Relief Feature Research Articles

A Comparison of Different Machine Learning Classifiers in Predicting Xerostomia and Sticky Saliva due to Head and Neck Radiotherapy using a Multi-objective, Multimodal Radiomics Model.

Although radiotherapy techniques are the primary treatment for head and neck cancer (HNC), they are still associated with substantial toxicity, and side effect. Machine learning (ML) based radiomics models for predicting toxicity mostly rely on features extracted from pre-treatment imaging data. This study aims to compare different models in predicting radiation-induced xerostomia and sticky saliva in both early and late stage of HNC patients using CT and MRI image features along with demographics and dosimetric information.

Materials and Methods: A cohort of 85 HNC patients who underwent radiation treatment was evaluated. We built different ML-based classifiers to build a multi-objective, multimodal radiomics model by extracting 346 different features from patient data. The models were trained and tested for prediction, utilizing Relief feature selection method and eight classifiers consisting eXtreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (NB), Logistic Regression (LR), and Decision Tree (DT). The performance of the models was evaluated using sensitivity, specificity, area under the curve (AUC), and accuracy metrics.

Results: Using combination of demographics, dosimetric, and image features, the SVM model obtained the best performance whit AUC of 0.77 and 0.81 for predicting early sticky saliva and xerostomia, respectively. Also, SVM and MLP classifiers achieved a noteworthy AUC of 0.85 and 0.64 for predicting late sticky saliva and xerostomia, respectively.

Conclusion: This study highlights the potential of baseline CT and MRI image features, combined with dosimetric data and patient demographics, to predict radiation-induced xerostomia and sticky saliva. The use of ML techniques provides valuable insights for personalized treatment planning to mitigate toxicity effects during radiation therapy for HNC patients.

A novel method for tracing gasoline using GC-IRMS and Relief-Stacking fusion model

Due to China’s vast geographical expanse and the complexity of its natural environment, traditional methods are not suitable for tracing the origins of gasoline samples from different regions of China. The aim of this study is to trace the origins of gasoline samples through the analysis of carbon stable isotopic characteristics from 60 gasoline samples collected across four major regions in China. In this study, a novel method that combines gas chromatography-isotope ratio mass spectrometry (GC-IRMS) with Relief-Stacking was proposed for the first time, significantly enhancing the precision of the provenance results. Firstly, eight characteristic components were identified by Relief feature selection model for the first time and applied to the assessment of carbon stable isotope ratios across different regions. The discovery of these components effectively reduces data redundancy, thereby enhancing the accuracy of provenance analysis. Subsequently, five effective source tracing models (XGBoost, Random Forest, CatBoost, LightGBM, and KNN) were selected based on the CEI values. To further enhance the learning efficiency of the sourcing models, this study integrated the five selected source tracing models using three different methods(voting, stacking, and blending) and validated the performance of the optimal sourcing model. The results indicated that the Stacking fusion model achieves a CEI value of 0.923, significantly outperforming other fusion models. This advantage is attributed to the Stacking fusion model combining the s trengths of Boosting and Bagging ensemble methods and leveraging the advantages of individual classifiers within the model. The method proposed in this study can effectively address the limitations of previous tracing methods and offer valuable insights for the development of platforms related to stable isotope source tracing. In future research, through appropriate parameter adjustments and feature adaptations, the Relief-Stacking model can likewise be applied to source tracing studies in other countries characterized by extensive geographic ranges and variable environmental conditions.

Ensemble Learning for Nuclear Power Generation Forecasting Based on Deep Neural Networks and Support Vector Regression

Forecasting nuclear energy production is essential for market operations such as security, economic efficiency, resource optimization, grid stability, and the integration of renewable energy sources. Forecasting approaches allow nuclear power plants to operate consistently, contributing to the overall reliability and long-term viability of the energy system. It is noted that energy systems researchers are increasingly interested in machine learning models used to face the challenge of time series forecasting. This study evaluates a hybrid ensemble learning of three time series forecasting models including least-squares support vector regression, gated recurrent unit, and long short-term memory models applied to nuclear power time series forecasting on the dataset of French power plants from 2009 to 2020. Furthermore, this research evaluates forecasting results in which approaches are directed towards the optimized RreliefF (Robust relief Feature) selection algorithm using a hyperparameter optimization based on tree-structured Parzen estimator and following an ensemble learning approach, showing promising results in terms of performance metrics. The suggested ensemble learning model, which combines deep learning and the RreliefF algorithm using a hold-out, outperforms the other nine forecasting models in this study according to performance criteria such as 75% for the coefficient of determination, a root squared error average of 0.108, and an average absolute error of 0.080.

A multi-fusion approach to classify pharyngitis, tonsillitis and oral cancer with iterative relief feature weighting

Bacterial pharyngitis and tonsillitis can lead to severe complications if untreated, while oral cancer poses risks of spreading if not detected early. Classifying pharyngitis, oral cancer, and tonsillitis is essential for timely and accurate medical interventions. Early diagnosis enables effective treatment planning, potentially saving lives and minimizing complications. Classification aids in tailoring specific medical approaches, contributing to better patient outcomes and healthcare management. The global COVID-19 pandemic has prompted a renewed interest in telemedicine for managing these conditions. Existing techniques, like Bag of Visual Words and individual pre-trained models, fall short in achieving optimal classification. To address this, we propose GHBResIncep, a framework that combines deep features from SE-ResNet, Inception-v4 and EfficientNetV2 with shallow features from improved BOVW, HOG, and Gabor filters. Employing an iterative relief feature weighting algorithm enhances feature selection. Our proposed model achieved highest classification accuracy of 95.58 %.The multi-fused features are fed into ML classifiers like XGBoost, showcasing significant improvements in various classification parameters compared to prior works.

Enhanced Detection of Chronic Heart Disease: A Novel Approach With Extreme Gradient Boosting-Logistic Regression Algorithm

In recent years, biomedical healthcare applications for managing and treating chronic heart diseases have increased. Chronic heart disease is a serious and sometimes deadly ailment that affects millions of individuals globally. Therefore, timely and effective detection of heart disease is crucial in medicine, particularly in cardiology. These complications can lead to reduced quality of life, increased medical costs, and increased risk of death. Obesity, smoking, and high blood pressure are some of the risk factors that worsen chronic heart disease. However, challenges occur in accurately and sensitively classifying heart disease in performance evaluation. To resolve this problem, we propose an Extreme Gradient Boosting-Logistic Regression (EGBLR) algorithm to accurately and quickly predict chronic heart disease. Furthermore, pre-processing can be performed using the Normalized Minimum-Maximum Scaling Feature (NMMSF) technique to estimate missing or duplicate values. Next, the Inter-Quartile Range Optimization (IQRO) technique can analyze heart disease data to identify and remove outliers. After that, the Relief Feature Vector (RFV) algorithm can be used to find each feature weight. Finally, the proposed EGBLR method can be employed to detect normal or abnormal chronic heart diseases and increase accuracy in diagnosis. The evaluation of the proposed techniques can be predicted using performance matrices such as recall, sensitivity score, precision, false rate, and precision. The accuracy of the proposed EGBLR detection approach exceeds that of previous techniques. Moreover, the proposed method for diagnosing chronic heart disease can be easily adapted to biomedical healthcare applications.

A Feature Selection Method Based on Relief Feature Ranking with Recursive Feature Elimination for the Inversion of Urban River Water Quality Parameters Using Multispectral Imagery from an Unmanned Aerial Vehicle

The timely monitoring of urban water bodies using unmanned aerial vehicle (UAV)-mounted remote sensing technology is crucial for urban water resource protection and management. Addressing the limitations of the use of satellite data in inferring the water quality parameters of small-scale water bodies due to their spatial resolution constraints and limited input features, this study focuses on the Zao River in Xi’an City. Leveraging UAV multispectral imagery, a feature selection method based on Relief Feature Ranking with Recursive Feature Elimination (Relief F-RFE) is proposed to determine the quality parameters of the typical urban pollution in water (dissolved oxygen (DO), total nitrogen (TN), turbidity, and chemical oxygen demand (COD). By constructing a potential feature set and utilizing optimal feature combinations, inversion models are developed for the four water quality parameters using three machine learning (ML) algorithms (Random Forest (RF), Support Vector Regression (SVR), Light Gradient Boosting Machine (LightGBM). The inversion accuracies of the different models are compared, and the spatial distribution of the four water quality parameters is analyzed. The results show that the models constructed based on UAV-based multispectral remote sensing imagery perform well in inferring the water quality parameters of the Zao River. The SVR algorithm, based on Relief F-RFE feature selection, achieves a higher accuracy, with RMSE values of 7.19 mg/L, 1.14 mg/L, 3.15 NTU, and 4.28 mg/L, respectively. The methods and conclusions of this study serve as a reference for research on the inversion of water quality parameters in urban rivers.

Deep learning convolutional neural network ResNet101 and radiomic features accurately analyzes mpMRI imaging to predict MGMT promoter methylation status with transfer learning approach

AbstractAccurate brain tumor classification is crucial for enhancing the diagnosis, prognosis, and treatment of glioblastoma patients. We employed the ResNet101 deep learning method with transfer learning to analyze the 2021 Radiological Society of North America (RSNA) Brain Tumor challenge dataset. This dataset comprises four structural magnetic resonance imaging (MRI) sequences: fluid‐attenuated inversion‐recovery (FLAIR), T1‐weighted pre‐contrast (T1w), T1‐weighted post‐contrast (T1Gd), and T2‐weighted (T2). We assessed the model's performance using standard evaluation metrics. The highest performance to detect MGMT methylation status for patients suffering glioblastoma was an accuracy (85.48%), sensitivity (80.64%), specificity (90.32%). Whereas classification performance with no tumor was yielded with accuracy (85.48%), sensitivity (90.32%), specificity (80.64%). The radiomic features (74) computed with ensembled Bagged Tree and relief feature selection method (30/74) improved the validation accuracy of 84.3% and AUC of 0.9038 to detect. O6‐methylguanine‐DNA methyltransferase (MGMT) promoter methylation status in glioblastoma patients holds promise for optimizing treatment planning and prognosis. By understanding MGMT methylation status, clinicians can make informed decisions about treatment strategies, potentially leading to improved clinical outcomes.

Prediction the prognosis of the poisoned patients undergoing hemodialysis using machine learning algorithms

BackgroundHemodialysis is a life-saving treatment used to eliminate toxins and metabolites from the body during poisoning. Despite its effectiveness, there needs to be more research on this method precisely, with most studies focusing on specific poisoning. This study aims to bridge the existing knowledge gap by developing a machine-learning prediction model for forecasting the prognosis of the poisoned patient undergoing hemodialysis.MethodsUsing a registry database from 2016 to 2022, this study conducted a retrospective cohort study at Loghman Hakim Hospital. First, the relief feature selection algorithm was used to identify the most important variables influencing the prognosis of poisoned patients undergoing hemodialysis. Second, four machine learning algorithms, including extreme gradient boosting (XGBoost), histgradient boosting (HGB), k-nearest neighbors (KNN), and adaptive boosting (AdaBoost), were trained to construct predictive models for predicting the prognosis of poisoned patients undergoing hemodialysis. Finally, the performance of paired feature selection and machine learning (ML) algorithm were evaluated to select the best models using five evaluation metrics including accuracy, sensitivity, specificity the area under the curve (AUC), and f1-score.ResultThe study comprised 980 patients in total. The experimental results showed that ten variables had a significant influence on prognosis outcomes including age, intubation, acidity (PH), previous medical history, bicarbonate (HCO3), Glasgow coma scale (GCS), intensive care unit (ICU) admission, acute kidney injury, and potassium. Out of the four models evaluated, the HGB classifier stood out with superior results on the test dataset. It achieved an impressive mean classification accuracy of 94.8%, a mean specificity of 93.5 a mean sensitivity of 94%, a mean F-score of 89.2%, and a mean receiver operating characteristic (ROC) of 92%.ConclusionML-based predictive models can predict the prognosis of poisoned patients undergoing hemodialysis with high performance. The developed ML models demonstrate valuable potential for providing frontline clinicians with data-driven, evidence-based tools to guide time-sensitive prognosis evaluations and care decisions for poisoned patients in need of hemodialysis. Further large-scale multi-center studies are warranted to validate the efficacy of these models across diverse populations.

Explaining predictors of discharge destination assessed along the patients’ acute stroke journey

Introduction: Accurate prediction of outcome destination at an early stage would help manage patients presenting with stroke. This study assessed the predictive ability of three machine learning (ML) algorithms to predict outcomes at four different stages as well as compared the predictive power of stroke scores.Methods: Patients presenting with acute stroke to the Canberra Hospital between 2015 and 2019 were selected retrospectively. 16 potential predictors and one target variable (discharge destination) were obtained from the notes. k-Nearest Neighbour (kNN) and two ensemble-based classification algorithms (Adaptive Boosting and Bootstrap Aggregation) were employed to predict outcomes. Predictive accuracy was assessed at each of the four stages using both overall and per-class accuracy. The contribution of each variable to the prediction outcome was evaluated by the ensemble-based algorithm and using the Relief feature selection algorithm. Various combinations of stroke scores were tested using the aforementioned models.Results: Of the three ML models, Adaptive Boosting demonstrated the highest accuracy (90%) at Stage 4 in predicting death while the highest overall accuracy (81.7%) was achieved by kNN (k=2/City-block distance). Feature importance analysis has shown that the most important features are the 24-hour Scandinavian Stroke Scale (SSS) and 24-hour National Institutes of Health Stroke Scale (NIHSS) scores, dyslipidaemia, hypertension and premorbid mRS score. For the initial and 24-hour scores, there was a higher correlation (0.93) between SSS scores than for NIHSS scores (0.81). Reducing the overall four scores to InitSSS/24hrNIHSS increased accuracy to 95% in predicting death (Adaptive Boosting) and overall accuracy to 85.4% (kNN). Accuracies at Stage 2 (pre-treatment, 11 predictors) were not far behind those at Stage 4.Conclusion: Our findings suggest that even in the early stages of management, a clinically useful prediction regarding discharge destination can be made. Adaptive Boosting might be the best ML model, especially when it comes to predicting death. The predictors’ importance analysis also showed that dyslipidemia and hypertension contributed to the discharge outcome even more than expected. Further, surprisingly using mixed score systems might also lead to higher prediction accuracies.

The Origin of Overpressure in the Pinghu Tectonic Zone of Xihu Depression and Its Relationship with Hydrocarbon Accumulation

Clarification of the cause of overpressure is of great significance for the study of hydrocarbon generation, migration and accumulation processes under an overpressure environment, and the prediction of predrilling pressure. The cause of overpressure in Xihu Depression is still controversial. This study, based on mudstone compaction research and organic matter correction of logging data, ascertained the causes of overpressure in the Pinghu tectonic zone, Xihu Depression. A modified discrimination method for overpressure genesis was used and the overpressure–hydrocarbon distribution relationship was explored. The results show the following: (1) Vertically, overpressure is located in the lower section of the Pinghu Formation, with a pressure coefficient of 1.1–1.7 and a pressure relief feature. On the plane, the pressure coefficient in the Pingzhong area exceeds that in the Pingbei area. (2) The main causes of abnormal high pressure in the research area are undercompaction and fluid expansion. The fluid expansion mechanisms include overpressure transmission and hydrocarbon charging within the reservoir as well as hydrocarbon generation pressurisation and overpressure transmission within the source rock. (3) In the surge section of kaolinite, under fluid pressure, kaolin migrates toward the low-pressure areas, decreasing the porosity in low-pressure areas and preserving pores in high-pressure areas. The evolution of fluid pressure can be divided into two stages: pressurisation; and both pressurisation and pressure relief. Pressurisation and pressure relief drive hydrocarbon charging, but hydrocarbons are more enriched in overpressure layers.

The application of immersive multimedia information technology in the teaching of vocal music

Abstract In this paper, immersive multimedia information technology is utilized to perform frame-splitting and window-adding operations on vocal signals in college vocal music teaching to facilitate the extraction of vocal signal features. According to the Principal Component Analysis feature space projection and Relief feature selection, the vocal emotion regression model combining multimedia information technology is constructed, and the structure of the vocal emotion regression model and its teaching application are explored in the vocal emotion regression model. Determine the research object and method, according to the research program on the integration of multimedia information technology of vocal music teaching research design and implementation, and the use of statistical analysis of multimedia information technology-based vocal music teaching empirical analysis. The results show that the subjects had the best emotional experience with an emotional immersion degree of 5.651 when the music of the calm category and the visual music motion picture of the calm category constituted the visual music and the vocal music immersion based on the vocal music emotional regression model of “combining multimedia information technology” was significantly enhanced when the emotional type of the music and the emotional type of the dynamic picture of the visual music was the same. This study carries out college vocal music teaching based on students’ emotional characteristics, which is of great significance to improve the quality of college vocal music teaching and students’ musical literacy.

Research on identification of coal and gangue under complex working conditions based on relief feature

ABSTRACT To improve the identification accuracy of coal gangue under the complex working conditions of pulverized coal and moisture adhesion on the surface, this paper studies the distribution difference of characteristic curves under five working conditions of different proportions of moisture and pulverized coal, and finds that moisture has a greater influence on gradient features, while pulverized coal has a greater influence on gray texture features. Then this paper studies the distribution of coarse texture and fine texture in coal and gangue, and finds that there are many fine textures and few coarse textures on the surface of gangue, while coal shows the opposite law. In addition, the ratio of pixels with large gray value to pixels with small gray value can reduce the occurrence of noncompliance with the above laws. Finally, through the combination of coarse texture, fine texture, and gray value difference, the relief feature is put forward. Compared with different features, the average feature overlap ratio proposed in this paper is lower, at 23.83%. Compared with different methods, this method has a higher identification rate under different working conditions, and the average identification accuracy rate is 89.59%, which is at least 13.93% higher than other methods.

Biodiversity estimation by environment drivers using machine/deep learning for ecological management

Biodiversity is a crucial indicator of the health and resilience of ecosystems. Accurate estimation and prediction of biodiversity can support effective ecological management practices. This study aimed to estimate and predict biodiversity based on Environmental Factors (EFs), using Machine Learning (ML) including Deep Learning (DL) algorithms. First, the importance of EFs, including Mean Annual Precipitation (MAP), slope, aspect, and elevation, in influencing biodiversity was evaluated using Minimum Redundancy Maximum Relevance (MRMR) and Recursive Feature Elimination with Relief Feature Selection (RReliefF), and their correlations with multi-spatial biodiversity indices were analyzed. Our findings revealed that MAP was the most important environmental variable in estimating biodiversity, followed by slope, aspect, and elevation. Next, the ability of four ML algorithms (multiple linear regression, decision tree, random forest, support vector machine) and a deep neural network (DNN) to estimate biodiversity was evaluated by the coefficient of determination (r-square) and the root-mean-square error (RMSE) metrics. The DNN model achieved the highest accuracy (r-square: 0.884) among the ML algorithms and was further optimized to determine the optimal level of model complexity. These findings highlight the potential of DNN to effectively estimate biodiversity and suggest that using EF features with DL algorithms can improve our understanding of the relationships between environmental drivers and biodiversity, providing valuable insights for conservation and management decision-making towards sustainable development.

Integrated transcriptomic meta-analysis and comparative artificial intelligence models in maize under biotic stress

Biotic stress imposed by pathogens, including fungal, bacterial, and viral, can cause heavy damage leading to yield reduction in maize. Therefore, the identification of resistant genes paves the way to the development of disease-resistant cultivars and is essential for reliable production in maize. Identifying different gene expression patterns can deepen our perception of maize resistance to disease. This study includes machine learning and deep learning-based application for classifying genes expressed under normal and biotic stress in maize. Machine learning algorithms used are Naive Bayes (NB), K-Nearest Neighbor (KNN), Ensemble, Support Vector Machine (SVM), and Decision Tree (DT). A Bidirectional Long Short Term Memory (BiLSTM) based network with Recurrent Neural Network (RNN) architecture is proposed for gene classification with deep learning. To increase the performance of these algorithms, feature selection is made from the raw gene features through the Relief feature selection algorithm. The obtained finding indicated the efficacy of BiLSTM over other machine learning algorithms. Some top genes ((S)-beta-macrocarpene synthase, zealexin A1 synthase, polyphenol oxidase I, chloroplastic, pathogenesis-related protein 10, CHY1, chitinase chem 5, barwin, and uncharacterized LOC100273479 were proved to be differentially upregulated under biotic stress condition.

A bi-layer model for identification of piwiRNA using deep neural learning

piwiRNA is a kind of non-coding RNA (ncRNA) that cannot be translated into proteins. It helps in understanding the study of gametes generation and regulation of gene expression over both transcriptional and post-transcriptional levels. piwiRNA has the function of instructing deadenylation, animal fertility, silencing transposons, fighting viruses, and regulating endogenous genes. Due to the great significance of piwiRNA, prediction of piwiRNA is essential for crucial cellular functions. Several predictors were established for prediction of piwiRNA. However, improving the prediction of piwiRNA is highly desirable. In the current study, we developed a more promising predictor named, BLP-piwiRNA. The features are explored by reverse complement k-mer, gapped-k-mer composition, and k-mer composition. The feature set of all descriptors is fused and the best features are selected by cascade and relief feature selection strategies. The best feature sets are provided to random forest (RF), deep neural network (DNN), and support vector machine (SVM). The models validation are examined by 10-fold test. DNN with optimal features of Cascade feature selection approach secured the highest prediction results. The results illustrate that BLP-piwiRNA effectively outperforms the existing studies. The proposed approach would be beneficial for both research community and drug development industry. BLP-piwiRNA would serve as novel biomarkers and therapeutic targets for tumor diagnostics and treatment. Communicated by Ramaswamy H. Sarma

Analysis of neuropsychological and neuroradiological features for diagnosis of Alzheimer's disease and mild cognitive impairment

BackgroundAge-related neurodegenerative diseases are constantly increasing with prediction that in 2050 over 60 % of population will suffer from some level of cognitive impairment. A cure for the Alzheimer’s disease (AD) does not exist, so early diagnosis is of a great importance. Machine learning techniques can help in early diagnosis with deep medical data processing, disease understanding, intervention analysis and knowledge discovery for achieving better medical decision making. MethodsIn this paper, we analyze the dataset consisting of 90 individuals and 482 input features. We investigate the achieved AD prediction performances using seven classifiers and five feature selection algorithms. We pay special focus on analyzing performance by utilizing only a subset of best ranked attributes to establish the minimum amount of input features that ensure acceptable performance. We also investigate the significance of neuropsychological (NP) and neuroradiological (NR) attributes for the AD diagnosis. ResultsThe accuracy for the whole set of attributes ranged between 66.22 % and 81.00 %, and the weighted average AUROC was between 76.3 % and 95.0 %. The best results were achieved by the naive Bayes classifier and the Relief feature selection algorithm. Additionally, Support Vector Machines classifier shows the most stable results since it depends the least on the feature selection algorithm which is used. As the main result of this paper, we compare the performance of models trained with automatically selected features to models trained with hand-selected features performed by medical experts (NP and NR features). ConclusionsThe results reveal that unlike the NR attributes, the NP attributes achieve a good performance that is comparable to the full set of attributes, which suggests that they possess a high predictive power for AD diagnosis.

Radiomic analysis for early differentiation of lung cancer recurrence from fibrosis in patients treated with lung stereotactic ablative radiotherapy.

The development of radiation-induced fibrosis after SABR can obscure follow-up images and delay detection of a local recurrence in early-stage lung cancer patients. The objective of this study was to develop a radiomics model for computer-assisted detection of local recurrence and fibrosis for an earlier timepoint (<1 year) after the SABR treatment.&#xD;&#xD;This retrospective clinical study included CT images (n=107) of 66 patients treated with SABR. A z-score normalization technique was used for radiomic feature standardization across scanner protocols. The training set for the radiomics model consisted of CT images (66 patients; 22 recurrences and 44 fibrosis) obtained at 24 months (median) follow-up. The test set included CT-images of 41 patients acquired at 5-12 months follow-up. Combinations of four widely used machine learning techniques (support vector machines (SVMs), gradient boosting, random forests (RF), and logistic regression (LR)) and feature selection methods (Relief feature scoring, maximum relevance minimum redundancy (MRMR), mutual information maximization (MIM), forward feature selection, and LASSO) were investigated. Pyradiomics was used to extract 106 radiomic features from the CT-images for feature selection and classification. &#xD;&#xD;An RF + LASSO model scored the highest in terms of AUC (0.87) and obtained a sensitivity of 75% and a specificity of 88% in identifying a local recurrence in the test set. In the training set, 86% accuracy was achieved using five-fold cross-validation. Delong's test indicated that AUC achieved by the RF+LASSO is significantly better than 11 other machine learning models presented here. The top three radiomic features: Interquartile Range (first order), Cluster Prominence (GLCM), and Autocorrelation (GLCM), were revealed as differentiating a recurrence from fibrosis with this model.&#xD;&#xD;The radiomics model selected, out of multiple machine learning and feature selection algorithms, was able to differentiate a recurrence from fibrosis in earlier follow-up CT-images with a high specificity rate and satisfactory sensitivity performance. &#xD.

Characterization of thin film Parylene C device curvature and the formation of helices via thermoforming

In microfabricated biomedical devices, flexible, polymer substrates are becoming increasingly preferred over rigid, silicon substrates because of their ability to conform to biological tissue. Such devices, however, are fabricated in a planar configuration, which results in planar devices that do not closely match the shape of most tissues. Thermoforming, a process which can reshape thermoplastic polymers, can be used to transform flat, thin film, polymer devices with patterned metal features into complex three-dimensional (3D) geometries. This process extends the use of planar microfabrication to achieve 3D shapes which can more closely interface with the body. Common shapes include spheres, which can conform to the shape of the retina; cones, which can be used as a sheath to interface with an insertion stylet; and helices, which can be wrapped around nerves, blood vessels, muscle fibers, or be used as strain relief feature. This work characterizes the curvature of thin film Parylene C devices with patterned metal features built with varying Parylene thicknesses and processing conditions. Device curvature is caused by film stress in each Parylene and metal layer, which is characterized experimentally and by a mathematical model which estimates the effects of device geometry and processing on curvature. Using this characterization, an optimized process to thermoform thin film Parylene C devices with patterned metal features into 0.25 mm diameter helices while preventing cracking in the polymer and metal was developed.

Semantic Segmentation for Digital Archives of Borobudur Reliefs Based on Soft-Edge Enhanced Deep Learning

Segmentation and visualization of three-dimensional digital cultural heritage are important analytical tools for the intuitive understanding of content. In this paper, we propose a semantic segmentation and visualization framework that automatically classifies carved items (people, buildings, plants, etc.) in cultural heritage reliefs. We also apply our method to the bas-reliefs of Borobudur Temple, a UNESCO World Heritage Site in Indonesia. The difficulty in relief segmentation lies in the fact that the boundaries of each carved item are formed by indistinct soft edges, i.e., edges with low curvature. This unfavorable relief feature leads the conventional methods to fail to extract soft edges, whether they are three-dimensional methods classifying a three-dimensional scanned point cloud or two-dimensional methods classifying pixels in a drawn image. To solve this problem, we propose a deep-learning-based soft edge enhanced network to extract the semantic labels of each carved item from multichannel images that are projected from the three-dimensional point clouds of the reliefs. The soft edges in the reliefs can be clearly extracted using our novel opacity-based edge highlighting method. By mapping the extracted semantic labels into three-dimensional points of the relief data, the proposed method provides comprehensive three-dimensional semantic segmentation results of the Borobudur reliefs.

Development and validation of nomogram of peritoneal metastasis in gastric cancer based on simplified clinicopathological features and serum tumor markers

BackgroundPeritoneal metastasis (PM) is not uncommon in patients with gastric cancer(GC), which affects clinical treatment decisions, but the relevant examination measures are not efficiently detected. Our goal was to develop a clinical radiomics nomogram to better predict peritoneal metastases.MethodsA total of 3480 patients from 2 centers were divided into 1 training, 1 internal validation, and 1 external validation cohort(1949 in the internal training set, 704 in the validation set, and 827 in the external validation cohort) with clinicopathologically confirmed GC. We recruited 11 clinical factors, including age, sex, smoking status, tumor size, differentiation, Borrmann type, location, clinical T stage, and serum tumor markers (STMs) comprising carbohydrate antigen 19–9 (CA19-9), carbohydrate antigen 72–4 (CA72-4), and carcinoembryonic antigen (CEA), to develop the radiomics nomogram. For clinical predictive feature selection and the establishment of clinical models, statistical methods of analysis of variance (ANOVA), relief and recursive feature elimination (RFE) and logistic regression analysis were used. To develop combined predictive models, tumor diameter, type, and location, clinical T stage and STMs were finally selected. The discriminatory ability of the nomogram to predict PM was evaluated by the area under the receiver operating characteristic curve(AUC), and decision curve analysis (DCA) was conducted to evaluate the clinical usefulness of the nomogram.ResultsThe AUC of the clinical models was 0.762 in the training cohorts, 0.772 in the internal validation cohort, and 0.758 in the external validation cohort. However, when combined with STMs, the AUC was improved to 0.806, 0.839 and 0.801, respectively. DCA showed that the combined nomogram was of good clinical evaluation value to predict PM in GC.ConclusionsThe present study proposed a clinical nomogram with a combination of clinical risk factors and radiomics features that can potentially be applied in the individualized preoperative prediction of PM in GC patients.