Название: Artificial Intelligence in Medicine: With 377 Figures and 127 Tables
Автор: Niklas Lidstromer, Hutan Ashrafian
Издательство: Springer
Год: 2022
Страниц: 1848
Язык: английский
Формат: pdf (true)
Размер: 41.1 MB

This book provides a structured and analytical guide to the use of Artificial Intelligence in medicine. Covering all areas within medicine, the chapters give a systemic review of the history, scientific foundations, present advances, potential trends, and future challenges of Artificial Intelligence within a healthcare setting. Artificial Intelligence in Medicine aims to give readers the required knowledge to apply Artificial Intelligence to clinical practice. The book is relevant to medical students, specialist doctors, and researchers whose work will be affected by Artificial Intelligence.

This is in all essence a book on the future of medicine. Artificial Intelligence in medicine (AIM) is without doubt the hottest and most intriguing branch of medicine at the moment. It dwells into all areas and aspects of medicine. Creating human hubris and hypes, and provoking raging debates, fears, and intense hopes, it stretches the limits of medical science and researchers’ minds, and raises questions of equality, humanism, emotional intelligence, and our very existence. Without the ardor of dedicated experts, AIM is a vast territory, hard to vanquish. AIM will bestow medicine with unrivalled new tools, and it is the authors’ cordial intention to deliver a broad systematic review of its entire history, scientific foundations, present advances, trends, possibilities, and future challenges.

This book offers a wide and profound overview of all the latest advancements within the field of Artificial Intelligence in medicine. The book both explains the basic concepts of AI, proceeds to the applications of AIM, and then analyzes all of the commonest medical specialties and their AIM advancements systematically.

Although AIM will change medicine radically, the amount of AI taught in medical schooling is astonishingly limited. This book aims to bridge the gaps in profound understanding of AI in medicine for medical students, specialist doctors, and other researchers, whose areas will be hugely affected by AI in the very near future.

This AIM textbook brings the reader into the world of applied AI, from the mathematical foundations through the world of algorithms and computer programs to the ultimate benefits for patients and clinicians. It will be shown how AIM learned a lot from general AI for imaging, such as super-resolution, image reconstruction, image matching, inpainting, age estimation, generative adversarial network (GAN) image generation, and other areas.

The book contains 130 chapters, as of its first edition, and is divided into three parts: the first is on AI in general; the second is on AI in medicine, covering the lessons for all doctors and the common trunk of AI applicable to all walks of medicine; and the third systematically goes through all medical specialties with as much width and depth as possible.

There are several languages used in AI applications, and one of the most popular and wellknown is Python, partly because of its simple and functional syntaxes, and also for the great number of libraries designed for Python (to implement Machine Learning algorithms in a straight-forward manner), such as Keras and Tensorflow. The Python advantages are related to its simplicity and their maintainability as well as the possibility to connect and integrate with files written in other programming languages. Problems of memory usage and not having multithreading are substantial Python disadvantages.

Python supports various programming paradigms, i.e., both object-oriented, and procedure-oriented programming, and is extensible, i.e., it can invoke C and C++ libraries, and can integrate with a multitude of other languages, such as Java and NET products. Python is the most rapid gainer in AI, with a huge momentum. Its use is ubiquitous to create AI algorithms, Machine Learning, IoT projects, etc. With Python, the developer doesn’t need to code very much, because there are ready-made packages, with algorithms. For instance, PiBrain (for Machine Learning), NumPy (scientific computing, Pandas, etc.) can be implemented, and a vast range of libraries.

Apart from Python, another popular programming language used mainly for statistical tasks is called R. This language well-performs in analysis and manipulation of incoming data for statistical purposes. R is well known for its publication-quality plots and its compatibility with other programming languages. However, R is less suitable for handling big data analysis tasks for its consuming memory characteristic compared to Python and its speed in other programming languages.

R is almost as easy as Python to learn. Both languages are very similar to English in syntax and construction, hence they belong to the easiest to
master. They both have an enormous number of libraries to provide all thinkable predefined algorithms, statistical models, data scientific inputs, AI, Machine Learning with algorithms, NLP, etc.

Moreover, Java is also used in AI, especially for Artificial Neural Networks and Genetic Programming. Here Java has its benefits with, e.g., simple packaging and debugging, user interaction, and functionality for mega-project scalability and graphics. The latter is one of the outstanding assets of Java with its standard interface and graphics’ toolkit – the graphical presentation is, of course, a vital part of AI, and which will be seen in AIM, especially when applications are directed toward patients and students. Java provides better managing tools of garbage and provides multi-threading, differently from Python.

Another alternative language is Lisp, less known, but the most ancient and perhaps best-adapted language for AI development. Lisp goes all back to the origins of AI, and was introduced by John McCarty in the late 1950s, and can process symbolic information, can prototype, create dynamic objects, automatic garbaging, and is deemed easy by developers. Though, nearly all of its excellent features have migrated into many other languages. The latter are more effective, have better packaging, etc.

SWI Prolog is a language, which is relevant in AIM, since it is often used in knowledge base and expert systems – it has features such as pattern matching, freebase data structuring, and automatic backtracking. This gives a strong and flexible framework for programming, which makes it frequently used in AIM.

Other languages worth mentioning are C++, SaaS, jаvascript, MATLAB, and Julia. All of these can be used for AI.