Search

Nasopharyngeal carcinoma is frequently an undifferentiated squamous cell carcinoma, which is primarily treated with radiotherapy with or without chemotherapy; however, for residual or recurrent cancer, salvage surgery is the treatment of choice for resectable disease because it reduces the significant morbidity associated with re-irradiation. This review highlights the current surgical approach, mapping the extent of disease with an emphasis on magnetic resonance imaging (MRI) and integrated positron-emission tomography (PET)/computed tomography (CT), imaging features that determine operability for nasopharyngectomy and neck dissection, and need for a succinct radiological report and multidisciplinary team discussion, which are of paramount importance for successful surgical planning.

Missing data widely exist in industrial processes and lead to difficulties in modelling, monitoring, fault diagnosis, and control. In this paper, we propose a nonlinear method to handle the missing data problem in the offline modelling stage or/and the online monitoring stage of statistical process monitoring. We provide a fast incremental nonlinear matrix completion (FINLMC) method for missing data imputation, which enables us to use kernel methods such as kernel principal component analysis (KPCA) to monitor nonlinear multivariate processes even when there are missing data. We also provide theoretical analysis for the effectiveness of the proposed method. Experiments show that the proposed method can reduce the false alarm rate and improve the fault detection rate in nonlinear processing monitoring with missing data. The proposed method FINLMC can also be used to solve missing data in other problems such as classification and process control.

Multilabel learning has been extensively studied in the past years, as it has many applications in different domains. It aims at annotating the labels for unseen data according to training data, which are often high dimensional in both instance and feature levels. The training data often have noisy and redundant information on these two levels. As an effective data preprocessing step, instance and feature selection should both be performed to find relevant training instances for each testing instance and relevant features for each label, respectively. However, most of the existing methods overlook the input-output correlation in each kind of selection. It will lead to the performance degradation. This article presents a formulation for multilabel learning from a topic view that exploits the dependence between features and labels in a topic space. We can perform effective instance and feature selection in the latent topic space, as the relationship between the input and output spaces is well captured in this space. The results from intensive experiments on various benchmarks demonstrate the effectiveness of the proposed framework.

Existing partial sequence labeling models mainly focus on a max-margin framework that fails to provide an uncertainty estimation of the prediction. Furthermore, the unique ground-truth disambiguation strategy employed by these models may include wrong label information for parameter learning. In this article, we propose structured Gaussian processes for partial sequence labeling (SGPPSL), which encodes uncertainty in the prediction and does not need extra effort for model selection and hyperparameter learning. The model employs factor-as-piece approximation that divides the linear-chain graph structure into the set of pieces, which preserves the basic Markov random field structure and effectively avoids handling a large number of candidate output sequences generated by partially annotated data. Then, confidence measure is introduced in the model to address different contributions of candidate labels, which enables the ground-truth label information to be utilized in parameter learning. Based on the derived lower bound of the variational lower bound of the proposed model, variational parameters and confidence measures are estimated in the framework of alternating optimization. Moreover, a weighted Viterbi algorithm is proposed to incorporate confidence measures to sequence prediction, which considers label ambiguity arose from multiple annotations in the training data and thus helps improve the performance. SGPPSL is evaluated on several sequence labeling tasks and the experimental results show the effectiveness of the proposed model.

The purpose of this article was to report a case of unilateral late-onset nontuberculous mycobacterial keratitis after small incision lenticule extraction (SMILE).This was a case report.A 27-year-old woman presented with Mycobacterium chelonae keratitis 3 weeks after uncomplicated SMILE with a solitary interface infiltrate. The keratitis worsened after an initial response to topical fortified and interface antibiotic irrigation. Despite repeated interface irrigation and topical and oral antibiotics, progressive, diffuse stromal infiltrates followed by melting of the cap ensued over the next 6 weeks. Cap amputation and intrastromal antibiotic injection followed by prolonged topical and oral antibiotics usage for the following 5 weeks led to infiltrate resolution and re-epithelization of the residual stromal bed. All medications were tapered off over 6 months after initial presentation without recurrence, but anterior stromal scarring and corneal neovascularization persisted.Cap amputation and intrastromal antibiotic injection for intractable post-SMILE keratitis can prevent the need for therapeutic keratoplasty.

In recent years, the estimation of the remaining useful life (RUL) has become an increasingly important topic. Existing RUL estimation studies mainly focus on linear degradation cases or degradation processes that can be linearized. A few nonlinear degradation models often rely on a training process based on a batch of samples obtained from the same population. Consequently, large bias or uncertainties may often occur under varying stress conditions. To address this problem, this article proposes a prognostic approach based on an adaptive particle filter (PF) to predict the RUL of the dynamic degradation systems using system degradation records. First, a nonlinear degradation model based on the fusion of an exponential item and a power law wear model were derived to capture the wear process under varying stress conditions. Second, the PF method was used to update the model parameters by treating the parameters as hidden state variables. Third, an adaptive strategy was derived based on the expectation–maximization algorithm and particle smoother algorithm to recursively update the hidden variables. Finally, an actual magnetic head wear dataset obtained from an actual manufacturing plant is used to verify the effectiveness of the proposed approach. The results reveal that the proposed approach significantly improves the prediction accuracy compared with the PF-based approach and extends Kalman-filter-based approach.

Background Circulating thrombospondin-2 (TSP2) levels were associated with the development of heart failure (HF) in recent studies. However, these studies included only a minority of patients with type 2 diabetes, which is associated with an increased HF risk. As hyperglycemia induces TSP2 expression and its tissue expression increases in type 2 diabetes, we investigated the prospective association of circulating TSP2 with incident HF hospitalization (HHF), and its associations with longitudinal changes of echocardiographic parameters in type 2 diabetes. Methods Baseline serum TSP2 levels were measured in 4949 patients with type 2 diabetes to determine its association with incident HHF using multivariable Cox regression analysis. In the echocardiographic study, baseline serum TSP2 levels were measured in another 146 patients with type 2 diabetes but without cardiovascular diseases who underwent detailed transthoracic echocardiography at baseline and after 1 year. Results Over a median follow-up of 7.8 years, 330 of 4949 patients (6.7%) developed incident HHF. Baseline serum TSP2 levels were independently associated with the development of HHF (HR 1.31, 95%CI 1.06–1.62, p = 0.014) after adjustments for baseline conventional cardiovascular risk factors, atrial fibrillation, estimated glomerular filtration rate, albuminuria and high-sensitivity C-reactive protein level, use of angiotensin-converting enzyme inhibitors, angiotensin receptor blockers, loop-diuretics, aspirin, insulin, metformin and sodium-glucose co-transporter 2 inhibitors. Moreover, baseline serum TSP2 levels were independently associated with increase in average E/e’ and left atrial volume index (p = 0.04 and Conclusion Serum TSP2 levels were independently associated with both incident HHF and deterioration in diastolic function in type 2 diabetes. Trial registration Not Applicable

Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n -slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model.

Current research on subset selection for opinion analysis assumes that their methods can retrieve the opinions expressed in documents from general text features. However, such relaxed conditions can hardly maintain the performance of the analysis in opinion mining , especially when given strict limitations on the subset size. In this paper, we propose a framework for opinion subset selection. This framework can select a small set of instances from original data to convey a subjective representation for opinion classification and regression. Compared with our framework, the conventional submodular based subset selection approach cannot capture the fine-grained opinion features expressed in the corpus. Specifically, we propose a monotone non-decreasing score function and a framework based on topic modeling and submodular maximization for filtering irrelevant information and selecting the subsets. Our work further introduces an opinion-sensitive algorithm for optimizing the proposed function for opinion subset construction . We perform extensive experiments and comparative analysis of different subset selection methods in this work. The experimental result shows that the proposed opinion subset selection framework can compress the original text training set and preserve the test set’s classification and regression metric performance at the same time.

To compare intrasession agreement and repeatability of wavefront aberration measurements from three different aberrometers obtained using Hartmann-Shack, ray tracing and automated retinoscopy methods, as well as their interdevice agreement.Three consecutive measurements were obtained using the Pentacam AXL Wave, the iTrace and the OPD-Scan III in 47 eyes of 47 patients. Wavefront refractions, root mean square of total aberrations (RMS total), RMS of higher-order aberrations (HOA) and second-, third- and fourth-order HOAs were exported for 4-mm pupils. Wavefront refractions were converted into vector components: M, JThe intrasession agreement and repeatability of RMS HOA were comparable between the three devices; both the Pentacam AXL Wave and the OPD-Scan III had better intrasession agreement and repeatability for the RMS total than the iTrace (p ≤ 0.02). Intrasession repeatability for the majority of second- and third-order aberrations was better on the Pentacam AXL Wave than on the iTrace (p ≤ 0.01) and OPD-Scan III (p ≤ 0.04), although their agreement and repeatability in spherical aberration were comparable (p ≥ 0.24). Significant systematic differences and proportional bias were detected for almost all refraction power vectors and Zernike coefficients among the three devices.In this study, all three devices provided good-to-excellent agreement for aberration measurements. Most of the individual Zernike's components were not exchangeable between different aberrometers. Their relative intrasession performance in agreement and repeatability varied significantly across different ocular aberration parameters.

Along with online social media’s prosperity, the amount of user-generated reviews dramatically increases. The kinds of text-based user-generated content are conducive to estimating public sentiments. Many sentiment analysis works are based on the assumption that the sentiment expressed in online reviews can be retrieved from general text features. However, text redundancy and quantity can potentially impact the analysis performance, especially when strict corpus size constraints are applied. This paper proposes a sentiment subset selection framework to construct a small set of documents from the original corpus to convey a subjective representation. The framework can filter irrelevant sentiment information based on topic modeling and select subsets by submodular maximization with respect to a cardinality constraint. Our proposed score function can facilitate the framework to capture fine-grained sentiment features expressed in reviews compared with the conventional submodular-based one. An empirical analysis for the efficacy of the proposed sentiment subset selection framework (SentiSS) on different context domains is conducted. The comparative study of the subset’s metric impact on different sentiment levels, namely positive, neural, and negative, is also performed. Experimental results show that the SentiSS framework can compress the sentiment corpus and maintain the classifier’s performance on the metrics at the same time.