This book offers a comprehensive review of quantitative imaging, from extraction of features to creating AI and machine specific algorithms. Quantitative imaging is the extraction of quantifiable features from images for the assessment of normality, severity, and degree of change. It includes the development, standardization, and optimization of protocols, data analysis, and display/reporting methods to allow for validation of image derived metrics. The radiology report is comprised of both qualitative and quantitative data. The former is narrative, detail oriented, easier for patients and other providers to understand, but difficult to summarize and hard to relate to outcome measures. Quantitative imaging on the other hand is objective and can be used in complex statistical calculations, but cannot really stand alone and needs stringent quality measures in order to preserve accuracy and reproducibility. With an increasing focus on AI and machine learning and the need to build patientand disease specific algorithms, this book offers a common ground for physicians, radiologists and data scientists to reference and further advance the field.
The main purpose of this book is to provide details of quantitative imaging from extraction of data from CT and MR images and incorporation into models for clinical translation and application. Individual chapters feature experts from around the world and covers all aspects of quantitative imaging in the thorax, from screening to diagnosis and management. This book also features chapters dedicated to radiomics and radiogenomics.
This is an ideal guide for radiologists, physicians, and data scientists working towards a common ground in quantitative imaging.
