• Labeling Brain Anatomical Structures in Digital Images

This is one of the possible Use Cases.

1. Abstract

This use case provides a scenario where rules are used to extend an OWL-DL ontology. The application aims at assisting the labeling of the brain cortex structures in MRI images. It requires reasoning with an OWL ontology and rules.

Example:

A rule is needed for expressing the dependency between the two ontology properties isMAEConnectedTo and isMAEBoundedBy:

Two MAE entities having a shared boundary are connected (simplified form)

isMAEBoundedBy(?x1,?x3) and isMAEBoundedBy(?x2,?x3) => isMAEConnectedTo(?x1,?x2)

2. Status

• Originally proposed by: Christine Golbreich (posted by IanHorrocks on her behalf)

• This use case was reported at Washington 2005 W3C Workshop on Rule Languages for Interoperability[4] and at OWL Experiences and Directions Workshop [5]

Slides available at: http://www.w3.org/2004/12/rules-ws/slides/christinegolbreich.pdf http://www.med.univ-rennes1.fr/~cgolb/Slides/OWLED-Rules-CG.pdf

3. Links to Related Use Cases

• SW rules for Health Care and Life Sciences

• Fuzzy Reasoning with Brain Anatomical Structures

4. Relationship to OWL/RDF Compatibility

• A rule extension to OWL DL
• Combining ontology and rules

5. Benefits of Interchange

• Integration of anatomical images thanks to the Brain Ontology.
• Possibility to integrate multiple distributed image sources indexed by anatomical features but with different vocabulary, thanks to mapping (aligning) rules
• Useful in large-scale federated systems for statistical analysis of brain images of major brain pathologies

6. Requirements on the RIF

• Reasoning support to reason over a knowledge base composed of ontology and rules
• Clear semantics that enables OWL DL and rules to safely interoperate (decidable, sound and complete reasoning)
• Although it should be more carefully investigated, the rule language required might be a FOL extension with function-free Horn rules (with negation as failure).

7. Breakdown

7.1. Actors and their Goals

• Surgeon - wants landmarks (labeled area) in the operating room for neuronavigation systems
• Clinician - wants to make clinical studies about major brain path ologies such as Alzheimer disease, multiple sclerosis or epilepsy and needs to search for information in distributed image sources.

7.2. Main Sequence

1. At a first step, numerical tools segment the various parts of a brain cortex in an MRI (Magnetic Resonance Image). The ouput is a list of items with a set of features like the length and depth of a sulcus segment in a brain cortex, the connection of two sulcus segments etc
2. Second step concerns the identification and labeling of the different items
3. The facts extracted from the image (XML) are converted into facts of the Abox or RBox
4. A composed query is created for identifying the given items.
5. A knowledge based engine is run to answer the query from the facts and the KB
6. The query results are displayed to the user.

8. Narratives

The general framework is sharing anatomical knowledge (ontology and rules) and tools (services) needed in the context of neuroimaging, applied both to medical practice, i.e. decision support in neurology and neurosurgery, and statistical analysis about neurological pathology such as epilepsy, dementia, etc. The application aims at developing new methods for assisting the labeling of the brain cortex structures in MRI images.

The system relies on two components: a brain ontology (O) storing the a priori canonical knowledge about the most important brain cortex anatomical structures and a rule base (R) representing the interdependencies between the properties.

A simplified scenario in [5] illustrates reasoning over the ontology extended by rules. This example illustrates that solutions are missed if the Web ontology language and the rule languages are not closely integrated.

9. Commentary

Extracted from [Use case] from medicine presented at the first f2f. Also available at http://www.med.univ-rennes1.fr/~cgolb/RIF/OntologyWithRule-CG.pdf

Rules available at http://idm.univ-rennes1.fr/~obierlai/anatomy/annexes/index.html.

[4] Golbreich, C. Bierlaire, O. Dameron, O. and B. Gibaud. Use case: Ontology with rules for identifying brain anatomical structures. W3C Workshop on Rule Languages for Interoperability, 2005.

[5] Golbreich, C. Bierlaire, O. Dameron, O. and B. Gibaud. What reasoning support for Ontology and Rules? the brain anatomy case study, OWL Experiences and Directions Workshop, collocated with the International Conference on Rule Markup Languages for the Semantic Web, Galway, Ireland, 2005