Medical Image Fusion in Spatial and Transform Domain: A Comparative Analysis

Medical Image Fusion in Spatial and Transform Domain: A Comparative Analysis

Alka Srivastava (Sant Longowal Institute of Engineering and Technology Punjab, India) and Ashwani Kumar Aggarwal (Sant Longowal Institute of Engineering and Technology Punjab, India)
DOI: 10.4018/978-1-5225-2848-7.ch011


Nowadays, there are a lot of medical images and their numbers are increasing day by day. These medical images are stored in the large database. To minimize the redundancy and optimize the storage capacity of images, medical image fusion is used. The main aim of medical image fusion is to combine complementary information from multiple imaging modalities (e.g. CT, MRI, PET, etc.) of the same scene. After performing medical image fusion, the resultant image is more informative and suitable for patient diagnosis. There are some fusion techniques which are described in this chapter to obtain fused image. This chapter presents two approaches to image fusion, namely spatial domain Fusion technique and transforms domain Fusion technique. This chapter describes Techniques such as Principal Component Analysis which is spatial domain technique and Discrete Wavelet Transform and Stationary Wavelet Transform which are Transform domain techniques. Performance metrics are implemented to evaluate the performance of image fusion algorithm.
Chapter Preview

1. Introduction

Medical imaging field demands images which have high resolution and higher information content, for necessary disease diagnosis and visualization. Therefore, in practical scenarios more complementary information is required for necessary disease diagnosis purpose. Multimodal medical image fusion algorithms and devices have shown notable achievements in improving clinical accuracy of decisions based on medical images. The selection of the imaging modality for a targeted clinical study requires medical insights specific to organs under study. It is practically impossible to capture all the details from one imaging modality that would ensure clinical accuracy and robustness of the analysis and resulting diagnosis. Medical images to be fused are taken from different modalities, i.e. CT scan, MRI scan, PET scan, etc. These modalities are used for different purposes as described below. Figure 1 shows medical image of different modalities.

1.1. Imaging Modalities

In medical imaging, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), Single Photon Emission Computed Tomography (SPECT) and other modes of medical images reflect human information from various angles. CT scan can clearly reflect the anatomical structure of bone tissues. It provides detailed cross sectional views of all types of tissues. SPECT scan can highlight the lesion of tissues and organs and provide information about blood flow and temperature of body parts. PET scanning can show blood flow, oxygen and glucose metabolism in the tissues of the brain. MRI can clearly reflect the anatomical structure of soft tissues, organs and blood vessels.

In the clinical diagnosis and treatment, the problems regarding comparison and synthesis of images like CT-PET, MRI-PET and CT-MRI were frequently encountered. In order to provide more useful information for clinical diagnosis, there is a need to combine more useful information from different source images. Combining complementary information from different images of the same lesion area is known as image fusion. A CT image gives distinct contours of bones but it cannot show clear image of ligaments which is needed for differentiating tumor from scar tissues. MRI shows the shape of both ligaments and bones but fails to produce distinct contours of the bones. Fusion of CT-MRI images is used to assist in planning surgical procedure. Combining PET with CT or MRI gives both anatomic and metabolic information. This is very useful in showing detailed views of moving organs or structures with higher anatomical variation which is used to detect lung cancer. Combination of MRI-PET images is used in detecting brain tumors, SPECT-CT is useful in abdominal studies and Ultra Sound (US)-MRI for vascular blood flow test (Azzwai, 2009).

Figure 1.

CT scan and MRI scan of same scene

1.2. Objective

The main motive of the chapter is to study about Medical Image Fusion and their classification. Medical Image Fusion’s method is classified in to two domains i.e. spatial domain and transform domain. The disadvantage of spatial domain technique is that they produce spatial distortion in the fused image. To eliminate the disadvantages of spatial domain fusion techniques, transform domain fusion techniques are used. Some of techniques which fall under this domain have been studied. The performance of Medical Image Fusion’s methods is calculated in terms of various parameters. Based on the various performance parameters, comparative analysis is done.


2. Advantages Of Image Fusion

Image Fusion is used in many areas due to the several advantages which are described below (Sharma, 1999).

Complete Chapter List

Search this Book: