Visual Medical Information Analysis
Maria Papadogiorgaki (Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece), Vasileios Mezaris (Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece) and Yiannis Chatzizisis (Aristotle University of Thessaloniki, Greece)
Copyright: © 2009
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.
Magnetic Resonance Imaging
Magnetic Resonance Imaging (MRI) is an important diagnostic imaging technique attending to the early detection of the abnormal conditions in tissues and organs because it is able to reliably identify anatomical areas of interest. In particular for brain imaging, several techniques which perform segmentation of the brain structures from MRIs are applied to the study of many disorders, such as multiple sclerosis, schizophrenia, epilepsy, Parkinson’s disease, Alzheimer’s disease, and so forth. MRI is particularly suitable for brain studies because it is virtually noninvasive, and it achieves a high spatial resolution and high contrast of soft tissues. To achieve the 3D reconstruction of the brain morphology, several of the existing approaches perform segmentation on sequential MR images. The overall process usually includes noise filtering of the images and edge detection for the identification of the brain contour. Following, perceptual grouping of the edge points is applied in order to recover the noncontinuous edges. In many cases, the next step is the recognition of the various connective components among the set of edge points, rejection of the components that consist of the smallest number of points, and use of the finally acquired points for reconstructing the 3D silhouette of the brain, as will be discussed in more detail in the sequel.
Mammography is considered to be the most effective diagnostic technique for detecting abnormal tissue conditions on women’s breast. Being used both for prevention and for diagnostic purposes, it is a very commonly used technique that produces mammographic images by administering a low-dose of x-ray radiation to the tissue under examination. The analysis of the resulting images aims at the detection of any abnormal structures and the quantification of their characteristics, such as size and shape, often after detecting the pectoral muscle and excluding it from the further processing. Methods for the analysis of mammographic images are presented in the sequel.
Key Terms in this Chapter
Computer-Aided Diagnosis: The process of using computer-generated analysis results for assisting doctors in evaluating medical data.
Intravascular Ultrasound (IVUS): Diagnostic catheter-based technique that renders two-dimensional images of coronary arteries.
Magnetic Resonance Imaging (MRI): Imaging technique that uses a magnetic field to provide two-dimensional images of internal body structures.
Medical Image Segmentation: The localization of known anatomic structures in medical images.
Active Contour Model: Energy-minimizing parametric curve that is the basis of several medical image analysis techniques.
Mammography: Diagnostic X-ray technique which produces breast images and is used to detect breast tissue abnormalities.
Coronary Angiography: X-ray diagnostic process for obtaining an image of the coronary arteries.