Introduction to Medical Image Analysis | springerprofessional.de

Springer Professional

Top

2020 | Book

Read chapter Read first chapter

Introduction to Medical Image Analysis

Authors: Assoc. Prof. Rasmus R. Paulsen, Prof. Thomas B. Moeslund

Publisher: Springer International Publishing

Book Series : Undergraduate Topics in Computer Science

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access

About this book

This easy-to-follow textbook presents an engaging introduction to the fascinating world of medical image analysis. Avoiding an overly mathematical treatment, the text focuses on intuitive explanations, illustrating the key algorithms and concepts in a way which will make sense to students from a broad range of different backgrounds.

Topics and features: explains what light is, and how it can be captured by a camera and converted into an image, as well as how images can be compressed and stored; describes basic image manipulation methods for understanding and improving image quality, and a useful segmentation algorithm; reviews the basic image processing methods for segmenting or enhancing certain features in an image, with a focus on morphology methods for binary images; examines how to detect, describe, and recognize objects in an image, and how the nature of color can be used for segmenting objects; introduces a statistical method to determine what class of object the pixels in an image represent; describes how to change the geometry within an image, how to align two images so that they are as similar as possible, and how to detect lines and paths in images; provides further exercises and other supplementary material at an associated website.

This concise and accessible textbook will be invaluable to undergraduate students of computer science, engineering, medicine, and any multi-disciplinary courses that combine topics on health with data science. Medical practitioners working with medical imaging devices will also appreciate this easy-to-understand explanation of the technology.

Advertisement

Table of Contents

Frontmatter

Chapter 1. Introduction

Abstract

This chapter introduces the book and gives a brief overview of the different flavors of image processing. A description of relevant general frameworks is also given. Finally, a note on deep learning is provided and the content of the book is compared to the use of modern deep learning techniques.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 2. Image Acquisition

Abstract

In this chapter, the different factors that influence how images are acquired using a standard camera are described. The focus of the chapter is on the three components; energy reflected from the object of interest, an optical system which focuses the energy and finally a sensor which measures the amount of energy. The energy is in this chapter visible light. The optical system is defined as a single lens, where the major properties of light reflection in a simple lens are described. Finally, the digital image sensor is described together with some common digital image types, including gray-scale, binary and multi-spectral images.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 3. Image Storage and Compression

Abstract

Images are normally stored on storage devices like the internal memory of a camera or on a hard disk. To be able to store an image, an image format needs to be defined and a method to compress the image. In this chapter, a brief overview of image storage formats and compression is given.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 4. Point Processing

Abstract

Point processing covers methods that change the value of all pixels in an image but do it independently of the location of the pixel and also independently of the neighbors of the individual pixels. Typical examples of point processing are changing the contrast and brightness of an image. The chapter covers the fundamental linear operations performed on pixel values. It also covers a selection of non-linear operations as gamma- and log mapping. Finally, thresholding of an image is covered.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 5. Neighborhood Processing

Abstract

In this chapter, we present a number of methods where the neighbor pixels play a role when determining the output value of a pixel. These methods are denoted neighborhood processing or image filtering. The methods are initially described using the median filter as an example. Secondly, the correlation and convolution operations are described and used with different filter kernels as, for example, the Prewitt edge filter. Finally, more advanced filtering approaches like template matching and gradient filters are described.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 6. MorphologyMorphology

Abstract

Mathematical morphology or simply morphology is an important tool when processing binary images. A binary image is typically a result of a previous image-processing tool like tresholding. They often contain unwanted noise like holes in the objects in the image or objects are touching each other. Morphology can be used to remove this kind of noise. In this chapter, the basic morphological operations are introduced. These methods includes erosion, dilation, opening and closing. Finally, an introduction to compound operations is given.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 7. BLOB Analysis

Abstract

A BLOB is a connected group of white pixels in binary image. BLOB analysis is about identifying these groups of pixels and computing different properties of these pixels. BLOB analysis is a major component in pattern recognition in images and is often seen as one of the final modules in an image analysis system. This chapter covers BLOB extraction and how to compute BLOB features like area, circularity, and compactness. Finally, some important metrics for determining how well an image analysis system performs are described. The metrics include accuracy, sensitivity, and specificity.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 8. Color Images

Abstract

In this chapter, we turn to the topic of color images, where the nature of color images and how they are captured and represented are described. The standard red, green, blue (RGB) representation is described together with less used but very important color spaces like the hue, saturation, and value (HSV) color space. Finally, it is described how thresholding can be used in color images.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 9. Pixel Classification

Abstract

An important task in image analysis is to assign each pixel in an image to a predefined class of objects. This class can be a specific anatomy like the liver in a computed tomography image. One commonly used step is pixel classification where each pixel is assigned a class-based purely on its value and independently of the pixel neighbors. In this chapter, we introduce basic pixel classification approaches like minimum distance classification and parametric classification, where the pixel value distributions are approximated using Gaussian kernels. Finally, a brief overview of Bayesian classification is given.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 10. Geometric Transformations

Abstract

Geometric transformations are used to change the geometry of an image while keeping the actual pixel values. An example is rotation of an image. In this chapter, we start by covering affine transformation, including translation, scaling, rotation, and shearing. It is described how a transformation can be performed using matrices and how inverse mapping is used with bilinear interpolation to avoid sampling artifacts. Finally, some non-linear transformations are briefly described.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 11. Image Registration

Abstract

Image registration covers methods that aligns two images so they in some sense become more similar than before the registration. Normally, one image is kept fixed and the second image is geometrically deformed to fit the first image. In this chapter, the basic concepts of image registration is introduced and exemplified using a landmark based registration approach. In landmark-based registration, the moving image is deformed so the landmark in the moving image is becoming as similar to the landmarks in the fixed image as possible.

Rasmus R. Paulsen, Thomas B. Moeslund

Chapter 12. Line and Path Detection

Abstract

An image analysis problem can often be described as a task of recognizing patterns in images. Example patterns are straight lines and curve-like structures. The Hough transform is a highly effective algorithm for detecting straight lines in images and is the topic of the first part of the chapter. In the second part, a method for tracing paths in images is presented. The algorithm is very fast and is based on the algorithmic approach called dynamic programming.

Rasmus R. Paulsen, Thomas B. Moeslund

Backmatter

Title: Introduction to Medical Image Analysis
Authors: Assoc. Prof. Rasmus R. Paulsen
Prof. Thomas B. Moeslund
Copyright Year: 2020
Publisher: Springer International Publishing
Electronic ISBN: 978-3-030-39364-9
Print ISBN: 978-3-030-39363-2
DOI: https://doi.org/10.1007/978-3-030-39364-9

Premium Partner