Biomedical imaging informatics

Images are pervasive in biomedicine, providing key information used for understanding the phenotype of disease. Biomedical imaging informatics is a field that involves computational methods related to acquisition, processing, and analysis of images in biomedicine. Major topics in biomedical imaging informatics follow the life cycle of images in the healthcare system, including image acquisition (generating images from the modality and converting them to digital form), image content representation (making the information in images accessible to machines for processing), image management and storage (methods for storing, transmitting, displaying, retrieving, and organizing images), image processing (methods to enhance, segment, visualize, fuse, or analyze the images), and finally image interpretation and computerized reasoning (methods by which the computer can assist the individual viewing the image to recognize content in the image or make better interpretations of images). The number of images being acquired in research and clinical practice is exploding, and the methods of biomedical informatics are increasingly essential in order to make optimal use of these key data. There is particular excitement in helping physicians to make better decisions by leveraging massive amounts of image data, and topics related to artificial intelligence in imaging and machine learning recently are showing promising results to improve image interpretation. At the same time, the types of medical images and imaging modalities continue to expand, bringing with them the need for new biomedical imaging informatics applications and demand for leveraging the content in new types images to characterize disease in patients. Continued research and development in biomedical imaging informatics will build on the core principles outlined in this chapter.