Thomas Walker; Khaled Tarabieh; Sherif Goubran; Gabrielle Machnik-Kekesi Springer International Publishing AG (2024) Saatavuus: Tulossa! Pehmeäkantinen kirja
Medical images, in various formats, are used by clinicians to identify abnormalities or markers associated with certain conditions, such as cancers, diseases, abnormalities or other adverse health conditions. Deep learning algorithms use vast volumes of data to train the computer to recognise certain features in the images that are associated with the disease or condition that you wish to identify.
Whilst analysing the images by eye can take a lot of time, deep learning algorithms have the benefit of reviewing medical images at a faster rate than a human can, which aids the clinician, speeding up diagnoses and freeing up clinicians' time for other duties.
Deep Learning in Medical Image Processing and Analysis introduces the fundamentals of deep learning for biomedical image analysis for applications including ophthalmology, cancer detection and heart disease. The book considers the principles of multi-instance feature selection, swarm optimisation, parallel processing models, artificial neural networks, support vector machines, as well as their design and optimisation, in biomedical applications. Topics such as data security, patient confidentiality, effectiveness and reliability will also be discussed.
Written by an international team of experts, this edited book covers principles and applications for industry and academic researchers, scientists, engineers, developers, and designers in the fields of machine learning, deep learning, AI, image processing, signal processing, computer science or related fields. It will also be of interest to standards bodies and regulators, and clinicians using deep learning models.
