22 April 2023 in Information Sciences
16 July 2021 in IEEE Transactions on Geoscience and Remote Sensing
Tensor-based robust principal component analysis (PCA) methods are efficient to discover the low-rank part of a hyperspectral image for reducing redundant information and guarantee good classification results. However, current methods cannot remove noise adequately, and the residual noise remaining in the low-rank image limits the further improvement of classification performance. Thus, enhancing the robustness to noise is important and helpful for tensor-based robust PCA (RPCA) methods to process hyperspectral images. To this end, we propose a tensor-based RPCA method with a locality preserving graph and frontal slice sparsity (LPGTRPCA) for hyperspectral image classification. Specifically, a tensor $l_{2,2,1}$ norm that requires the frontal slice sparsity of a tensor is defined to extract the noise in the hyperspectral image from the frontal direction. What is more, a position-based Laplacian graph that preserves the local structures of a tensor according to the spatial position is designed for relieving the impact of the residual noise remaining in the low-rank image. Based on the tensor nuclear norm, the tensor $l_{2,2,1}$ norm, and the position-based Laplacian graph, LPGTRPCA efficiently separates the low-rank part with little noise from a raw hyperspectral image and achieves more robust classification results than current methods. LPGTRPCA is optimized by the alternative direction multiplier method (ADMM), and the convergence of solutions is experimentally demonstrated. In the experiments conducted on Indian Pines, Pavia University, and Salinas datasets, LPGTRPCA outperformed various state-of-the-art and classical tensor-based RPCA methods in terms of average class classification accuracy (AA), overall classification accuracy (OA), and kappa coefficient (KC).
1 August 2019 in Translational Lung Cancer Research
Background: Antiangiogenic agent-treated patients usually develop cavitation in their lung lesions. The clinical significance of lung cavitation development during antiangiogenic therapy has not been determined yet. Herein, we evaluated the clinical outcomes of patients who developed tumor cavitation following apatinib treatment and explored the mechanisms. Methods: In this study (Clinical Trial No. NCT03629691), 187 patients (77 lung cancer and 110 gastric adenocarcinoma patients) who had progressed or relapsed after undergoing at least two lines of systemic therapy in accordance with the NCCN guidelines for primary or metastatic lung tumors were treated with apatinib at a dosage of 250 mg per day between February 1, 2015 and May 19, 2017. The effect of lung cavitation development on locoregional control (LRC), progression-free survival (PFS), and overall survival (OS) was analyzed with Kaplan-Meier estimates and compared with the log-rank test. Zebrafish experiments were used to study the anticancer mechanism of apatinib in different tumors. Western-blotting was used to analyze the expression of Cyclin D1, p53, HIF-α, and VEGFR before and after apatinib treatment in both normoxia and hypoxia. Results: Cavitation development was beneficial in patients receiving apatinib therapy regardless of whether they had primary or metastatic lung cancer. Zebrafish experiments showed that apatinib inhibited tumor growth by both suppressing vascular growth and inhibiting cell proliferation. Vascular proliferation induced by the H1299 cell lines showed higher sensitivity to apatinib than that induced by the SCG-7901 cell line. However, apatinib showed weak tumor type selectivity on cell proliferation inhibition in vivo. Under hypoxic conditions, apatinib could not inhibit the protein expression of VEGFR and HIF-α in both cell lines; however, apatinib decreased the expression of cyclin D1 and P53 significantly. Conclusions: Lung cavitation development is common with apatinib therapy and is a potential prognostic marker. Apatinib inhibits tumor growth by both vessel growth inhibition and proliferation inhibition.
1 November 2021 in Applied Soft Computing
6 November 2019 in BMC Bioinformatics
Background: Mass spectra are usually acquired from the Liquid Chromatography-Mass Spectrometry (LC-MS) analysis for isotope labeled proteomics experiments. In such experiments, the mass profiles of labeled (heavy) and unlabeled (light) peptide pairs are represented by isotope clusters (2D or 3D) that provide valuable information about the studied biological samples in different conditions. The core task of quality control in quantitative LC-MS experiment is to filter out low-quality peptides with questionable profiles. The commonly used methods for this problem are the classification approaches. However, the data imbalance problems in previous control methods are often ignored or mishandled. In this study, we introduced a quality control framework based on the extreme gradient boosting machine (XGBoost), and carefully addressed the imbalanced data problem in this framework. Results: In the XGBoost based framework, we suggest the application of the Synthetic minority over-sampling technique (SMOTE) to re-balance data and use the balanced data to train the boosted trees as the classifier. Then the classifier is applied to other data for the peptide quality assessment. Experimental results show that our proposed framework increases the reliability of peptide heavy-light ratio estimation significantly. Conclusions: Our results indicate that this framework is a powerful method for the peptide quality assessment. For the feature extraction part, the extracted ion chromatogram (XIC) based features contribute to the peptide quality assessment. To solve the imbalanced data problem, SMOTE brings a much better classification performance. Finally, the XGBoost is capable for the peptide quality control. Overall, our proposed framework provides reliable results for the further proteomics studies.