En savoir plus
This book discusses explainable Artificial Intelligence (AI) and its applications in healthcare, providing a broad overview of state-of-the-art approaches for accurate analysis and diagnosis. It encompasses computational vision processing techniques that handle complex physiological information, electronic healthcare records, and medical imaging data that assist in earlier prediction. This book explores how explainable AI methods provide a solution for the future of medical data analytics precision medicine and highlights the challenges and considerations that must be addressed.
This book summarizes and categorize the explainable AI types and highlight the algorithms used to increase interpretability in medical data and imaging topics. In addition, it focuses on the challenging explainable AI problems in medical applications and provide guidelines to develop better learning models using explainable AI concepts in medical image and text analysis. Furthermore, this edited book will provide future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical data/imaging.
Table des matières
.- Explainable Artificial Intelligence (AI): Introduction.- Explainable AI: An Overview of Explainability.- Explainability for Tabular Data.- Explainable AI: Deep learning.- Explainable AI: Fuzzy Decision Tree (FDT).- Neuro Explainable AI.- Local Interpretable Model-agnostic Explanations (LIME).- Contextual importance and utility (CIU).- Challenges of Explainable AI: Medical data.- Explainable AI for X-ray image analysis.- Explainable AI: CT and Ultrasound.- Explainable AI for disease prediction.
A propos de l'auteur
Ganesh R. Naik ranked top 2% of researchers worldwide in Biomedical Engineering (Stanford University Research), is a leading expert in biomedical engineering and signal processing. He received his Ph.D. in Electronics Engineering, specializing in biomedical engineering and signal processing, from RMIT University, Melbourne, Australia, in December 2009. He is a senior academic and researcher in Computer Science and IT at Torrens University, Adelaide, Australia. Dr. Naik was a research theme co-lead and academic at Adelaide Institute for Sleep Health, Flinders University, for 3 years, from July 2020 to August 2023. He held a Postdoctoral Research Fellow position at MARCS Institute, Western Sydney University (WSU), between July 2017 and July 2020. Ganesh led the data analysis team on a multimillion-dollar CRC project for sleep and developed several novel algorithms (wearables) related to sleep projects. Before that, he held a Chancellor's Postdoctoral Research Fellowship position in the Centre for Health Technologies, University of Technology Sydney (UTS), between February 2013 and June 2017. As a mid-career researcher, he has edited 12 books and authored around 150 papers in peer-reviewed journals and conferences. Ganesh is an associate editor for IEEE ACCESS, Frontiers in Neurorobotics, and two Springer journals (Circuits, Systems, and Signal Processing and Australasian Physical & Engineering Sciences in Medicine). He is a Baden–Württemberg Scholarship recipient from Berufsakademie, Stuttgart, Germany (2006–2007). In 2010, he was awarded an ISSI overseas fellowship from Skilled Institute Victoria, Australia.
Résumé
This book discusses explainable Artificial Intelligence (AI) and its applications in healthcare, providing a broad overview of state-of-the-art approaches for accurate analysis and diagnosis. It encompasses computational vision processing techniques that handle complex physiological information, electronic healthcare records, and medical imaging data that assist in earlier prediction. This book explores how explainable AI methods provide a solution for the future of medical data analytics precision medicine and highlights the challenges and considerations that must be addressed.
This book summarizes and categorize the explainable AI types and highlight the algorithms used to increase interpretability in medical data and imaging topics. In addition, it focuses on the challenging explainable AI problems in medical applications and provide guidelines to develop better learning models using explainable AI concepts in medical image and text analysis. Furthermore, this edited book will provide future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical data/imaging.
