Towards the Semantic Representation of Biological Images: From Pixels to Regions

Towards the Semantic Representation of Biological Images: From Pixels to Regions

Kenneth McLeod (Department of Computer Science, Heriot-Watt University, Edinburgh, UK), D. N. F. Awang Iskandar (Faculty of Computer Science & Information Technology, Universiti Malaysia Sarawak, Kota Samarahan, Malaysia), and Albert Burger (Department of Computer Science, Heriot-Watt University, Edinburgh, UK)
Copyright: © 2013 |Pages: 20
DOI: 10.4018/ijiit.2013100103
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Biomedical images and models contain vast amounts of information. Regrettably, much of this information is only accessible by domain experts. This paper describes a biological use case in which this situation occurs. Motivation is given for describing images, from this use case, semantically. Furthermore, links are provided to the medical domain, demonstrating the transferability of this work. Subsequently, it is shown that a semantic representation in which every pixel is featured is needlessly expensive. This motivates the discussion of more abstract renditions, which are dealt with next. As part of this, the paper discusses the suitability of existing technologies. In particular, Region Connection Calculus and one implementation of the W3C Geospatial Vocabulary are considered. It transpires that the abstract representations provide a basic description that enables the user to perform a subset of the desired queries. However, a more complex depiction is required for this use case.
Article Preview
Top

2. Use Case

It is important to understand the biological mechanisms determining how humans develop in order to better comprehend health issues such as cleft lips and cancer. Clearly, ethical and social considerations limit the experiments that can be performed upon humans. Accordingly, the mouse is often used as a model organism.

The developmental mouse is the mouse from the moment it is conceived until it is born. This period of time is commonly split into twenty-six distinct periods called Theiler Stages (TS). Each stage provides a snapshot of the growing mouse capturing its anatomy and how that anatomy differs from the previous stage.

DNA is the blueprint from which an individual is constructed. Genes are sub-sections of DNA that tell the body how to create proteins. Proteins are, amongst other functions, the building blocks that combine to form biological structures, e.g., the heart.

A specific gene will be used in the creation of some biological structures, but not others. A strongly expressed gene plays an important role in the development of a structure, whereas a weakly expressed gene has a lesser role, and a gene that is not expressed will not be involved. Determining where, and at what level, a gene is expressed is the purpose of a gene expression experiment.

There are a variety of technologies for assessing gene expression each with a slightly different focus. In this work, in situ hybridisation gene expression is used. These experiments are primarily concerned with determining precisely where a gene is expressed. Although information regarding the strength (or level) of expression is captured this is with far less granularity than the location information.

Experimental results can be published in traditional journals and/or online in resources like EMAGE (EMAGE, 2012). Figure 1 presents the result of one experiment, published in EMAGE, which is looking to discover where the gene Oxt2 is expressed in TS17 of the developmental mouse.

Figure 1.

Result of EMAGE experiment EMAGE:1411. The gene is expressed in the midbrain (where the dark colour appears in the image). This image is best viewed in colour.

ijiit.2013100103.f01

Complete Article List

Search this Journal:
Reset
Volume 21: 1 Issue (2025)
Volume 20: 1 Issue (2024)
Volume 19: 1 Issue (2023)
Volume 18: 4 Issues (2022): 3 Released, 1 Forthcoming
Volume 17: 4 Issues (2021)
Volume 16: 4 Issues (2020)
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing