Название: Cloud Computing in Medical Imaging
Автор: Ayman El-Baz, Jasjit S. Suri
Издательство: CRC Press
Год: 2023
Страниц: 279
Язык: английский
Формат: pdf (true)
Размер: 10.5 MB

Today’s healthcare organizations must focus on a lot more than just the health of their clients. The infrastructure it takes to support clinical-care delivery continues to expand, with information technology being one of the most significant contributors to that growth. As companies have become more dependent on technology for their clinical, administrative, and financial functions, their IT departments and expenditures have had to scale quickly to keep up. However, as technology demands have increased, so have the options for reliable infrastructure for IT applications and data storage. The one that has taken center stage over the past few years is cloud computing. Healthcare researchers are moving their efforts to the cloud because they need adequate resources to process, store, exchange, and use large quantities of medical data.

Cloud services come in three varieties: internal (private), outsourced (public), or hybrid. The variety depends on the user requirements and the required infrastructure. For a typical healthcare provider, a dedicated private cloud infrastructure is the most ideal mode for ensuring quality, reliability, and privacy of services, but this mode carries a high cost. The cloud-computing model is composed of six main features: (i) resource pooling; (ii) on-demand service; (iii) large network access; (iv) rapid elasticity; (v) security; and (vi) measured services. Nowadays, there exist many cloud services providers like Amazon web service, Google cloud platform, Microsoft Azure, Rackspace, Salesforce, Apache Hadoop. Generally, cloud-computing platforms consist of three service types, namely, Software as a Service (SaaS), Platform as a Service (PaaS), and Infrastructure as a Service (IaaS).

Machine Learning (ML) techniques are essential in many cyber security applications. Machine Learning and Deep Learning models are currently being used to detect and respond to attacks in almost all aspects of cyber security. On the defensive side, Machine Learning models help develop more robust and automated ways to boost performance and early detection of attacks, lowering the impact and damage. This study is a systematic review to illustrate the analysis and interpretation of the latest approach based on machine learning to solve the issues related to healthcare data security. This report also discusses the advantages and disadvantages of all modern techniques to healthcare data security. In addition, a better security model has been presented based on background research of all conceivable solutions to the problem. It will help readers comprehend Machine Learning models and their application in the healthcare field. Each section and subsection will highlight distinct parts of the research. We included research questions, a search and selection approach for papers relating to our problem, and inclusion and exclusion criteria in the research methods section, which helped us conduct the review effectively. The section on results and discussions displays the systematic search results and observations that led to identifying prevalent strategies for preventing cyberattacks and their limits and comparison. We also conducted an algorithm complexity analysis.

Cloud Computing in Medical Imaging covers the state-of-the-art techniques for cloud computing in medical imaging, healthcare technologies, and services. The book focuses on:

Machine Learning algorithms for health data security
Fog computing in IoT-based health care
Medical imaging and healthcare applications using fog IoT networks
Diagnostic imaging and associated services
Image steganography for medical informatics

This book aims to help advance scientific research within the broad field of cloud computing in medical imaging, healthcare technologies, and services. It focuses on major trends and challenges in this area and presents work aimed to identify new techniques and their use in biomedical analysis.