University, Meybod, Iran 0000-0001-6763-6626 Journal Article 2025 11 27 Colorectal neoplasia, while rare, is high-risk in children. As such, colonoscopic detection of paediatric polyps is of clinical importance. Current deep learning–based computer-aided systems are trained on adult data and do not provide solutions for class imbalance, cross-centre generalisation or interpretability in paediatrics. We introduce an imbalance-aware dual-branch hybrid-features (IDHF) framework for polyp versus non-polyp classification. IDHF, based on a ResNet-50 backbone, is equipped with complementary texture branch to augment deep semantic features, adaptive gating for late fusion and optimisation of a class-weighted loss function with false-negative penalty and branch-agreement regularisation. The proposed model is trained on CP-CHILD-A (8,000 images, 1,000 polyp/7,000 non-polyp) and tested without fine-tuning on CP-CHILD-B (1,500 images, 400 polyp/1,100 non-polyp) on another platform. ResNet-50+IDHF achieves 99.6% accuracy, 100.0% sensitivity, 99.5% specificity, 96.8% precision and a 98.4% F1-score on CP-CHILD-A. ResNet-50+IDHF achieves 99.5% accuracy, 99.2% sensitivity, 99.6% specificity, 99.0% precision and a 99.1% F1-score on CP-CHILD-B, supporting a robust and interpretable solution for computer-aided paediatric polyp detection. https://jemsc.qom.ac.ir/article_4302_59b297a90d6f3229de6845085ada6eeb.pdf