Hierarchical clustering of fMRI time-series by deterministic annealing

Wismüller, Axel; Dersch, Dominik R.; Lipinski, Bernadette; Hahn, Klaus; Auer, Dorothee P.

doi:10.1016/s1053-8119(18)31426-5

Cited by 18 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of fMRI data analysis, various clustering methods have been introduced by several authors [82][83][84][85][86][87][88][89][90][91][92][93][94]. For VQ analysis, the PTCs of gray levels at each pixel obtained from biomedical timeseries data can be interpreted as feature vectors sampled from a multidimensional probability distribution.…”

Section: Image Time-seriesmentioning

confidence: 99%

“…In particular, the approach has been proven to be useful in applications to (i) fMRI data analysis for human brain mapping [74,[93][94][95][96][97][98][99][100], (ii) dynamic contrast-enhanced perfusion MRI for the diagnosis of cerebrovascular disease [74,101,102], (iii) magnetic resonance mammography for the analysis of suspicious lesions in patients with breast cancer [103][104][105][106], and (iv) nuclear medicine in dynamic renal scintigraphy for the differential diagnosis between functional and obstructive urinary excretion deficits in children [107,108].…”

Section: Image Time-seriesmentioning

confidence: 99%

See 1 more Smart Citation

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Wismüller

2010

Comput Sci Res Dev

View full text Add to dashboard Cite

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 RadialBasis-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 A. Wismüller ( )

show abstract

Section: Image Time-seriesmentioning

confidence: 99%

Section: Image Time-seriesmentioning

confidence: 99%

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Wismüller

2010

Comput Sci Res Dev

View full text Add to dashboard Cite

show abstract

“…Specifically, in [51] the neural network vector quantization techniques explained in Section 7.3.1 of this chapter have been introduced as a multipurpose approach to image time-series analysis that can be applied to many fields of medicine, ranging from biomedical basic research to clinical assessment of patient data. In particular, this model-free approach has been proven to be useful in applications to (i) functional MRI data analysis for human brain mapping [51][52][53][54][55][56][57][58][59]; (ii) dynamic contrastenhanced perfusion MRI for the diagnosis of cerebrovascular disease [51,60,61]; (iii) magnetic resonance mammography for the analysis of suspicious lesions in patients with breast cancer [62][63][64][65]; and (iv) nuclear medicine in dynamic renal scintigraphy for the differential diagnosis between functional and obstructive urinary excretion deficits in children [66].…”

Section: Vector Quantization As a Multipurpose Tool For Image Time-sementioning

confidence: 99%

Segmentation with Neural Networks

Wismueller

2009

Handbook of Medical Image Processing and Analysis

View full text Add to dashboard Cite

“…Currently, this is achieved (a) by model-dependent, statistical methods (Bandettini et al, 1993;Friston et al, 1996) or via (b) explorative, paradigm-independent strategies such as (rotated) principal component analysis (PCA) (Sychra et al, 1994; or fuzzy clustering (FCA) (Scarth et al, 1995;Baumgartner et al, , 1998Moser et al, 1997a). Recently, other strategies have been proposed and presented in abstract form (e.g., Fischer et al, 1996;Golay et al, 1996;Wismueller et al, 1998). In analogy to nuclear medicine and magnetic resonance spectroscopy, the full power of pattern recognition approaches should be explored systematically in fMRI.…”

Section: Introductionmentioning

confidence: 99%

Explorative signal processing in functional MR imaging

Moser¹,

Baumgartner²,

Barth³

et al. 1999

Int. J. Imaging Syst. Technol.

View full text Add to dashboard Cite

Identification and separation of artifacts as well as quantification of expected, i.e., stimulus-correlated, and novel information on brain activity are important for both new insights in neuroscience and future developments in functional magnetic resonance imaging (MRI) of the human brain. Here, we present several examples in which gross head motion or physiologic motion (e.g., pulsation, respiration, large veins) could be identified and separated by using fuzzy cluster analysis of fMRI time series. Furthermore, our experience with singleand multislice fMRI (FLASH and EPI; 1.5 and 3 T) data analysis is summarized and several examples, including long echo time and high-resolution fMRI of the motor cortex, are discussed. Explorative signal processing in fMRI, based on fuzzy clustering, represents a robust and powerful tool for screening large fMRI data sets, extracting expected and novel functional activity of the human brain, and obtaining improved reproducibility of fMRI results. Finally, it may help to improve or develop functional brain models which can then be tested by applying statistical models.

show abstract

Hierarchical clustering of fMRI time-series by deterministic annealing

Cited by 18 publications

References 1 publication

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Segmentation with Neural Networks

Explorative signal processing in functional MR imaging

Contact Info

Product

Resources

About