Regular Model Research Articles

Regular Tetrahedron Model for the Assessment of High-Resolution Mass Spectrometry Data of Four-Way Fractionated Dissolved Organic Matter.

A regular tetrahedron model was established to pierce the fractionation of dissolved organic matter (DOM) among quaternary components by using high-resolution mass spectrometry. The model can stereoscopically visualize molecular formulas of DOM to show the preference to each component according to the position in a regular tetrahedron. A classification method was subsequently developed to divide molecular formulas into 15 categories related to fractionation ratios, the relative change of which was demonstrated to be convergent with the uncertainty of mass peak area. The practicality of the regular tetrahedron model was verified by seven kinds of sludge from waste leachate treatment and sewage wastewater treatment plants by using stratification of extracellular polymeric substances coupled with Orbitrap MS as an example, presenting the DOM chemodiversity in stratified sludge flocs. Sensitivity analysis proved that classification results were relatively stable with the perturbation of four model parameters. Multinomial logistic regression analysis could further help identify the effect of molecular properties on the fractionation of DOM based on the classification results of the regular tetrahedron model. This model offers a methodology for the assessment of specificity of sequential extraction on DOM from solid or semisolid components and simplifies the complex mathematical expression of fractionation coefficients for quaternary components.

Exploring spatiotemporal patterns of algal cell density in lake Dianchi with explainable machine learning

The escalating global occurrence of algal blooms poses a growing threat to ecosystem services. In this study, the spatiotemporal heterogeneity of water quality parameters was leveraged to partition Lake Dianchi into three clusters. Considering water quality parameters and both the delayed and instantaneous effects of meteorological factors, ensemble learning, and quasi-Monte Carlo methods were employed to predict daily algal cell density (AD) between January 2021 and January 2024. Consistently, superior predictive accuracy across all three clusters was exhibited by the Stacking-Elastic-Net regularization model. Furthermore, the minimum combination of drivers that achieved near-optimal accuracy for each cluster was identified, striking a balance between accuracy and cost. The ranking of the effect of drivers on AD varied by cluster, while the delayed effect of meteorological factors on AD generally outweighed their instantaneous effect for all clusters. Additionally, the heterogeneous or homogeneous thresholds and responses between drivers and AD were explored. These findings could serve as a scientific and cost-effective basis for government agencies to develop regional sustainable strategies for managing water quality.

Solubility of oxazepam in supercritical carbon dioxide: Experimental and modeling

This study thoroughly investigates the solubility of oxazepam in supercritical carbon dioxide (SC-CO2) at temperatures of 308, 318, 328, and 338 K and pressures ranging from 12 to 30 MPa. The solubility measurements revealed a mole fraction of oxazepam ranging from 2.50 × 10−6 to 7.13 × 10−5, with the highest solubility observed at 338 K and 30 MPa. The solubility data were effectively modeled using semi-empirical density-based models (Mendez-Santiago and Teja (MST), Chrastil, Bartle et al., Kumar and Johnston (K-J), and Alwi-Garlapati), two equations of state (Peng-Robinson and modified-Pazuki) and regular solution models. The K-J model emerged as the best fit for the experimental data, boasting the lowest Average Absolute Relative Deviation (AARD) value of 7.73 %. The Peng-Robinson equation of state outperformed the modified-Pazuki equation, with AARD values of 15.71 % and 18.15 %, respectively. The study's key finding is the low solubility of oxazepam in SC-CO2, which suggests that supercritical antisolvent techniques could be effectively employed for synthesizing nanoparticles of this pharmaceutical compound. These findings have practical implications as they provide valuable insights for optimizing drug formulation processes and demonstrate the potential of SC-CO2 in pharmaceutical applications.

Automatic classification of fetal heart rate based on a multi-scale LSTM network.

Fetal heart rate monitoring during labor can aid healthcare professionals in identifying alterations in the heart rate pattern. However, discrepancies in guidelines and obstetrician expertise present challenges in interpreting fetal heart rate, including failure to acknowledge findings or misinterpretation. Artificial intelligence has the potential to support obstetricians in diagnosing abnormal fetal heart rates. Employ preprocessing techniques to mitigate the effects of missing signals and artifacts on the model, utilize data augmentation methods to address data imbalance. Introduce a multi-scale long short-term memory neural network trained with a variety of time-scale data for automatically classifying fetal heart rate. Carried out experimental on both single and multi-scale models. The results indicate that multi-scale LSTM models outperform regular LSTM models in various performance metrics. Specifically, in the single models tested, the model with a sampling rate of 10 exhibited the highest classification accuracy. The model achieves an accuracy of 85.73%, a specificity of 85.32%, and a precision of 85.53% on CTU-UHB dataset. Furthermore, the area under the receiver operating curve of 0.918 suggests that our model demonstrates a high level of credibility. Compared to previous research, our methodology exhibits superior performance across various evaluation metrics. By incorporating alternative sampling rates into the model, we observed improvements in all performance indicators, including ACC (85.73% vs. 83.28%), SP (85.32% vs. 82.47%), PR (85.53% vs. 82.84%), recall (86.13% vs. 84.09%), F1-score (85.79% vs. 83.42%), and AUC(0.9180 vs. 0.8667). The limitations of this research include the limited consideration of pregnant women's clinical characteristics and disregard the potential impact of varying gestational weeks.

Image reconstruction based on TV-L1 model for planar array capacitance defect detection

Planar array capacitive imaging is an emerging nondestructive testing (NDT) technology with broad application prospects. The severe ill-posed inverse problem of planar array capacitive imaging reduces quality of reconstructed images. In this paper, a total variation regularization model with an L1-norm (TV-L1 model) of 3 × 4 planar array capacitance imaging is established for imaging the defects detected in the inner layers of multi-layer composite components. Considering the solution instability caused by the non-differentiability of the TV-L1 model, a variable splitting self-adaptive augmented Lagrange alternating direction algorithm (VS-SALAD) is proposed. An augmented Lagrange method enhances model splitability, and a series of subproblems are obtained by variable splitting operation. The subproblems are solved iteratively using alternating minimization method with self-adaptive penalty parameter. Experimental results demonstrate that TV-L1 model effectively alleviates the ill-posed problem, and the proposed algorithm significantly improves both the quality of reconstructed images and solving speed of the TV-L1 model.

High Performance CNN Accelerators based on Hardware and Algorithm Co-Optimization

The efficacy of convolutional neural networks (CNNs) has led to their extensive application in picture recognition and categorization. Nevertheless, embedded systems face challenges when it comes to storing the massive volumes of weight data required by CNNs in their on-chip memory. Pruning a convolutional neural network (CNN) model can reduce its size with no impact on accuracy; however, when used with a parallel architecture, the resulting model will be slower to execute. A CNN compression method that is hardware-centric is introduced in this paper. A model of a deep neural network (DNN) will include "pruning layers (P-layers)" and "no-pruning layers (NP-layers)" attached to it. For effective and parallel processing, an NP-layer employs a regular distribution for its weights. Pruning causes a P-layer to have an irregular form, yet the high compression ratio it yields makes the shape undesirable. Using uniform and gradual quantization methods, we can achieve a processing efficiency/compression ratio trade-off with a small loss of precision. Integrating multiple parallel finite impulse response (FIR) filters into an NP-layer distributed convolutional architecture, we further improve the regular model. The P-layer irregular sparse model is suggested to use an ADF-based processing element. The suggested compression strategy and hardware architecture can be utilised by a hardware/algorithm co-optimization (HACO) method to run an NP→P hybrid compressed CNN model on FPGAs. The VGG-16 network achieves a compression ratio of 27.5× with a top-5 accuracy loss of 0.44% by using a hardware accelerator on a single FPGA chip without off-chip memory. A result of 83.0 FPS, or 1.8 times quicker, was achieved when the compressed VGG-16 model was implemented on a Xilinx VCU118 evaluation board for image applications. Index Terms - CNN, Accelerators, Co-Optimization.

Deep Neural Networks and Tabular Data: A Survey.

Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous datasets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their adaptation to tabular data for inference or data generation tasks remains highly challenging. To facilitate further progress in the field, this work provides an overview of state-of-the-art deep learning methods for tabular data. We categorize these methods into three groups: data transformations, specialized architectures, and regularization models. For each of these groups, our work offers a comprehensive overview of the main approaches. Moreover, we discuss deep learning approaches for generating tabular data and also provide an overview over strategies for explaining deep models on tabular data. Thus, our first contribution is to address the main research streams and existing methodologies in the mentioned areas while highlighting relevant challenges and open research questions. Our second contribution is to provide an empirical comparison of traditional machine learning methods with 11 deep learning approaches across five popular real-world tabular datasets of different sizes and with different learning objectives. Our results, which we have made publicly available as competitive benchmarks, indicate that algorithms based on gradient-boosted tree ensembles still mostly outperform deep learning models on supervised learning tasks, suggesting that the research progress on competitive deep learning models for tabular data is stagnating. To the best of our knowledge, this is the first in-depth overview of deep learning approaches for tabular data; as such, this work can serve as a valuable starting point to guide researchers and practitioners interested in deep learning with tabular data.

Classification of HER2 status across multiple cancers using epigenomic profiles from a novel liquid biopsy assay.

3047 Background: The efficacy of trastuzumab deruxtecan in multiple cancers led to a recent FDA granting of priority review for the treatment of adults with HER2-positive solid tumors. This underscores the critical need for reliable assessment of HER2 expression across cancers. The current standard using IHC/ISH for HER2 scoring is fraught with challenges including scoring discordance and tumor heterogeneity. Here we describe the ability to classify HER2 status from 1 ml of plasma, using epigenomic signatures from a novel multi-analyte liquid biopsy (LBx) platform, offering a minimally invasive approach for patient (pt) selection across cancers. Methods: We selected 179 samples from 172 pts with advanced breast (BC), gastro-esophageal (GEA) and ovarian (OV) cancers who had associated HER2 status scored from tissue-based IHC/ISH according to ASCO/CAP guidelines (table). Samples were taken at baseline or at progression and those with detectable cell free DNA, as assessed by iChorCNA, were profiled for genome-wide epigenomic signals across histone modifications associated with active enhancers, promoters and DNA methylation. A regularized regression model developed to classify HER2 status in BC cell lines and was refined and validated for HER2 status prediction for each pt cohort (HER2+ = 3+, 2+/ISH+; HER2- = 2+/ISH-, 1+, 0). The BC cell-line derived HER2 classifier was refined to incorporate GEA and OV cancer specific features before being applied to those samples. Performance was assessed via AUC in a leave-one-out cross-validation schema. We also evaluated HER2 status at progression in a subset of pts with benchmarked HER2 IHC to assess dynamic changes in receptor status by LBx. Results: The epigenomic HER2 classifier was applied to all samples with ctDNA detectable by ichorCNA (90 of 179; 50%). HER2 classification of BC pts by epigenomic liquid biopsy was concordant with standard tissue-based IHC for 64/72 (89%) BC samples (AUC 0.9, table). HER2 classifier predictions for all longitudinally collected samples were concordant with IHC-based HER2 status, including the one patient whose status switched from HER2+ to HER2- at progression. Accurate classification of 11/14 (79%, GEA) and 4/4 (100%, OV) pts was achieved using the indication-refined HER2 classifier. Conclusions: We demonstrate proof of concept for a HER2 classification approach using comprehensive epigenomic signals from 1 ml of plasma that could be applied across multiple cancers. With further development, our genome-wide profiling approach could alleviate clinical constraints associated with multiple tissue-based HER2 scoring assays (IHC/ISH) and enable longitudinal monitoring of HER2 status on therapy. [Table: see text]

Guided regularization and its application for image restoration

Variational regularization, renowned for its sound theoretical foundations and impressive performance, is widely used in image restoration. The traditional regularization models typically use a predefined regularizer to promote smoothness in the solution. However, these models do not explicitly take into account any external information that should be preserved in the restoration. In this paper, we introduce a novel guided regularization model to enhance the efficacy of traditional regularization. Our model incorporates an external guidance regularizer, utilizing a guidance image to bolster the quality of restoration. By integrating this external information into the regularization process, the model is better equipped to preserve specific features or attributes indicated by the guidance image, leading to more accurate and aesthetically pleasing restored images. Furthermore, we demonstrate the convexity of the model and prove the existence and uniqueness of the solution. The alternating direction method of multipliers (ADMM) algorithm is employed to numerically solve the proposed model. In the experimental evaluation, the proposed model is applied to image denoising and deblurring tasks. The experiments successfully validate the proposed model and algorithm. Compared with several state-of-the-art models, the proposed model demonstrates the best performance in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).

"Sweet space" strategy for solvent system selection in countercurrent chromatography: A case study on separation of polyunsaturated fatty acids from borage oil.

This study presents a comprehensive strategy for the selection and optimization of solvent systems in countercurrent chromatography (CCC) for the effective separation of compounds. With a focus on traditional organic solvent systems, the research introduces a "sweet space" strategy that merges intuitive understanding with mathematical accuracy, addressing the significant challenges in solvent system selection, a critical bottleneck in the widespread application of CCC. By employing a combination of volume ratios and graphical representations, including both regular and trirectangular tetrahedron models, the proposed approach facilitates a more inclusive and user-friendly strategy for solvent system selection. This study demonstrates the potential of the proposed strategy through the successful separation of gamma-linolenic acid, oleic acid, and linoleic acid from borage oil, highlighting the strategy's effectiveness and practical applicability in CCC separations.

Model selection for generalized linear models with weak factors

AbstractThe literature has witnessed an upsurge of interest in model selection in diverse fields and optimization applications. Despite the substantial progress, model selection remains a significant challenge when covariates are highly correlated, particularly within economic and financial datasets that exhibit cross‐sectional and serial dependency. In this paper, we introduce a novel methodology named factor augmented regularized model selection with weak factors (WeakFARM) for generalized linear models in the presence of correlated covariates with weak latent factor structure. By identifying weak latent factors and idiosyncratic components and employing them as predictors, WeakFARM converts the challenge from model selection with highly correlated covariates to that with weakly correlated ones. Furthermore, we develop a variable screening method based on the proposed WeakFARM method. Comprehensive theoretical guarantees including estimation consistency, model selection consistency and sure screening property are also provided. We demonstrate the effectiveness of our approach by extensive simulation studies and a real data application in economic forecasting.

The oncologic burden of residual disease in incidental gallbladder cancer: An elastic net regression model to profile high-risk features

IntroductionIncidental Gallbladder Cancer (IGBC) following cholecystectomy constitutes a significant portion of gallbladder cancer diagnoses. Re-exploration is advocated to optimize disease clearance and enhance survival rates. The consistent association of residual disease (RD) with inferior oncologic outcomes prompts a critical examination of re-resection's role as a modifying factor in the natural history of IGBC. MethodsAll patients diagnosed with gallbladder cancer between 2012 and 2022 were included. An elastic net regularized regression model was employed to profile high-risk predictors of RD within the IGBC group. Survival outcomes were assessed based on resection margins and RD. ResultsAmong the 181 patients undergoing re-exploration for IGBC, 133 (73.5 %) harbored RD, while 48 (26.5 %) showed no evidence. The elastic net model, utilizing a selected λ = 0.029, identified six coefficients associated with the risk of RD: aspiration from cholecystectomy (0.141), hepatic tumor origin (1.852), time to re-exploration >8 weeks (1.879), positive margin status (2.575), higher T stage (1.473), and poorly differentiated tumors (2.241). Furthermore, the study revealed a median overall survival of 44 months (CI 38–60) for IGBC patients with no evidence of RD, compared to 31 months (23–42) for those with RD (p < 0.001). ConclusionRe-resection revealed a high incidence of RD (73.5 %), significantly correlating with poorer survival outcomes. The preoperative identification of high-risk features provides a reliable biological disease profile. This aids in strategic preselection of patients who may benefit from re-resection, underscoring the need to consolidate outcomes with tailored chemotherapy for those with unfavorable characteristics.

OPTIMIZING HEART ATTACK DIAGNOSIS USING RANDOM FOREST WITH BAT ALGORITHM AND GREEDY CROSSOVER TECHNIQUE

Cardiovascular disease stands as one of the primary contributors to global mortality, with the World Health Organization (WHO) reporting approximately 17.9 million deaths annually. Swift and accurate diagnosis of heart attacks is crucial to ensure timely and specialized intervention for patients afflicted by this ailment. A machine learning algorithm that can be employed for addressing such issues is the Random Forest algorithm. However, the efficacy of the model is significantly influenced by the features selected during the training phase. To mitigate this, the Binary Bat Algorithm (BBA) with greedy crossover has been utilized to enhance feature selection within the model. This approach is particularly adept at preventing convergence issues often associated with local minima. The optimal parameters for BBA with greedy crossover are determined to be , , , and . With these parameters, the proposed algorithm identifies the most relevant features, including age, gender, cp, chol, thalach, oldpeak, slope, and ca, achieving an accuracy of 94.19% on the training data and 91.8% on the test data. Furthermore, the precision and recall values for both classes range from 0.87 to 0.96, contributing to an approximate -score of 0.92. The proposed method has increased its -score by 0.05 if compared with the regular Random Forest model. These results underscore the effectiveness of the proposed algorithm in providing accurate and reliable predictions for heart disease diagnosis. As such, this model makes diagnosing heart attack more convenient and effective because it does not require too much medical features or patient data. Hopefully, the results of this research help medical practitioners make better and timely decisions in the diagnosis and treatment of heart attacks, as well as assist in planning more effective public health programs for heart attack prevention.

Machine learning versus deep learning in land system science: a decision-making framework for effective land classification

This review explores the comparative utility of machine learning (ML) and deep learning (DL) in land system science (LSS) classification tasks. Through a comprehensive assessment, the study reveals that while DL techniques have emerged with transformative potential, their application in LSS often faces challenges related to data availability, computational demands, model interpretability, and overfitting. In many instances, traditional ML models currently present more effective solutions, as illustrated in our decision-making framework. Integrative opportunities for enhancing classification accuracy include data integration from diverse sources, the development of advanced DL architectures, leveraging unsupervised learning, and infusing domain-specific knowledge. The research also emphasizes the need for regular model evaluation, the creation of diversified training datasets, and fostering interdisciplinary collaborations. Furthermore, while the promise of DL for future advancements in LSS is undeniable, present considerations often tip the balance in favor of ML models for many classification schemes. This review serves as a guide for researchers, emphasizing the importance of choosing the right computational tools in the evolving landscape of LSS, to achieve reliable and nuanced land-use change data.

Blind deblurring text images via Beltrami regularization

This article proposes a blind image deblurring model based on Beltrami regularization. The existence and uniqueness of the Beltrami model are proved, and we perform a theoretical analysis of the convergence and error estimation of the algorithm for solving the Beltrami regularization model. Meanwhile, we apply a half-quadratic splitting algorithm to solve it and obtain the blur kernel of the blurred image. Furthermore, we get a clean image through some non-blind deblurring algorithms. Finally, we compare this with the state-of-art methods, and our algorithm has specific performance improvements and advantages in the text images.© 2024 Elsevier Ltd. All rights reserved.

Activity Calculation and Vacuum Separation Theoretical Research concerning Ag–Cu, Ag–Sb and Cu–Sb Binary Alloys

The Ag–Cu–Sb system is a key component of lead anode slime and boasts an exceptionally high economic recovery value. In this work, six models, including the Molecular Interaction Volume Model (MIVM), Modified Molecular Interaction Volume Model (M-MIVM), Wilson equation, Miedema model, Regular Solution Model (RSE) and Sub-Regular Solution Model (SRSE), are used to calculate the predicted values of the activity and its deviations with experimental data for binary alloys in the Ag–Cu–Sb system for the first time. The result reveals that the overall means of the average relative deviation and average standard deviation of the M-MIVM are 0.01501 and 3.97278%, respectively, which are about two to six times smaller than those of the other five models, indicating the stability and reliability of the M-MIVM. In the meantime, the predicted data of the Cu–Ag binary alloy at 1423 K, Sb–Ag binary alloy at 1250 K and Sb–Cu binary alloy at 1375 K calculated from the M-MIVM are more reliable and pass the Herington test. Then, the separation coefficient–composition (β–x), temperature–composition (T–x–y) and pressure–composition (P–x–y) of the Cu–Ag, Sb–Ag and Sb–Cu binary alloys are plotted based on the M-MIVM and vacuum theories, showing that the Cu–Ag binary alloy is relatively difficult to separate and that high temperatures or high copper contents are detrimental to obtaining high-purity silver. Meanwhile, theoretical data of the T–x–y diagram are consistent with the available experimental data. These results can guide vacuum separation experiments and industrial production concerning Ag–Cu, Ag–Sb and Cu–Sb binary alloys.

Eigenspectrum regularisation reverse neighbourhood discriminative learning

AbstractLinear discriminant analysis is a classical method for solving problems of dimensional reduction and pattern classification. Although it has been extensively developed, however, it still suffers from various common problems, such as the Small Sample Size (SSS) and the multimodal problem. Neighbourhood linear discriminant analysis (nLDA) was recently proposed to solve the problem of multimodal class caused by the contravention of independently and identically distributed samples. However, due to the existence of many small‐scale practical applications, nLDA still has to face the SSS problem, which leads to instability and poor generalisation caused by the singularity of the within‐neighbourhood scatter matrix. The authors exploit the eigenspectrum regularisation techniques to circumvent the singularity of the within‐neighbourhood scatter matrix of nLDA, which is called Eigenspectrum Regularisation Reverse Neighbourhood Discriminative Learning (ERRNDL). The algorithm of nLDA is reformulated as a framework by searching two projection matrices. Three eigenspectrum regularisation models are introduced to our framework to evaluate the performance. Experiments are conducted on the University of California, Irvine machine learning repository and six image classification datasets. The proposed ERRNDL‐based methods achieve considerable performance.

LSTM-Autoencoder Deep Learning Model for Anomaly Detection in Electric Motor

Anomaly detection is the process of detecting unusual or unforeseen patterns or events in data. Many factors, such as malfunctioning hardware, malevolent activities, or modifications to the data’s underlying distribution, might cause anomalies. One of the key factors in anomaly detection is balancing the trade-off between sensitivity and specificity. Balancing these trade-offs requires careful tuning of the anomaly detection algorithm and consideration of the specific domain and application. Deep learning techniques’ applications, such as LSTMs (long short-term memory algorithms), which are autoencoders for detecting an anomaly, have garnered increasing attention in recent years. The main goal of this work was to develop an anomaly detection solution for an electrical machine using an LSTM-autoencoder deep learning model. The work focused on detecting anomalies in an electrical motor’s variation vibrations in three axes: axial (X), radial (Y), and tangential (Z), which are indicative of potential faults or failures. The presented model is a combination of the two architectures; LSTM layers were added to the autoencoder in order to leverage the LSTM capacity for handling large amounts of temporal data. To prove the LSTM efficiency, we will create a regular autoencoder model using the Python programming language and the TensorFlow machine learning framework, and compare its performance with our main LSTM-based autoencoder model. The two models will be trained on the same database, and evaluated on three primary points: training time, loss function, and MSE anomalies. Based on the obtained results, it is clear that the LSTM-autoencoder shows significantly smaller loss values and MSE anomalies compared to the regular autoencoder. On the other hand, the regular autoencoder performs better than the LSTM, comparing the training time. It appears then, that the LSTM-autoencoder presents a superior performance although it was slower than the standard autoencoder due to the complexity of the added LSTM layers.

Preoperative CT-based radiomic prognostic index to predict the benefit of postoperative radiotherapy in patients with non-small cell lung cancer: a multicenter study

BackgroundThe value of postoperative radiotherapy (PORT) for patients with non-small cell lung cancer (NSCLC) remains controversial. A subset of patients may benefit from PORT. We aimed to identify patients with NSCLC who could benefit from PORT.MethodsPatients from cohorts 1 and 2 with pathological Tany N2 M0 NSCLC were included, as well as patients with non-metastatic NSCLC from cohorts 3 to 6. The radiomic prognostic index (RPI) was developed using radiomic texture features extracted from the primary lung nodule in preoperative chest CT scans in cohort 1 and validated in other cohorts. We employed a least absolute shrinkage and selection operator-Cox regularisation model for data dimension reduction, feature selection, and the construction of the RPI. We created a lymph-radiomic prognostic index (LRPI) by combining RPI and positive lymph node number (PLN). We compared the outcomes of patients who received PORT against those who did not in the subgroups determined by the LRPI.ResultsIn total, 228, 1003, 144, 422, 19, and 21 patients were eligible in cohorts 1–6. RPI predicted overall survival (OS) in all six cohorts: cohort 1 (HR = 2.31, 95% CI: 1.18–4.52), cohort 2 (HR = 1.64, 95% CI: 1.26–2.14), cohort 3 (HR = 2.53, 95% CI: 1.45–4.3), cohort 4 (HR = 1.24, 95% CI: 1.01–1.52), cohort 5 (HR = 2.56, 95% CI: 0.73–9.02), cohort 6 (HR = 2.30, 95% CI: 0.53–10.03). LRPI predicted OS (C-index: 0.68, 95% CI: 0.60–0.75) better than the pT stage (C-index: 0.57, 95% CI: 0.50–0.63), pT + PLN (C-index: 0.58, 95% CI: 0.46–0.70), and RPI (C-index: 0.65, 95% CI: 0.54–0.75). The LRPI was used to categorize individuals into three risk groups; patients in the moderate-risk group benefited from PORT (HR = 0.60, 95% CI: 0.40–0.91; p = 0.02), while patients in the low-risk and high-risk groups did not.ConclusionsWe developed preoperative CT-based radiomic and lymph-radiomic prognostic indexes capable of predicting OS and the benefits of PORT for patients with NSCLC.

Hyperspectral Image Mixed Noise Removal via Double Factor Total Variation Nonlocal Low-Rank Tensor Regularization

A hyperspectral image (HSI) is often corrupted by various types of noise during image acquisition, e.g., Gaussian noise, impulse noise, stripes, deadlines, and more. Thus, as a preprocessing step, HSI denoising plays a vital role in many subsequent tasks. Recently, a variety of mixed noise removal approaches have been developed for HSI, and the methods based on spatial–spectral double factor and total variation (DFTV) regularization have achieved comparable performance. Additionally, the nonlocal low-rank tensor model (NLR) is often employed to characterize spatial nonlocal self-similarity (NSS). Generally, fully exploring prior knowledge can improve the denoising performance, but it significantly increases the computational cost when the NSS prior is employed. To solve this problem, this article proposes a novel DFTV-based NLR regularization (DFTVNLR) model for HSI mixed noise removal. The proposed model employs low-rank tensor factorization (LRTF) to characterize the spectral global low-rankness (LR), introduces 2-D and 1-D TV constraints on double-factor to characterize the spatial and spectral local smoothness (LS), respectively. Meanwhile, the NLR is applied to the spatial factor to characterize the NSS. Then, we developed an algorithm based on proximal alternating minimization (PAM) to solve the proposed model effectively. Particularly, we effectively controlled the computational cost from two aspects, namely taking small-sized double factor as regularization object and putting the time-consuming NLR model before the main loop with fewer iterations to solve it independently. Finally, considerable experiments on simulated and real noisy HSI substantiate that the proposed method is superior to the related state-of-the-art methods in balancing the denoising effect and speed.