A Projection Neural Network for the Generalized Lasso

Inertial primal-dual projection neurodynamic approaches for constrained convex optimization problems and application to sparse recovery

Second-order (inertial) neurodynamic approaches are excellent tools for solving convex optimization problems in an accelerated manner, while the majority of existing approaches to neurodynamic approaches focus on unconstrained and simple constrained convex optimization problems. This paper presents a centralized primal - dual projection neurodynamic approach with time scaling (CPDPNA-TS). Built upon the heavy - ball method, this approach is tailored for convex optimization problems characterized by set and affine constraints, which contains a second-order projection ODE (ordinary differential equation) with derivative feedback for the primal variables and a first-order ODE for the dual variables. We prove a strong global solution to CPDPNA-TS in terms of existence, uniqueness and feasibility. Subsequently, we demonstrate that CPDPNA-TS has a nonergodic exponential and an ergodic O1t convergence properties when choosing suitable time scaling parameters, without strong convexity assumption on the objective functions. In addition, we extend the CPDPNA-TS to a case that CPDPNA-TS with a small perturbation and a case that has a distributed framework, and prove that two versions of the extension enjoy the similar convergence properties of CPDPNA-TS. Finally, we perform numerical experiments on sparse recovery in order to illustrate the effectiveness and superiority of the presented projection neurodynamic approaches.

Chest CT radiomics is feasible in evaluating bone changes in chronic kidney diseases

BACKGROUND

Non-invasive imaging methods are still lacking for evaluating bone changes in chronic kidney diseases (CKD).

PURPOSE

To investigate the feasibility of chest CT radiomics in evaluating bone changes caused by CKD.

MATERIAL AND METHODS

In total, 75 patients with stage 1 CKD (CKD1) and 75 with stage 5 CKD (CKD5) were assessed using the chest CT radiomics method. Radiomics features of bone were obtained using 3D Slicer software and were then compared between CKD1 and CKD5 cases. The methods of maximum correlation minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were used to establish a prediction model to determine CKD. The receiver operating characteristic (ROC) curve was used to determine the performance of the model.

RESULTS

Cases of CKD1 and CKD5 differed in 40 radiomics features (P <0.05). Using the mRMR and LASSO methods, five features were finally selected to establish a predication model. The area under the receiver operating characteristic curve of the model in the determination of CKD1 and CKD5 was 0.903 and 0.854, respectively, for the training and validation cohorts.

CONCLUSION

Chest CT radiomics is feasible in evaluating bone changes caused by CKD.

Construction of a prognostic prediction model for renal clear cell carcinoma combining clinical traits

Kidney renal clear cell carcinoma (KIRC) is one of the common malignant tumors of the urinary system. Patients with different risk levels are other in terms of disease progression patterns and disease regression. The poorer prognosis for high-risk patients compared to low-risk patients. Therefore, it is essential to accurately high-risk screen patients and gives accurate and timely treatment. Differential gene analysis, weighted correlation network analysis, Protein-protein interaction network, and univariate Cox analysis were performed sequentially on the train set. Next, the KIRC prognostic model was constructed using the least absolute shrinkage and selection operator (LASSO), and the Cancer Genome Atlas (TCGA) test set and the Gene Expression Omnibus dataset verified the model's validity. Finally, the constructed models were analyzed; including gene set enrichment analysis (GSEA) and immune analysis. The differences in pathways and immune functions between the high-risk and low-risk groups were observed to provide a reference for clinical treatment and diagnosis. A four-step key gene screen resulted in 17 key factors associated with disease prognosis, including 14 genes and 3 clinical features. The LASSO regression algorithm selected the seven most critical key factors to construct the model: age, grade, stage, GDF3, CASR, CLDN10, and COL9A2. In the training set, the accuracy of the model in predicting 1-, 2- and 3-year survival rates was 0.883, 0.819, and 0.830, respectively. The accuracy of the TCGA dataset was 0.831, 0.801, and 0.791, and the accuracy of the GSE29609 dataset was 0.812, 0.809, and 0.851 in the test set. Model scoring divided the sample into a high-risk group and a low-risk group. There were significant differences in disease progression and risk scores between the two groups. GSEA analysis revealed that the enriched pathways in the high-risk group mainly included proteasome and primary immunodeficiency. Immunological analysis showed that CD8 (+) T cells, M1 macrophages, PDCD1, and CTLA4 were upregulated in the high-risk group. In contrast, antigen-presenting cell stimulation and T-cell co-suppression were more active in the high-risk group. This study added clinical characteristics to constructing the KIRC prognostic model to improve prediction accuracy. It provides help to assess the risk of patients more accurately. The differences in pathways and immunity between high and low-risk groups were also analyzed to provide ideas for treating KIRC patients.