Estimating the number of spectral signal sources, denoted by, in hyperspectral imagery is very challenging due to the fact that many unknown material substances can be uncovered by very high spectral resolution hyperspectral sensors. This paper investigates a recent approach, called maximum orthogonal complement algorithm (MOCA) developed by Kuybeda et al. for estimating the rank of a rare vector space in a high-dimensional noisy data space which was essentially derived from the automatic target generation process (ATGP) developed by Ren and Chang. By appropriately interpreting the MOCA in context of the ATGP, a potentially useful technique, called maximum orthogonal subspace projection (MOSP) can be further developed where a stopping rule for the ATGP provided by MOSP turns out to be equivalent to a procedure for estimating the rank of a rare vector space by the MOCA and the number of targets determined by the MOSP to generate is the desired value of the parameter. Furthermore, a Neyman-Pearson detector version of MOCA, referred to as ATGP/NPD can be also derived where the MOCA can be considered as a Bayes detector. Surprisingly, the ATGP/NPD has a very similar design rationale to that of a technique, called Harsanyi-Farrand-Chang method that was developed to estimate the virtual dimensionality (VD) where the ATGP/NPD provides a link between MOCA and VD

No abstract

Endmember finding has become increasingly important in hyperspectral data exploitation because endmembers can be used to specify unknown particular spectral classes. Pixel purity index (PPI) and N-finder algorithm (N-FINDR) are probably the two most widely used techniques for this purpose where many currently available endmember finding algorithms are indeed derived from these two algorithms and can be considered as their variants. Among them are three well-known algorithms derived from imposing different abundance constraints, that is, abundance-unconstrained automatic target generation process (ATGP), abundance nonnegativity constrained vertex component analysis (VCA), and fully abundance constrained simplex growing algorithm (SGA). This paper explores relationships among these three algorithms and further shows that theoretically they are essentially the same algorithms in the sense of design rationale. The reason that these three algorithms perform differently is not because they are different algorithms, but rather because they use different preprocessing steps, such as initial conditions and dimensionality reduction transforms. Index Terms-Automatictarget generation process (ATGP), endmember finding algorithm (EFA), growing simplex algorithm (SGA), linear spectral unmixing (LSU), N-finder algorithm (N-FINDR), orthogonal projection (OP), pixel purity index (PPI), simplex volume (SV), vertex component analysis (VCA).

In this work, the authors present an effective denoising method to attempt reducing the noise in mammographic images. The method is based on using hierarchical correlation of the coefficients of discrete stationary wavelet transforms. The features of the proposed technique include iterative use of undecimated multi-directional wavelet transforms at adjacent scales. To validate the proposed method, computer simulations were conducted, followed by its applications to clinical mammograms. Mutual information originating from information theory was used as an evaluation measure for selection of an optimal wavelet basis function. We examined the performance of the proposed method by comparing it with the conventional undecimated discrete wavelet transform (UDWT) method in terms of processing time-consuming and image quality. Our results showed that with the use of the proposed method the computation time can be reduced to approximately 1/10 of the conventional UDWT method consumed. The results of visual assessment indicated that the images processed with the proposed UDWT method showed statistically significant superior image quality over those processed with the conventional UDWT method. Our research results demonstrate the superiority and effectiveness of the proposed approach.

Objective Hyperspectral imaging (HSI) is a novel technology for obtaining quantitative measurements from transcutaneous spatial and spectral information. In patients with SSc, the severity of skin tightness is associated with internal organ involvement. However, clinical assessment using the modified Rodnan skin score is highly variable and there are currently no universal standardized protocols. This study aimed to compare the ability to differentiate between SSc patients and healthy controls using skin scores, ultrasound and HSI. Methods Short-wave infrared light was utilized to detect the spectral angle mapper (SAM) of HSI. In addition, skin severity was evaluated by skin scores, ultrasound to detect dermal thickness and strain elastography. Spearman’s correlation was used for assessing skin scores, strain ratio, thickness and SAM. Comparisons of various assessment tools were performed by receiver operating characteristic curves. Results In total, 31 SSc patients were enrolled. SAM was positively correlated with skin scores and dermal thickness. In SSc patients with normal skin scores, SAM values were still significantly higher than in healthy controls. SAM exhibited the highest area under the curve (AUC: 0.812, P < 0.001) in detecting SSc compared with skin scores (AUC: 0.712, P < 0.001), thickness (AUC: 0.585, P = 0.009) and strain ratio by elastography (AUC: 0.522, P = 0.510). Moreover, the severity of skin tightness was reflected by the incremental changes of waveforms in the spectral diagrams. Conclusion SAM was correlated with skin scores and sufficiently sensitive to detect subclinical disease. HSI can be used as a novel, non-invasive method for assessing skin changes in SSc.

Purpose: To effectively perform quantification of brain normal tissues and pathologies simultaneously, independent component analysis (ICA) coupled with support vector machine (SVM) is investigated and evaluated for effective volumetric measurements of normal and lesion tissues using multispectral MR images. Materials and Methods:Synthetic and real MR data of normal brain and white matter lesion (WML) data were used to evaluate the accuracy and reproducibility of gray matter (GM), white matter (WM), and WML volume measurements by using the proposed ICAþSVM method to analyze three sets of MR images, T1-weighted, T2-weighted, and proton density/fluid-attenuated inversion recovery images.Results: The Tanimoto indexes of GM/WM classification in the normal synthetic data calculated by the ICAþSVM method were 0.82/0.89 for data with 0% noise level. As for clinical MR data experiments, the ICAþSVM method clearly extracted the normal tissues and white matter hyperintensity lesions from the MR images, with low intra-and inter-operator coefficient of variations. Conclusion:The experiments conducted provide evidence that the ICAþSVM method has shown promise and potential in applications to classification of normal and pathological tissues in brain MRI.

Independent component analysis (ICA) has recently received considerable interest in applications of magnetic resonance (MR) image analysis. However, unlike its applications to functional magnetic resonance imaging (fMRI) where the number of data samples is greater than the number of signal sources to be separated, a dilemma encountered in MR image analysis is that the number of MR images is usually less than the number of signal sources to be blindly separated. As a result, at least two or more brain tissue substances are forced into a single independent component (IC) in which none of these brain tissue substances can be discriminated from another. In addition, since the ICA is generally initialized by random initial conditions, the final generated ICs are different. In order to resolve this issue, this paper presents an approach which implements the over-complete ICA in conjunction with spatial domain-based classification so as to achieve better classification in each of ICA-demixed ICs. In order to demonstrate the proposed over-complete ICA, (OC-ICA) experiments are conducted for performance analysis and evaluation. Results show that the OC-ICA implemented with classification can be very effective, provided the training samples are judiciously selected.

Two of the most challenging issues in the unsupervised linear spectral mixture analysis (ULSMA) are: 1) determining the number of signatures to form a linear mixing model; and 2) finding the signatures used to unmix data. These two issues do not occur in supervised LSMA since the target signatures are assumed to be known a priori. With recent advances in hyperspectral sensor technology, many unknown and subtle signal sources can now be uncovered and revealed and such signal sources generally cannot be identified by prior knowledge. Even when they can, the obtained knowledge may not be reliable, accurate, or complete. As a consequence, the resulting unmixed results may be misleading. This paper addresses these issues by introducing a new concept of inter-band spectral information (IBSI), which can be used to categorize signatures into background and target classes in terms of their sample spectral statistics. It then develops a component analysis (CA)-based ULSMA where two classes of signatures can be extracted directly from the data by two different CA-based transforms without requiring prior knowledge. In order to substantiate the utility of the proposed approach, synthetic images are used for experiments and real images are further used for validation