Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns
- First Online:
- Cite this article as:
- Wismüller, A. Comput Sci Res Dev (2011) 26: 15. doi:10.1007/s00450-010-0138-9
Technical innovations in radiology, such as advanced cross-sectional imaging methods, have opened up new vistas for the exploration of structure and function of the human body enabling both high spatial and temporal resolution. However, these techniques have led to vast amounts of data whose precise and reliable visual analysis by radiologists requires a considerable amount of human intervention and expertise, thus resulting in a cost factor of substantial economic relevance. Hence, the computer-assisted analysis of biomedical image data has moved into the focus of interest as an issue of high priority research efforts. In this context, innovative approaches to exploratory analysis of huge complex spatio-temporal patterns play a key role to improve computer-assisted signal and image processing in radiology. Examples of such approaches are various unsupervised vector quantization methods or supervised function approximation techniques, such as Generalized Radial-Basis-Functions- (GRBF-) neural networks. Recent developments motivated by concepts of computational intelligence are the ‘Deformable Feature Map’ (DM) as an algorithm for self-organized model adaptation, the ‘Mutual Connectivity Analysis’ (MCA) as an instrument for the analysis of large time-series ensembles and the ‘Exploratory Observation Machine’ (XOM) as a novel general framework for learning by self-organization—three methods that the author has invented and applied to biomedical real-world applications. This contribution covers both conceptual foundations and applications of such methods for pattern recognition and analysis to a wide scope of radiological data sets, such as structural and functional segmentation in Magnetic Resonance Imaging (MRI), ranging from functional MRI for human brain mapping to the monitoring of disease progression in multiple sclerosis by automatic lesion segmentation, as well as novel approaches to image time-series analysis in MRI mammography for breast cancer diagnosis. Current projects related to the modeling of speech production and to genome-wide expression analysis of microarray data in bioinformatics confirm the broad applicability of the presented methods.