Cutting-edge Computational Intelligence in Healthcare With Convolution and Kronecker Convolution-based Approaches

Cutting-edge Computational Intelligence in Healthcare with Convolution and Kronecker Convolution-based Approaches focuses on the use of deep learning techniques in the field of medical imagine analysis. These advances offer promising progress in healthcare through improvements in diagnostic accuracy, efficiency in medical image interpretation, and breakthroughs in treatment planning. Divided into five sections, the book begins with foundational coverage of deep learning in medical imaging and fundamentals of Convolutional Neural Networks. Discover the role convolutions play in extracting meaningful features from images, aiding tasks such as diagnosis and segmentation. The second section takes a deep dive into Kronecker convolutions and their unique advantages, such as enhanced spatial hierarchy understanding, efficient parameter utilization, and improved adaptability to specific characteristics of medical images. Section three reviews specific applications in tumor detection, enhancing organ segmentation as well as disease classification, and section four explores real-world implementation of AI-driven diagnostic imaging, precision medicine via imaging analytics, and wearable devices and continuous health monitoring. The final section offers discussion on the unique challenges, trends, and potential future directions these innovative computational approaches have on medical image processing and advanced healthcare. In summary, this book takes an interdisciplinary approach to bridge the gap between theory and practice, fusing knowledge from the domains of medicine, computer science, and machine learning to address issues in healthcare through sophisticated image analysis techniques.

• Investigates opportunities and challenges of deep learning, including convolutional neural networks (CNNs) and their applications in medical image processing
• Includes comprehensive examination and elucidation of Kronecker convolutional procedures and their significance in medical image processing
• Explores specific medical imaging tasks where Kronecker convolutions prove beneficial
• Provides detailed examples demonstrating how convolutions may be employed to improve healthcare, offering insights into how deep learning is currently being used in clinical settings

Jaya Prakash Allam received his PhD in Electronics and Communication Engineering from the National Institute of Technology Rourkela, India, specializing in artificial intelligence. He is a Research Scientist and Postdoctoral Fellow at United Arab Emirates University, Al Ain, UAE, and has academic and research experience spanning India and the United Arab Emirates. His research focuses on biomedical signal processing, deep learning, machine learning, wearable and Edge AI systems, explainable artificial intelligence, and remote sensing. His work centers on the development of intelligent healthcare technologies, including AI-driven analysis of physiological signals and clinical decision-support systems. He serves as Associate Editor of a leading journal in biomedical and health informatics, Editor-in-Chief of Frontiers in Biomedical Signal Processing, and Academic Editor of PLOS Computational Biology. His current interests include biomedical data analytics, resource-efficient intelligent systems, and the translation of AI technologies into real-world healthcare applications.

Dr. Kiran Kumar Patro, Ph.D., is Associate Professor in the Department of Electronics and Communication Engineering at Aditya Institute of Technology and Management (A), Tekkali, India. He earned his Ph.D. in Electronics and Communication Engineering from Andhra University, with research focused on artificial intelligence and machine learning applications. His research interests include biomedical signal and image processing, deep learning, Edge AI, Internet of Things (IoT)-enabled intelligent systems, and federated learning. Dr. Patro serves as an Academic Editor for PLOS ONE and is a member of the editorial boards of BMC Artificial Intelligence and Frontiers in Bioinformatics. His work focuses on the development and evaluation of intelligent computational approaches for healthcare and engineering applications, with particular emphasis on AI-driven signal processing and distributed intelligent systems. In this volume, he contributes expertise in benchmarking methodologies, Edge AI systems, and federated learning frameworks.

Dr. Paweł Pławiak is Professor and Dean of the Faculty of Computer Science and Telecommunications at Cracow University of Technology, Poland. He holds a Ph.D. in Biocybernetics and Biomedical Engineering from AGH University in Kraków and a D.Sc. in Technical Computer Science and Telecommunications from the Silesian University of Technology. His research focuses on machine learning, computational intelligence, signal processing, and biomedical engineering, with particular interests in neural networks, evolutionary computation, ensemble learning, and deep learning methods. His work has contributed to the application of advanced computational techniques for the analysis and interpretation of complex biomedical and engineering data. In this volume, he provides expertise in machine learning methodologies and supports the development of rigorous benchmarking and evaluation approaches across the covered topics.