Search for: All records

Chest X-rays are commonly used for diagnosing and characterizing lung diseases, but the complex morphological patterns in radiographic appearances can challenge clinicians in making accurate diagnoses. To address this challenge, various learning methods have been developed for algorithm-aided disease detection and automated diagnosis. However, most existing methods fail to account for the heterogeneous variability in longitudinal imaging records and the presence of missing or inconsistent temporal data. In this paper, we propose a novel longitudinal learning framework that enriches inconsistent imaging data over sequential time points by leveraging 2D Principal Component Analysis (2D-PCA) and a robust adaptive loss function. We also derive an efficient solution algorithm that ensures both objective and sequence convergence for the non-convex optimization problem. Our experiments on the CheXpert dataset demonstrate improved performance in capturing indicative abnormalities in medical images and achieving satisfactory diagnoses. We believe that our method will be of significant interest to the research community working on medical image analysis. 

The COVID-19 pandemic caused by SARS-CoV-2 has emphasized the importance of studying virus-host protein-protein interactions (PPIs) and drug-target interactions (DTIs) to discover effective antiviral drugs. While several computational algorithms have been developed for this purpose, most of them overlook the interplay pathways during infection along PPIs and DTIs. In this paper, we present a novel multipartite graph learning approach to uncover hidden binding affinities in PPIs and DTIs. Our method leverages a comprehensive biomolecular mechanism network that integrates protein-protein, genetic, and virus-host interactions, enabling us to learn a new graph that accurately captures the underlying connected components. Notably, our method identifies clustering structures directly from the new graph, eliminating the need for post-processing steps. To mitigate the detrimental effects of noisy or outlier data in sparse networks, we propose a robust objective function that incorporates the L2,p-norm and a constraint based on the pth-order Ky-Fan norm applied to the graph Laplacian matrix. Additionally, we present an efficient optimization method tailored to our framework. Experimental results demonstrate the superiority of our approach over existing state-of-the-art techniques, as it successfully identifies potential repurposable drugs for SARS-CoV-2, offering promising therapeutic options for COVID-19 treatment. 

Graphical representations are essential for comprehending high-dimensional data across diverse fields, yet their construction often presents challenges due to the limitations of traditional methods. This paper introduces a novel methodology, Beyond Simplex Sparse Representation (BSSR), which addresses critical issues such as parameter dependencies, scale inconsistencies, and biased data interpretation in constructing similarity graphs. BSSR leverages the robustness of sparse representation to noise and outliers, while incorporating deep learning techniques to enhance scalability and accuracy. Furthermore, we tackle the optimization of the standard simplex, a pervasive problem, by introducing a transformative approach that converts the constraint into a smooth manifold using the Hadamard parametrization. Our proposed Tangent Perturbed Riemannian Gradient Descent (T-PRGD) algorithm provides an efficient and scalable solution for optimization problems with standard simplex or L1-norm sphere constraints. These contributions, including the BSSR methodology, robustness and scalability through deep representation, shift-invariant sparse representation, and optimization on the unit sphere, represent major advancements in the field. Our work offers novel perspectives on data representation challenges and sets the stage for more accurate analysis in the era of big data.