Background: Peripheral blood inflammation factor neutrophil-lymphocyte ratio (NLR), platelet count (PLT) and nutritional factor serum albumin (ALB) have been proposed as prognostic markers of head and neck squamous carcinoma cancer (HNSCC) in recent years. In the current study, nomogram predict models based on pre-treatment hematological parameters and a modified risk-stratified score system have been built. Methods: A total of 197 patients with oropharyngeal, hypopharyngeal and laryngeal cancers receiving multimodality treatment between 2012 and 2014 were included. The pre-treatment ALB, neutrophil, lymphocyte and platelet count (PLT) were detected. Cancer-specific survival and locoregional recurrence (LRC) by 5 years' follow-up in the cases were obtained. To integrate clinical characteristics, we propose a modified risk-stratified score system. Kaplan-Meier method, proportional hazards COX model, logistic models were used to establish nomograms within external validation. Results: Five-year LRC was decreased (p=0.004) for 140 patients with pre-treatment NLR <2.77. Five-year LRC and 5-year cancer-specific survival were decreased (p=0.031, p=0.021) with pre-treatment PLT ≥248×10 9 /L. Comparison of univariate parametric models demonstrated that pre-treatment NLR evaluation and PLT>248×10 9 /L were better among tested models. On Bayesian information criteria (BIC) analysis, the optimal prognostic model was then used to develop nomograms predicting 3-and 5-year LRC. The external validation of this predictive model was confirmed in 57 patients from another hospital. Conclusion: Pre-treatment NLR elevation and PLT>248×10 9 /L are promising predictors of prognosis in patients with operable HNSCC. Nomograms based on the pre-treatment hematological markers and modified risk-stratified score system provide distinct risk stratifications. There results provided the feasibility of anti-inflammatory and antiplatelet treatments for HNSCC patients.

Recently, the Coherent Point Drift (CPD) algorithm has become a very popular and efficient method for point set registration. However, this method does not take into consideration the neighborhood structure information of points to find the correspondence and requires a manual assignment of the outlier ratio. Therefore, CPD is not robust for large degrees of degradation. In this paper, an improved method is proposed to overcome the two limitations of CPD. A structure descriptor, such as shape context, is used to perform the auxiliary calculation of the correspondence, and the proportion of each GMM component is adjusted by the similarity. The outlier ratio is formulated in the EM framework so that it can be automatically calculated and optimized iteratively. The experimental results on both synthetic data and real data demonstrate that the proposed method described here is more robust to deformation, noise, occlusion, and outliers than CPD and other state-of-the-art algorithms.

Nowadays, surface defect detection systems for steel strip have replaced traditional artificial inspection systems, and automatic defect detection systems offer good performance when the sample set is large and the model is stable. However, the trained model does work well when a new production line is initiated with different equipment, processes, or detection devices. These variables make just tiny changes to the real-world model but have a significant impact on the classification result. To overcome these problems, we propose an evolutionary classifier with a Bayes kernel (BYEC) that can be adjusted with a small sample set to better adapt the model for a new production line. First, abundant features were introduced to cover detailed information about the defects. Second, we constructed a series of support vector machines (SVMs) with a random subspace of the features. Then, a Bayes classifier was trained as an evolutionary kernel fused with the results from the sub-SVM to form an integrated classifier. Finally, we proposed a method to adjust the Bayes evolutionary kernel with a small sample set. We compared the performance of this method to various algorithms; experimental results demonstrate that the proposed method can be adjusted with a small sample set to fit the changed model. Experimental evaluations were conducted to demonstrate the robustness, low requirement for samples, and adaptiveness of the proposed method.

No abstract

No abstract