Validated Swin Transformer-Based Deep Learning Pipeline with Cross-Validation and McNemar’s Test for Multi-Class Hemorrhage Classification in Traumatic Brain Injury CT Scans

Arun Singh; Manik Rakhra; Raunak Raj; Saiprasad Potharaju; MVV PRASAD KANTIPUDI; Swathi Gowroju; Pradeep Kumar N S

doi:10.37965/jait.2026.0917

Validated Swin Transformer-Based Deep Learning Pipeline with Cross-Validation and McNemar’s Test for Multi-Class Hemorrhage Classification in Traumatic Brain Injury CT Scans

Authors

Arun Singh Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India https://orcid.org/0000-0002-9712-9921
Manik Rakhra Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
Raunak Raj Parul Institute of Engineering and Technology, Parul University, Gujarat, India https://orcid.org/0000-0002-7550-6810
Saiprasad Potharaju Department of CSE, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, MH, India
MVV PRASAD KANTIPUDI Department of Electronics & Telecommunication (E&TC), Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, MH, India https://orcid.org/0000-0002-0605-4654
Swathi Gowroju Department of CSE (AI&ML), Sreyas Institute of Engineering and Technology, Hyderabad, India https://orcid.org/0000-0002-4940-1062
Pradeep Kumar N S Department of Electronics and Communication Engineering, S.E.A College of Engineering and Technology, Bangalore, India

DOI:

https://doi.org/10.37965/jait.2026.0917

Keywords:

CT scan classification, deep learning, McNemar’s test, medical imaging, statistical validation, Swin Transformer, traumatic brain injury, Vision Transformer

Abstract

Traumatic brain injury (TBI) remains a major global health concern, where rapid and accurate identification of intracranial hemorrhage on computed tomography (CT) scans is essential for improving patient outcomes. Manual radiological assessment, although clinically effective, is time-consuming and subject to inter-observer variability, creating a need for reliable automated diagnostic systems. Most existing artificial intelligence (AI) studies focus on binary hemorrhage detection or limited subtype classification, leaving a gap in robust multi-class intracranial hemorrhage categorization. This study presents a validated deep learning pipeline based on the Swin Transformer—a hierarchical Vision Transformer architecture that employs windowed and shifted multi-head self-attention to capture both local and global contextual information. A balanced dataset of 60,000 CT images across six clinically relevant classes was generated through structured augmentation of a publicly available source, ensuring fairness and improved generalization. The model was optimized using AdamW, cosine annealing scheduling, and label smoothing to enhance stability. The proposed framework achieved a classification accuracy of 82.02%, outperforming the strong baseline EfficientNetV2-S model (80.17%). Statistical significance was established using McNemar’s test (p < 0.0001), and robustness was demonstrated through 5-fold cross-validation. Gradient-weighted Class Activation Mapping (Grad-CAM)++- based interpretability analysis further confirmed that the model consistently highlighted clinically meaningful hemorrhagic regions, reinforcing its diagnostic relevance. These findings establish the Swin Transformer as an effective, interpretable, and statistically validated solution for multi-class intracranial hemorrhage classification, with strong potential to support radiologists in emergency triage and improve clinical decision-making.