special session

This special session aims to feature innovative methods and applications of Multimodal Generative AI in healthcare that explore multimodal medical data such as radiology and pathology images, signals, medical reports, electronic health records, radiomics and genomics. It will also address key challenges, such as data integration and interpretability, and propose solutions to improve the reliability and effectiveness of multimodal AI approaches in healthcare.

This Special Section aims to explore the transformative role of Artificial Intelligence (AI), intelligent systems, and assistive robotics in revolutionizing healthcare. It will focus on the design, development, and application of advanced technologies such as wearable devices, sensor networks, assistive robotics, haptics, and smart rehabilitation tools to enhance patient-centered care, disorder diagnosis, and movement understanding. The special section seeks to provide a platform for cutting-edge research and innovation addressing real-time data collection, analysis, and integration of these technologies into existing healthcare systems.

This special session focuses on the design, evaluation, and deployment of Trustworthy AI for healthcare, emphasising methods that are explainable, reliable, fair, privacy-preserving, and clinically meaningful under real-world constraints. Aligned with the AIiH conference themes, the session invites contributions spanning AI-aided medical imaging and signal processing, predictive and proactive healthcare, precision and personalised medicine, digital pathology and neurology, mental health, and healthcare workflow optimisation. Particular emphasis is placed on approaches that incorporate explainability, uncertainty awareness, robustness, and human-centred design to foster clinician trust and support safe decision-making.

This special session focuses on the human-centred governance of advanced deep learning architectures, including CNNs, transformers, LMs, and agentic AI systems in healthcare, shifting the field from explainability towards accountability, assurance, and effective oversight. The session will bring together interdisciplinary research addressing how responsibility, decision authority, and control can be meaningfully allocated between humans and AI systems across the AI lifecycle.

This special session aims to bring together interdisciplinary contributions that explore design, evaluation, and deployment strategies for privacy-aware and personalised AAL solutions. By addressing acceptance-related challenges, the session seeks to advance the effective integration of AAL technologies into home environments to support personalised healthcare.

This special session brings together researchers and clinicians working at the intersection of hyperspectral imaging, computational modelling, and AI for diagnosis, with an emphasis on translational impact and deployment in real clinical settings. The session will cover the end-to-end pipeline: (i) imaging hardware and acquisition protocols (surgical, endoscopic, dermatological, and microscopy contexts), (ii) spectral unmixing and physics-informed learning to improve interpretability and robustness, (iii) learning with limited labels through weak supervision, domain adaptation, and uncertainty quantification, (iv) multimodal fusion with histopathology, radiology, or clinical metadata, and (v) validation frameworks, dataset design, and regulatory/ethical considerations for clinical translation.

This special session explores how Artificial Intelligence (AI) is revolutionising Autism Spectrum Disorder (ASD) diagnosis by addressing challenges such as delayed detection and reliance on subjective assessments. It highlights recent advances in AI-powered tools, including machine learning models for analysing multimodal data (e.g., speech, facial expressions, and neuroimaging), while addressing key considerations like interpretability, ethics, and equitable access. Attendees will gain insights into successful applications of AI in early screening, personalised interventions, and long-term monitoring, as well as the collaborative efforts needed to bridge research and clinical practice.

This special session will showcase state-of-the-art research across the full digital biomarker pipeline: (i) discovery and validation from high-frequency, multimodal time series; (ii) causal inference and counterfactual reasoning to improve interpretability, generalisability, and clinical utility; and (iii) predictive modelling for early detection, prognosis, and treatment response monitoring.