Slowly varying temporally correlated activity fluctuations between functionally related brain areas have been identified
by functional magnetic resonance imaging (fMRI) research in recent years. These low-frequency oscillations of less than
0.08 Hz appear to play a major role in various dynamic functional brain networks, such as the so-called 'default mode'
network. They also have been observed as a property of symmetric cortices, and they are known to be present in the motor
cortex among others. These low-frequency data are difficult to detect and quantify in fMRI. Traditionally, user-based
regions of interests (ROI) or 'seed clusters' have been the primary analysis method. In this paper, we propose unsupervised
clustering algorithms based on various distance measures to detect functional connectivity in resting state fMRI. The
achieved results are evaluated quantitatively for different distance measures. The Euclidian metric implemented by standard
unsupervised clustering approaches is compared with a non-metric topographic mapping of proximities based on the the
mutual prediction error between pixel-specific signal dynamics time-series. It is shown that functional connectivity in the
motor cortex of the human brain can be detected based on such model-free analysis methods for resting state fMRI.
An application of dependent component analysis techniques
is reported for the detection and characterization of
small indeterminate breast lesions
in dynamic contrast-enhanced MRI.
These techniques enable the extraction of spatial and temporal
features of dynamic MRI data stemming from patients with
confirmed lesion diagnosis. By revealing regional
properties of contrast-agent uptake characterized by subtle differences
of signal amplitude and dynamics, this method provides
both a set of prototypical time-series and a corresponding set of
cluster assignment maps which further provides a
segmentation with regard to identification and regional subclassification
of pathological breast tissue lesions.
We present two different segmentation methods for the evaluation of
signal intensity time courses for the differential diagnosis of
enhancing lesions inStarting from the conventional methodology, we proceed by
introducing the
separate concepts of threshold segmentation and
dependent component analysis
and in
the last step
by combining those two concepts.
The results suggest that the
dependent component approach
has the potential to
increase the diagnostic accuracy
of MRI mammography by improving the sensitivity without reduction
of specificity.
An intelligent medical systems based on a radial basis neural network is applied to the automatic classification of suspicious lesions in breast MRI and compared with two standard mammographic reading methods. Such systems represent an important component of future sophisticated computer-aided diagnosis systems and enable the extraction of spatial and temporal features of dynamic MRI data stemming from patients with confirmed lesion diagnosis. Intelligent medical systems combining both kinetics and lesions' morphology are expected to have substantial implications in healthcare politics by contributing to the diagnosis of indeterminate breast lesions by non-invasive imaging.
An application of an unsupervised self-organizing neural network, the neural gas network, is reported for the
detection and characterization of small indeterminate breast lesions in dynamic contrast-enhanced MRI. This
technique enables the extraction of spatial and temporal features of dynamic MRI data stemming from patients
with confirmed lesion diagnosis. By revealing regional properties of contrast-agent uptake characterized by subtle
differences of signal amplitude and dynamics, this method provides both a set of prototypical time-series and a
corresponding set of cluster assignment maps which further provides a segmentation with regard to identification
and regional subclassification of pathological breast tissue lesions. We present two different segmentation methods
for the evaluation of signal intensity time courses for the differential diagnosis of enhancing lesions in breast
MRI. Starting from the conventional methodology, we proceed by introducing the separate concepts of threshold
segmentation and cluster analysis based on the neural gas network, and in the last step by combining those two
concepts. The results suggest that the neural gas network has the potential to increase the diagnostic accuracy
of MRI mammography by improving the sensitivity without reduction of specificity.
As a complement to model-based approaches for the analysis of functional magnetic resonance imaging (fMRI)
data, methods of exploratory analysis offer interesting options. While unsupervised clustering techniques can
be employed for the extraction of signal patterns and segmentation purposes, topographic mapping techniques
such as the Self-Organizing Map (SOM) and the Topographic Mapping for Proximity Data (TMP) provide
additionally a structured representation of the data.
In this contribution we investigate the applicability of two recently proposed variants of these algorithms which
make use of concepts from non-Euclidean geometry for the analysis of fMRI data. Compared to standard methods,
both approaches provide more freedom for the representation of complex relationships in low-dimensional
mappings while they offer a convenient interface for the visualization and exploration of high-dimensional data
sets. Based on data from fMRI experiments, the application of these techniques is discussed and the results are
quantitatively evaluated by means of ROC statistics.
In recent years, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become a powerful
complement to X-ray based mammography in breast cancer diagnosis and monitoring. In DCE-MRI the time
related development of the signal intensity after the administration of contrast agent can provide valuable information
about tissue characteristics at pixel level. The integration of this information constitutes an important
step in the analysis of DCE-MRI data.
In this contribution we investigate the applicability of three different approaches from the field of independent
component analysis (ICA) for feature extraction and image fusion in the context of DCE-MRI data. Next
to FastICA, Tree-Dependent Component Analysis and Topographic ICA are applied to twelve clinical cases
from breast cancer research with a histopathologically confirmed diagnosis. The outcome of all algorithms is
quantitatively evaluated by means of Receiver Operating Characteristics (ROC) statistics. Additionally, the
estimated components are discussed exemplarily and the corresponding data is visualized.
The study suggests that all of the employed algorithms show some potential for the purposes of lesion detection
and subclassification and are rather robust with respect to their parameterization. However, with respect to ROC
analysis Tree-Dependent Component Analysis tends to outperform all other algorithms as well as with regarding
to the consistency of the results.
KEYWORDS: Quantization, Breast, Magnetic resonance imaging, Diagnostics, Neural networks, Mammography, Computer aided diagnosis and therapy, Data analysis, Pattern recognition, Breast cancer
We quantitatively evaluate a novel neural network pattern recognition approach for characterization of diagnostically challenging breast lesions in contrast-enhanced dynamic breast MRI. Eighty-two women with 84 indeterminate mammographic lesions (BIRADS III-IV, 38/46 benign/malignant lesions confirmed by histopathology and follow-up, median lesion diameter 12mm) were examined by dynamic contrast-enhanced breast MRI. The temporal signal dynamics results in an intensity time-series for each voxel represented by a 6-dimensional feature vector. These vectors were clustered by minimal-free-energy Vector Quantization (VQ), which identifies groups of pixels with similar enhancement kinetics as prototypical time-series, so-called codebook vectors. For comparison, conventional analysis based on lesion-specific averaged signal-intensity time-courses was performed according to a standardized semi-quantitative evaluation score. For quantitative assessment of diagnostic accuracy, areas under ROC curves (AUC) were computed for both VQ and standard classification methods. VQ increased the diagnostic accuracy for classification between benign and malignant lesions, as confirmed by quantitative ROC analysis: VQ results (AUC=0.760) clearly outperformed the conventional evaluation of lesion-specific averaged time-series (AUC=0.693). Thus, the diagnostic benefit of neural network VQ for MR mammography analysis is quantitatively documented by ROC evaluation in a large data base of diagnostically challenging small focal breast lesions. VQ outperforms the conventional method w.r.t. diagnostic accuracy.
Intelligent medical systems based on supervised and unsupervised
artificial neural networks are applied to the automatic visualization and classification of suspicious lesions in breast MRI. These systems
represent an important component of future sophisticated
computer-aided diagnosis systems and enable the extraction of spatial and temporal features of dynamic MRI data stemming from patients with confirmed lesion diagnosis. By taking into account the heterogenity of the cancerous tissue, these techniques reveal the malignant, benign and normal kinetic signals and and provide a regional subclassification of pathological breast tissue. Intelligent medical systems are expected to have substantial implications in healthcare politics by contributing to the diagnosis of indeterminate breast lesions by non-invasive imaging.
KEYWORDS: Functional magnetic resonance imaging, Medical imaging, Brain, Visualization, Fuzzy logic, Data analysis, Independent component analysis, Data modeling, Model-based design, Detection and tracking algorithms
Exploratory data-driven methods such as unsupervised clustering are considered to be hypothesis-generating
procedures, and are complementary to the hypothesis-led statistical inferential methods in functional magnetic
resonance imaging (fMRI). The major problem with clustering of real bioimaging data is that of deciding how
many clusters are present. This motivates the application of cluster validity techniques in order to quantitatively
evaluate the results of the clustering algorithm. In this paper, we apply three different cluster validity techniques,
namely, Kim's index, Calinski Harabasz index, and the intraclass index to the evaluation of the clustering results
of fMRI data. The benefits and major limitations of these cluster validity techniques are discussed based on the
achieved results of several datasets.
Recent research in functional magnetic resonance imaging (fMRI) revealed slowly varying temporally correlated
fluctuations between functionally related areas. These low-frequency oscillations of less than 0.08 Hz appear
to be a property of symmetric cortices, and they are known to be present in the motor cortex among others.
These low-frequency data are difficult to detect and quantify in fMRI. Traditionally, user-based regions of
interests (ROI) or "seed clusters" have been the primary analysis method. We propose in this paper to employ
unsupervised clustering algorithms employing arbitrary distance measures to detect the resting state of functional
connectivity. There are two main benefits using unsupervised algorithms instead of traditional techniques: (1) the
scan time is reduced by finding directly the activation data set, and (2) the whole data set is considered and not a
relative correlation map. The achieved results are evaluated for different distance metrics. The Euclidian metric
implemented by the standard unsupervised clustering approaches is compared with a more general topographic
mapping of proximities based on the correlation and the prediction error between time courses. Thus, we are
able to detect functional connectivity based on model-free analysis methods implementing arbitrary distance
metrics.
An application of an unsupervised self-organizing neural network—the minimal free energy vector quantization neural network—is reported for the detection and characterization of breast lesions in dynamic contrast-enhanced magnetic resonance imaging (MRI). This technique enables the extraction of spatial and temporal features of dynamic MRI data stemming from patients with confirmed lesion diagnosis. By revealing regional properties of contrast-agent uptake, characterized by subtle differences of signal amplitude and dynamics, this method provides both a set of prototypical time series and a corresponding set of cluster assignment maps, which further provides a segmentation with regard to identification and regional subclassification of pathological breast tissue lesions. We present three different segmentation methods for the evaluation of signal intensity time courses for the differential diagnosis of enhancing lesions in breast MRI. Starting from the conventional methodology, we proceed by introducing the separate concepts of threshold segmentation and cluster analysis based on the minimal free energy vector quantization neural network, and in the last step by combining those two concepts. The results suggest that the minimal free energy vector quantization neural network has the potential to increase the diagnostic accuracy of MRI mammography by improving sensitivity without reduction of specificity.
We employ unsupervised clustering techniques for the analysis of dynamic contrast-enhanced perfusion MRI time-series in patients with and without stroke. "Neural gas" network, fuzzy clustering based on deterministic annealing, self-organizing maps, and fuzzy c-means clustering enable self-organized data-driven segmentation w.r.t.fine-grained differences of signal amplitude and dynamics, thus identifying
asymmetries and local abnormalities of brain perfusion. We conclude that clustering is a useful extension to conventional perfusion parameter maps.
Exploratory data analysis techniques are applied to the segmentation
of lesions in MRI mammography as a first step of a computer-aided
diagnosis system. ICA and clustering techniques are tested on biomedical time-series representing breast MRI scans. This techniques enable the extraction of spatial and temporal features of dynamic MRI data stemming from patients with confirmed lesion diagnosis. By revealing regional properties of contrast-agent uptake characterized by subtle differences of signal amplitude and dynamics, these methods provide both a set of prototypical time-series and a corresponding set of cluster assignment maps which further provide a segmentation with regard to identification and regional subclassification of pathological breast tissue lesions.
Exploratory data-driven methods such as unsupervised clustering and independent component analysis (ICA) are considered to be hypothesis-generating procedures, and are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). In this paper, we present a comparison between unsupervised clustering and ICA in a systematic fMRI study. The comparative results were evaluated by a very detailed ROC analysis.
For the fMRI data, a comparative quantitative evaluation between the three clustering techniques, SOM, "neural gas" network, and fuzzy clustering based on deterministic annealing, and the three ICA methods, FastICA, Infomax and topographic ICA was performed. The ICA methods proved to extract features relatively well for a small number of independent components but are limited to the linear mixture assumption. The unsupervised clustering outperforms ICA in terms of classification results but requires a longer processing time than the ICA methods.
Conventional model-based or statistical analysis methods for functional MRI (fMRI) are easy to implement, and are effective in analyzing data with simple paradigms. However, they are not applicable in situations in which patterns of neural response are complicated and when fMRI response is unknown. In this paper the Gath-Geva algorithm is adapted and rigorously studied for analyzing fMRI data. The algorithm supports spatial connectivity aiding in the identification of activation sites in functional brain imaging. A comparison of this new method with the fuzzy n-means algorithm, Kohonen's self-organizing map, fuzzy n-means algorithm with unsupervised initialization, minimal free energy vector quantizer and the "neural gas" network is done in a systematic fMRI study showing comparative quantitative evaluations. The most important findings in the paper are: (1) the Gath-Geva algorithms outperforms for a large number of codebook vectors all other clustering methods in terms of detecting small activation areas, and (2) for a smaller number of codebook vectors the fuzzy n-means with unsupervised initialization outperforms all other techniques. The applicability of the new algorithm is demonstrated on experimental data.
Exploratory data-driven methods such as unsupervised clustering and independent component analysis (ICA) are considered to be hypothesis-generating procedures, and are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). Recently, a new paradigm in ICA emerged, that of finding “clusters” of dependent components. This striking philosophy found its implementation in two new ICA algorithms: tree-dependent and topographic ICA. For fMRI, this represents the unifying paradigm of combining two powerful exploratory data analysis methods, ICA and unsupervised clustering techniques. For the fMRI data, a comparative quantitative evaluation between the two methods, tree-dependent and topographic ICA was performed. The comparative results were evaluated by (1) task-related activation maps, (2) associated time-courses and (3) ROC study. It can be seen that topographic ICA outperforms all other ICA methods including tree-dependent ICA for 8 and 9 ICs. However, for 16 ICs topographic ICA is outperformed by both FastICA and tree-dependent ICA (KGV) using an approximation of the mutual information the kernel generalized variance.
Exploratory data analysis techniques are applied to the segmentation of lesions in MRI mammography as a first step of a computer-aided diagnosis system. Three new unsupervised clustering techniques are tested on biomedical time-series representing breast MRI scans: fuzzy clustering based on deterministic annealing, "neural gas" network, and topographic independent component analysis. While the first two methods enable a correct segmentation of the lesion, the latter, although incorporating a topographic mapping, fails to detect and subclassify lesions.
Exploratory data-driven methods such as data partitioning techniques and independent component analysis (ICA) are considered to be hypothesis-generating procedures, and are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). In this paper, we present a comparison between data partitioning techniques and ICA in a systematic fMRI study. The comparative results were evaluated by (1) task-related activation maps and (2) associated time-courses. For the fMRI data, a comparative quantitative evaluation between the three clustering techniques, SOM, “neural gas” network, and fuzzy clustering based on deterministic annealing, and the three ICA methods, FastICA, Infomax and topographic ICA was performed. The ICA methods proved to extract features better than the clustering methods but are limited to the linear mixture assumption. The data partitioning techniques outperform ICA in terms of classification results but requires a longer processing time than the ICA methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.