A Comparative Study of Medical Image Retrieval Using Distance, Transform, Texture, and Shape

A Comparative Study of Medical Image Retrieval Using Distance, Transform, Texture, and Shape

A. Swarnambiga (Indian Institute of Technology Madras, India) and Vasuki S. (Vellammal College of Engineering and Technology, India)
Copyright: © 2019 |Pages: 35
DOI: 10.4018/978-1-5225-5876-7.ch011
OnDemand PDF Download:
No Current Special Offers


Content-based medical image retrieval (CBMIR) is the application of computer vision techniques to the problem of medical image search in large databases. Three main techniques are applied to check the applicability. The first technique implemented is distance metrics-based retrieval. The second technique implemented is transform-based retrieval. The transform which has lesser performance is combined with higher performance, to check the applicability of the results. The third technique implemented is content-based medical image retrieval. Texture and shape-based retrieval techniques are also applied. Shape-based retrieval is processed using canny edge with the Otsu method. The multifeature-based technique is also applied and analyzed. The best retrieval rate is achieved by multifeature-based retrieval with 100/50%. Based on more relevant retrieved images all the three, brain, liver, and knee, images are found to be retrieved more with 100/50%.
Chapter Preview

Although image retrieval have been frequently proposed for use in medical image management, only a few systems have been developed specifically for medical images Manjunath (1996); Shyu (1999); Smelders (2000); Shao Hong (2005); Dimitrovski (2015) and Van kitanovski (2017). Techniques applied for huge image based databases for exact clinical diagnosis with medical justification in this research is provided. A brief survey is given in Table 1.

Table 1.
Brief summary of the image feature descriptors used in medical domain
S. No.YearAuthorTitle of the PaperComments
11999Comaniciu DImage guided decision support system for pathology(a) Representation by color.
(b)Using histogram.
22003Gletsos MA computer aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier(a) Representation by gray scale.
(b) Moments based.
31999Shyu C RASSERT: A physician in the loop content based image retrieval system for HRCT image databases.(a) Representation by gray scale
(b) Texture Co-occurrence
42002Kwak D.MContent-based ultrasound image retrieval using a coarse to fine approach(a) Representation by gray scale
(b) Wavelet based
52005Cauvin JMComputer-assisted diagnosis system in digestive endoscopy(a) Anatomic location, shape and color are the descriptors used
(b) Block based
62007Rahman MA framework for medical image retrieval using machine learning and statistical similarity matching techniques with relevance feedback.(a) Using edge histograms
(b)By contours/curves
72000Wang J ZPathfinder: multiresolution region –based searching for pathology images using IRM.(a) By region and parts
(b) By wavelet based region descriptors
82005Pokrajac DApplying spatial distribution analysis techniques to classification of 3-D medical images.(a) By region and parts
(b)Spatial distribution of ROI.
92007Toews MA statistical parts-based model of anatomical variability.(a) By region and parts
(b) By statistical anatomical parts model
102005Qian X NOptimal embedding for shape indexing in medical image databases.(a) By point sets
(b) By shape spaces

Complete Chapter List

Search this Book: