Visual Medical Information Analysis

Abstract

Images have constituted an essential data source in medicine in the last decades. Medical images derived from diagnostic technologies (e.g., X-ray, ultrasound, computed tomography, magnetic resonance, nuclear imaging) are used to improve the existing diagnostic systems for clinical purposes, but also to facilitate medical research. Hence, medical image processing techniques are constantly investigated and evolved. Medical image segmentation is the primary stage to the visualization and clinical analysis of human tissues. It refers to the segmentation of known anatomic structures from medical images. Structures of interest include organs or parts thereof, such as cardiac ventricles or kidneys, abnormalities such as tumors and cysts, as well as other structures such as bones, vessels, brain structures and so forth. The overall objective of such methods is referred to as computer-aided diagnosis; in other words, they are used for assisting doctors in evaluating medical imagery or in recognizing abnormal findings in a medical image. In contrast to generic segmentation methods, techniques used for medical image segmentation are often applicationspecific; as such, they can make use of prior knowledge for the particular objects of interest and other expected or possible structures in the image. This has led to the development of a wide range of segmentation methods addressing specific problems in medical applications. In the sequel of this article, the analysis of medical visual information generated by three different medical imaging processes will be discussed in detail: Magnetic Resonance Imaging (MRI), Mammography, and Intravascular Ultrasound (IVUS). Clearly, in addition to the aforementioned imaging processes and the techniques for their analysis that are discussed in the sequel, numerous other algorithms for applications of segmentation to specialized medical imagery interpretation exist.