Organizers: Dr. Muhammad Aamir, College of Computer Science and Artificial Intelligence, Huanggang Normal University, Huanggang, China, Dr. Uzair Aslam Bhatti, College of Information and Communication Engineering, Hainan University, Haikou, China, Dr. Nomica Choudhry, School of Information Technology, Faculty of Science, Engineering and Built Environment, Deakin University, Burwood, VIC, Australia
Email: aamirshaikh86@hotmail.com, 184311@hainanu.edu.cn, choudhryn@deakin.edu.au
Medical imaging is central to modern clinical diagnosis, prognosis, and personalized treatment. The rapid evolution of deep learning has fundamentally transformed medical image analysis, enabling breakthroughs in disease detection, segmentation, and classification across diverse clinical specialties. Cutting-edge architectures , including convolutional–transformer hybrids, self-supervised learning frameworks, and multimodal fusion networks , are reshaping intelligent diagnostic pipelines with remarkable accuracy and generalizability.
This special session convenes researchers, clinicians, and industry practitioners to present and discuss the latest advances in deep learning for medical image interpretation and disease classification.
Contributions are welcomed across a broad spectrum of imaging modalities , MRI, CT, PET, X-ray, ultrasound, retinal OCT, and digital histopathology , and clinical domains including neurology, oncology, cardiology, ophthalmology, and pathology.
The session places particular emphasis on bridging the gap between algorithmic innovation and real-world clinical utility, promoting AI systems that are not only accurate but interpretable, robust, privacy-preserving, and deployable within healthcare workflows. By fostering interdisciplinary dialogue, it aims to accelerate progress toward precision medicine and improved patient outcomes.
Topics of interest include, but are not limited to:
• Deep learning architectures for medical image detection, segmentation, and classification
• Self-supervised, semi-supervised, and weakly supervised learning in clinical imaging
• Multimodal and cross-modality fusion (imaging + clinical data + omics + radiology reports)
• Federated and privacy-preserving learning for multi-institutional collaboration
• Explainable AI (XAI) and uncertainty quantification for trustworthy medical diagnostics
• Domain adaptation and model robustness across scanners, sites, and patient populations
• Lightweight and real-time models for point-of-care and mobile health applications
• Benchmark datasets and challenge results (e.g., BraTS, ADNI, ISLES, CheXpert, CAMELYON)
• Clinical translation, workflow integration, regulatory pathways, and deployment considerations
Keywords: Deep learning; Medical image analysis; Disease classification; Multimodal fusion; Radiology; Histopathology; Self-supervised learning; Vision Transformers; Federated learning; Explainable AI; Precision medicine; Clinical translation.