Detection of Sources in Non-Negative Blind Source Separation by Minimum Description Length Criterion

An MRI Radiogenomic Signature to Characterize the Transcriptional Heterogeneity Associated with Prognosis and Biological Functions in Glioblastoma

BACKGROUND

The study sought to establish a radiogenomic signature to evaluate the transcriptional heterogeneity that reflects the prognosis and tumour-related biological functions of patients with glioblastoma.

METHODS

Transcriptional subclones were identified via fully unsupervised deconvolution of RNA sequencing. A genomic prognostic risk score was developed from transcriptional subclone proportions in the development dataset (n = 532) and independently verified in the testing dataset (n = 225). Multimodal magnetic resonance imaging (MRI) analysis involved feature extraction from three distinct anatomical regions across four imaging sequences. Key features were selected to construct a radiogenomic signature predictive of the genomic risk score in the radiogenomic dataset (n = 99), with subsequent survival analysis conducted in the image testing dataset (n = 233).

RESULTS

A total of 8 transcriptional subclones were identified, of which the metabolic pathway subclone and spinocerebellar ataxia subclone were independent risk factors for overall survival. The genomic risk score effectively differentiated patient subgroups with divergent survival outcomes in both development (p < 0.001) and testing datasets (p = 0.0003). Nineteen radiomic features were selected to construct a radiogenomic signature, with these features being linked to hallmark cancer pathways and the malignant behaviours of cancer cells. The radiogenomic signature predicted overall survival in the image testing dataset (hazard ratios (HR) = 1.67, p = 0.011).

CONCLUSIONS

A prognostic radiogenomic signature was established and verified to characterize transcriptional subclones with underlying biological functions in glioblastoma.

Hyperspectral Tensor Completion Using Low-Rank Modeling and Convex Functional Analysis

Hyperspectral tensor completion (HTC) for remote sensing, critical for advancing space exploration and other satellite imaging technologies, has drawn considerable attention from recent machine learning community. Hyperspectral image (HSI) contains a wide range of narrowly spaced spectral bands hence forming unique electrical magnetic signatures for distinct materials, and thus plays an irreplaceable role in remote material identification. Nevertheless, remotely acquired HSIs are of low data purity and quite often incompletely observed or corrupted during transmission. Therefore, completing the 3-D hyperspectral tensor, involving two spatial dimensions and one spectral dimension, is a crucial signal processing task for facilitating the subsequent applications. Benchmark HTC methods rely on either supervised learning or nonconvex optimization. As reported in recent machine learning literature, John ellipsoid (JE) in functional analysis is a fundamental topology for effective hyperspectral analysis. We therefore attempt to adopt this key topology in this work, but this induces a dilemma that the computation of JE requires the complete information of the entire HSI tensor that is, however, unavailable under the HTC problem setting. We resolve the dilemma, decouple HTC into convex subproblems ensuring computational efficiency, and show state-of-the-art HTC performances of our algorithm. We also demonstrate that our method has improved the subsequent land cover classification accuracy on the recovered hyperspectral tensor.

Neural functional network of early Parkinson's disease based on independent component analysis

This work explored neural network changes in early Parkinson's disease: Resting-state functional magnetic resonance imaging was used to investigate functional alterations in different stages of Parkinson's disease (PD). Ninety-five PD patients (50 early/mild and 45 early/moderate) and 37 healthy controls (HCs) were included. Independent component analysis revealed significant differences in intra-network connectivity, specifically in the default mode network (DMN) and right frontoparietal network (RFPN), in both PD groups compared to HCs. Inter-network connectivity analysis showed reduced connectivity between the executive control network (ECN) and DMN, as well as ECN-left frontoparietal network (LFPN), in early/mild PD. Early/moderate PD exhibited decreased connectivity in ECN-LFPN, ECN-RFPN, ECN-DMN, and DMN-auditory network, along with increased connectivity in LFPN-cerebellar network. Correlations were found between ECN-DMN and ECN-LFPN connections with UPDRS-III scores in early/mild PD. These findings suggest that PD progression involves dysfunction in multiple intra- and inter-networks, particularly implicating the ECN, and a wider range of abnormal functional networks may mark the progression of the disease.

Nonnegative Blind Source Separation for Ill-Conditioned Mixtures via John Ellipsoid

Nonnegative blind source separation (nBSS) is often a challenging inverse problem, namely, when the mixing system is ill-conditioned. In this work, we focus on an important nBSS instance, known as hyperspectral unmixing (HU) in remote sensing. HU is a matrix factorization problem aimed at factoring the so-called endmember matrix, holding the material hyperspectral signatures, and the abundance matrix, holding the material fractions at each image pixel. The hyperspectral signatures are usually highly correlated, leading to a fast decay of the singular values (and, hence, high condition number) of the endmember matrix, so HU often introduces an ill-conditioned nBSS scenario. We introduce a new theoretical framework to attack such tough scenarios via the John ellipsoid (JE) in functional analysis. The idea is to identify the maximum volume ellipsoid inscribed in the data convex hull, followed by affinely mapping such ellipsoid into a Euclidean ball. By applying the same affine mapping to the data mixtures, we prove that the endmember matrix associated with the mapped data has condition number 1, the lowest possible, and that these (preconditioned) endmembers form a regular simplex. Exploiting this regular structure, we design a novel nBSS criterion with a provable identifiability guarantee and devise an algorithm to realize the criterion. Moreover, for the first time, the optimization problem for computing JE is exactly solved for a large-scale instance; our solver employs a split augmented Lagrangian shrinkage algorithm with all proximal operators solved by closed-form solutions. The competitiveness of the proposed method is illustrated by numerical simulations and real data experiments.

Endmember Estimation with Maximum Distance Analysis

Endmember estimation plays a key role in hyperspectral image unmixing, often requiring an estimation of the number of endmembers and extracting endmembers. However, most of the existing extraction algorithms require prior knowledge regarding the number of endmembers, being a critical process during unmixing. To bridge this, a new maximum distance analysis (MDA) method is proposed that simultaneously estimates the number and spectral signatures of endmembers without any prior information on the experimental data containing pure pixel spectral signatures and no noise, being based on the assumption that endmembers form a simplex with the greatest volume over all pixel combinations. The simplex includes the farthest pixel point from the coordinate origin in the spectral space, which implies that: (1) the farthest pixel point from any other pixel point must be an endmember, (2) the farthest pixel point from any line must be an endmember, and (3) the farthest pixel point from any plane (or affine hull) must be an endmember. Under this scenario, the farthest pixel point from the coordinate origin is the first endmember, being used to create the aforementioned point, line, plane, and affine hull. The remaining endmembers are extracted by repetitively searching for the pixel points that satisfy the above three assumptions. In addition to behaving as an endmember estimation algorithm by itself, the MDA method can co-operate with existing endmember extraction techniques without the pure pixel assumption via generalizing them into more effective schemes. The conducted experiments validate the effectiveness and efficiency of our method on synthetic and real data.