CAREER: Extracting Patterns from Medical Image Databases

Temple University, Philadelphia PA

Investigators

Abstract

CAREER: Extracting Patterns from Medical Image Databases The goal of this career development plan is to build an education and research program that will focus on the discovery of patterns and relations between anatomy (structure) and function through the effective and efficient analysis of large repositories of medical images and other clinical data. Medical centers almost everywhere today are facing an interesting challenge in analyzing the huge volumes of image and associated clinical data collected daily as part of several ongoing studies. By focusing on the regions of interest (ROIs), the approach uses novel techniques to extract their most discriminative features and uses them in classification and similarity searches. New representations of the information content of medical images are also provided. Statistical and data compression techniques are employed to facilitate the retrieval of similar ROIs. Information theoretic tools are used to relate complexity of function to that of structure. Moreover, spatial data mining tools are developed to efficiently discover associations between image data and non-image (functional) data. The approaches have applicability to medical images from a wide range of modalities (e.g., mammography, angiography, CT, MRI, fMRI, confocal microscopy, etc) showing normal and abnormal conditions of various structures. Information about the function of structures related to various medical conditions is extracted from clinical assessment. Finding similarities and differences between image data of a given new subject and previously seen subjects will assist the correlation of this information with clinical assessment of function, pathology, or response to drugs. It is expected that this work will be widely used within the medical imaging community to facilitate advances in both diagnosis, and treatment, and to provide new insight into the relation of anatomy and function. The project will provide an excellent resource for graduate work in data mining, data compression, multimedia databases, and other areas. The goal of the educational plan is to provide students with a solid theoretical background and practical experience on data mining and its applications in medicine, promote interdisciplinary learning, and enable the training of a more versatile type of scientist. The basic components of the teaching and education program will be made readily available to students and researchers. Results can be found at the project's Web site (http://www.cis.temple.edu/~vasilis).