Talk by: Prof. Vasileios Megalooikonomou, CIS Faculty, Temple University

Title: Mining of Brain Image Data

Abstract:  

Understanding patterns and discovering associations, regularities and anomalies between anatomical structures and normal or abnormal function of the human brain is a fundamental goal in the neuroscience community. Current advances in brain image acquisition techniques have made available enormous amounts of remarkable high-resolution three-dimensional (3-D) image data. In addition to the continuous development of improved brain imaging techniques, greater computer capabilities and improvements in normalization techniques are leading to the creation of large databases of structure/function information. The availability of this data has already facilitated many advances in human brain mapping during the last decade. The analysis and exploitation of such large collections of brain image data though still remains a problem. More advances are yet to come as scientists get access to efficient tools that take full advantage of all the available data. The field of data mining in brain imaging addresses the question of how best to use this data to gain a deeper understanding of how the brain functions improving, as a result, the process of medical decision-making.

 Major issues in the current attempts for managing this data are the efficiency, effectiveness and robustness of the database and data mining tools used to extract knowledge (in the form of patterns, associations, etc). We discuss ways to overcome these problems and address the great need for developing efficient brain data mining tools for the analysis and management of large collections of brain images (from various imaging modalities) and associated clinical data. One of the goals of our project (that just started) is the development of a general unified framework for managing spatial regions of interest (ROIs) regardless of whether these are lesions, tumors, areas of brain activation, or regions of (normal/abnormal) morphological variability of a variety of brain structures. This framework will enable interoperable brain image data representation that is easy to search.

 Other objectives of our project are to develop tools for content-based (similarity) retrieval, association mining, classification, etc, that can have a significant impact in our attempts to understand the human brain. These tools can advance abilities to analyze 3-D brain image data and discover associations between spatial patterns, anomalies or normal variations and other non-spatial data. We discuss how developing efficient methods for feature extraction and classification of ROIs in brain images, as well as fast and effective database techniques supporting efficient retrieval of similar regions of interest in large brain image databases can facilitate the understanding of patterns in brain structures. We present ideas about how spatial data mining tools can be used for discovering associations between anatomic and other variables such as function, pathology, or response to drugs. Furthermore, we show how integration of the above techniques with morphological analysis tools can be used to correlate morphological changes to changes of functional, physiological and other measurements.

 This Human Brain Project/Neuroinformatics research is supported by NIMH, NIA and NINDS, award MH068066. It is a joint project with Zoran Obradovic, James Gee, Orest B. Boyko, and Diana S. Woodruff-Pak