From Biomedical Image Analysis to Biomedical Image Understanding Using Machine Learning

From Biomedical Image Analysis to Biomedical Image Understanding Using Machine Learning

Eduardo Romero (National University of Colombia, Colombia) and Fabio González (National University of Colombia, Colombia)
DOI: 10.4018/978-1-60566-956-4.ch001
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

This chapter introduces the reader into the main topics covered by the book: biomedical images, biomedical image analysis and machine learning. The general concepts of each topic are presented and the most representative techniques are briefly discussed. Nevertheless, the chapter focuses on the problem of image understanding (i.e., the problem of mapping the low-level image visual content to its high-level semantic meaning). The chapter discusses different important biomedical problems, such as computer assisted diagnosis, biomedical image retrieval, image-user interaction and medical image navigation, which require solutions involving image understanding. Image understanding, thought of as the strategy to associate semantic meaning to the image visual contents, is a difficult problem that opens up many research challenges. In the context of actual biomedical problems, this is probably an invaluable tool for improving the amount of knowledge that medical doctors are currently extracting from their day-to-day work. Finally, the chapter explores some general ideas that may guide the future research in the field.
Chapter Preview
Top

Biomedical Images

The term “biomedical images” denotes digital images captured from living beings or parts of living beings, with structural or functional information to be analyzed, documented, annotated and formalized. This type of images constitutes the foundation of any knowledge in life sciences, they give support to the medical diagnosis, medical treatment or follow-up as well as to medical and biological research. Images are indeed a large part of the biomedical knowledge which is multi-modal by nature. It combines visual structural or functional information with many different types of information. Knowledge in life sciences has been made up by integrating visual information with different physiological analysis techniques related to a particular anatomical structure.

Biomedical images are acquired using different mechanisms that range from simple, e.g. a digital camera coupled with a conventional optical microscope, to complex, e.g. specialized equipment for Positron Emission Tomography (PET). A complete account of the different biomedical image types would require a complete volume only devoted to it and clearly exceeds the scope of this chapter. However, we present a brief list of some of the most representative types of biomedical images (the interested reader may refer to (Bankman, 2000; Buxton, 2003) for further details):

  • Radiography

  • Computed Tomography (CT) Scanning

  • Ultrasound

  • Magnetic Resonance Imaging (MRI)

  • Positron Emission Tomography (PET) Scanning

  • Single Proton Emission Computer Tomography (SPECT)

  • Functional Magnetic Resonance

  • Endoscopy

  • Microscopy

  • Confocal Microscopy

  • Medical Photography

  • Molecular Imaging

  • Spectroscopy

Complete Chapter List

Search this Book:
Reset