Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization

Scalable and Interpretable AI: Paving the Way for Next-Generation Clinical Image Analysis

Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization is pleased to welcome you to submit your research to the Article Collection "Scalable and Interpretable AI: Paving the Way for Next-Generation Clinical Image Analysis ".

Recent advances in AI, deep learning, computer vision, and multimodal foundation models have significantly transformed the analysis and interpretation of biomedical images. AI-driven techniques are increasingly being applied across various medical imaging modalities, including dermoscopic images, clinical skin photographs, X-ray imaging, and microscopy, enabling improvements in image reconstruction, segmentation, classification, detection, and visualization. In dermatology, these technologies have demonstrated considerable potential for the early detection and accurate classification of skin cancers, supporting timely diagnosis and improved patient outcomes. Furthermore, the integration of imaging data with complementary biomedical information, such as electronic health records, genomic profiles, and clinical metadata, is facilitating the development of more comprehensive and personalized diagnostic systems. This Article Collection aims to showcase recent advances in AI-based methods for skin cancer detection and classification from medical and dermoscopic images, emphasizing robust, interpretable, and clinically applicable solutions that can enhance diagnostic accuracy and support clinical decision-making.

The development of AI-based systems for skin cancer detection and classification is of critical importance due to the growing cases of skin malignancies. Recent breakthroughs in deep learning have enabled AI models to identify subtle visual patterns associated with malignant skin lesions. These advances have the potential to support clinicians in making faster and more informed decisions, particularly in resource-constrained settings where access to dermatology specialists may be limited. However, despite impressive research outcomes, translating AI solutions from laboratory settings into routine clinical practice remains challenging. Key barriers include limited model interpretability, robustness and generalizability across diverse patient populations, and the need for rigorous clinical validation. Addressing these challenges is essential to build trust among healthcare professionals and regulatory bodies. Consequently, there is growing interest in developing explainable, transparent, and clinically validated AI systems that can facilitate an effective adoption of skin cancer diagnostic technologies in real-world environments.

This Article Collection welcomes original research articles, review papers, and methodological studies that advance the application of artificial intelligence, machine learning, and deep learning techniques for skin cancer detection, diagnosis, and classification. Topics of interest include, but are not limited to, skin lesion segmentation, dermoscopic and clinical image analysis, feature extraction and representation learning, multimodal data integration, explainable and trustworthy AI, foundation models for dermatological imaging, and computer-aided diagnostic systems. Submissions addressing early melanoma detection, lesion characterization, risk assessment, image enhancement and reconstruction, synthetic data generation, and automated screening approaches are particularly encouraged. The Collection also welcomes studies focused on robustness, fairness, interpretability, uncertainty quantification, benchmarking, and external validation of AI models across diverse populations and imaging conditions. Contributions that demonstrate clinical utility, workflow integration, regulatory considerations, and real-world deployment of AI-enabled skin cancer diagnostic systems are especially encouraged to facilitate the translation of research innovations into routine clinical practice.

Meet the Guest Advisors

Dr. Zahid Mahmood earned his Ph.D. in Electrical and Computer Engineering from North Dakota State University, USA. Currently, he is an Associate Professor in the Department of Computer Engineering at COMSATS University Islamabad, Abbottabad Campus, Pakistan. His research interests include Machine Learning applications and Pattern Recognition.

Dr. Ibtihaj Ahmad is a research scholar and a teacher. He earned his PhD in Computer Science from Northwestern Polytechnical University, China, and a master’s degree in computer engineering from the National University of Science and Technology, Pakistan. He is currently working at the National Health and Medical Big Data Research Institute of the School of Public Health, Shandong University. His interests include Artificial Intelligence and Machine Learning pipelines, Image Processing, Medical Image Processing, and Cyber-Physical Systems.

Dr. Hazrat Ali is a Lecturer in AI at the University of Stirling, United Kingdom. He is the lead editor of the book Advances in Deep Generative Models for Medical AI published by Springer Nature, and is currently editing a book Large Language Models in Healthcare, to be published by CRC Press in 2026. His research interests include Generative AI and Medical Imaging.

The Guest Advisors declare no conflict of interest regarding this work.