Despite success with treatment when diagnosed early, breast cancer is still one of the most fatal forms of cancer for women. Imaging diagnosis is still one of the most efficient ways to detect early breast changes with mammography among the most used techniques. However, there are other techniques that have emerged as alternatives or even complementary tests in the early detection of breast lesions (e.g., breast thermography and electrical impedance tomography). Artificial intelligence can be used to optimize image diagnosis, increasing the reliability of the reports and supporting professionals who do not have enough knowledge or experience to make good diagnoses. Biomedical Computing for Breast Cancer Detection and Diagnosis is a collection of research that presents a review of the physiology and anatomy of the breast; the dynamics of breast cancer; principles of pattern recognition, artificial neural networks, and computer graphics; and the breast imaging techniques and computational methods to support and optimize the diagnosis. While highlighting topics including mammograms, thermographic imaging, and intelligent systems, this book is ideally designed for medical oncologists, surgeons, biomedical engineers, medical imaging professionals, cancer researchers, academicians, and students in medicine, biomedicine, biomedical engineering, and computer science.

Provides strong and accessible theoretical bases to swarm intelligence algorithms, from particle optimization to bioinspired and meta-heuristic algorithms Presents emerging meta-heuristic algorithms and applications Provides overviews on Python and R based computing libraries for swarm intelligence and meta-heuristic algorithms Presenting real-world applications, especially on Industry, Medicine and Biology.

This book presents the theoretical basis and applications of biomedical signal analysis and processing. Initially, the nature of the most common biomedical signals, such as electroencephalography, electromyography, electrocardiography and others, is described. The theoretical basis of linear signal processing is summarized, with continuous and discrete representation, linear filters and convolutions, Fourier and Wavelets transforms. Machine learning concepts are also presented, from classic methods to deep neural networks. Finally, several applications in neuroscience are presented and discussed, involving diagnosis and therapy, in addition to other applications. Features: Explains signal processing of neuroscience applications using modern data science techniques. Provides comprehensible review on biomedical signals nature and acquisition aspects. Focusses on selected applications of neurosciences, cardiovascular, muscle related biomedical areas. Includes computational intelligence, machine learning and biomedical signal processing and analysis. Reviews theoretical basis of deep learning and state-of-the-art biomedical signal processing and analysis. This book is aimed at researchers, graduate students in biomedical signal processing, signal processing, electrical engineering, neuroscience, and computer science.

Provides strong and accessible theoretical bases to swarm intelligence algorithms, from particle optimization to bioinspired and meta-heuristic algorithms Presents emerging meta-heuristic algorithms and applications Provides overviews on Python and R based computing libraries for swarm intelligence and meta-heuristic algorithms Presenting real-world applications, especially on Industry, Medicine and Biology.

Diagnosis can be a deep investigative process, complex by nature. The diagnostic processes have become much more multidisciplinary, demanding the use of an eclectic set of technological methodologies and tools, especially from the Fourth Revolution. Biosensors, Artificial Intelligence, Internet of Things and 3D Printing have become common terms in health research. Cancer in all its forms has become one of the biggest public health issues of the twentieth century. Among all types of cancer, breast cancer is the most dangerous for older and middle-aged women; it is also the most common form of cancer among the female population. Breast cancer is among the five most common cancers worldwide. This disease has been proliferating in developed, underdeveloped and developing countries. Its incidence rate is increasing with the average life expectancy of the population and with the adoption of new forms of consumption. There are some preventive strategies for breast cancer, such as stimulating visual inspection and touching of the breasts. However, they are not efficient enough to impact breast cancer mortality rate because the disease is still being diagnosed late in many cases. Therefore, a deeper understanding of the disease is necessary, including its risk factors and strategies for early identification and efficient treatment. The existence of these tools in public healthcare systems is important because they may contribute to increasing the chances of cure and the treatment options, decreasing mortality rates. Herein this collection book, we present to readers a set of works from the state-of-the-art dealing with cancer diagnosis using biosensors, artificial intelligence and other approaches. We hope this collection could present some of the state of the art of innovative techniques based on the Fourth Industrial Revolution to support early and accurate diagnosis of cancer, especially breast cancer.

One possible solution to the increased amount of paper generated by mankind over recent years is to use the computer and its associated possibility of storing digital information. Through digitisation, the image of a paper can be stored in a digital file. With the development of new storage mediums with even larger capacity and faster access times, it is possible to put a complete collection of books in a single DVD or a small flash drive. This brought forth a possible solution to the problem of carrying and copying the information. But as new opportunities appear to us, we create new possibilities and new problems with them. In this way, carrying and copying moved away from being the centre of the problem. This book covers the main aspects of document analysis and processing, including digitisation, storage, thresholding, filtering, segmentation and automatic recognition.