Digital Image Processing for Medical Applications

Imaging science visualizes an object and quantitatively characterizes its structure and/or function. Biomedical imaging applies imaging science to the presentation of and interaction with multi-modality biomedical images with a view to using them productively to examine and diagnose disease in human patients. This chapter discusses a number of specific applications in medicine that illustrate many of the concepts introduced in this book. The examples have been chosen to demonstrate a wide range of algorithms and approaches; none represent complete solutions, but are rather examples of continuing research.
After reading this chapter you will be able to:
appreciate the complexity and problems associated with imaging tasks;
recognize broad schemes for approaching image analysis;
analyze the component parts in an imaging problem;
select potential strategies for analyzing images from a variety of applications.
Mammography (Section 3.2.3) is the single most important technique in the investigation of breast cancer, the most common malignancy in women. It can detect disease at an early stage when therapy or surgery is most effective. However the interpretation of screening mammograms is a repetitive task involving subtle signs, and suffers from a high rate of false negatives (10 30% of women with breast cancer are falsely told that they are free of the disease on the basis of their mammograms (Martin, Moskowitz and Milbrath, 1979)), and false positives (only...