Prescreening Stage Research Articles

The role of temporal distancing on the sense of meaning in life among individuals experiencing daily stressors.

Existing evidence has indicated that adopting a temporally distanced perspective can enhance the search for and presence of meaning in life. However, this effect may not hold among individuals facing highly stressful situations, as meaning-search might be considered dysfunctional in such contexts. Furthermore, prior research has not distinguished between near and distant perspectives when examining the impact of temporal distancing on meaning-search and meaning-presence. To address these gaps, this study utilized a prescreening stage (N= 972) to recruit participants dealing with unresolved stressors of moderate-to-high severity. A pre-test and post-test design was employed, with participants randomly assigned to either near-future or distant-future conditions. The results (n= 129) showed that temporal distancing manipulation increased meaning-presence scores across both conditions. Meaning-search scores were significantly lower at post-test compared to pre-test within the distant-future condition but not within the near-future condition. By examining the differential effects of near-future versus distant-future perspectives and recruiting individuals experiencing moderate-to-severe unresolved stressors, this study sheds light on how temporal distancing serves as a coping strategy, enabling individuals to maintain a relatively balanced sense of meaning in life when confronted with significant stressors.

Prescreening bank failures with K-means clustering: Pros and cons

To study the merits of the popular K-means clustering technique while predicting failures of commercial banks, we contrast hereafter two forecasting systems. The first one contains two complementary stages, with unsupervised K-means clustering followed by logistic regression deployed over the three most hazardous clusters (out of five) formed. The second system incorporates logistic regression over the entire sample of banks. We find that the first prognostic system is relatively strict. It better identifies bank failures beforehand, but it also projects more potential failures among the solvent banks. The second system is more lenient. It does not identify in advance actual bank failures in many cases, yet it does not speculate failures for many solvent banks either. The second system achieves a slightly higher overall predictive power than the first system. The minor statistical disadvantage of the K-means clustering is observed mainly because of the scarcity of bank failures in practice. The K-means clustering prescreening stage intensifies the systemic costs associated with type-II errors (predicting failures for solvent banks), but it simultaneously reduces the systemic costs linked to type-I errors (not predicting failures for eventually failed banks). Overall, the K-means clustering prescreening technique has prospective economic advantages, as it assists in slashing the total simulated systemic costs.

A Scalable PDC Placement Technique for Fast and Resilient Monitoring of Large Power Grids

The Wide Area Measurement System (WAMS) is a key enabler of real-time monitoring of power grids. The essential goals of WAMS design are fast and resilient data transfer from phasor measurement units (PMU) to phasor data concentrators (PDC). We propose a scalable two-stage PDC placement technique for minimizing the end-to-end delay while maintaining resiliency. In the prescreening stage, the plausible candidates of PDC configurations are identified based on a graph theory-based multi-median function (MMF). A computationally efficient meta-heuristic algorithm is used to address scalability. In the candidate selection stage, two different algorithms, namely Suurballe's and Dijkstra's, are employed to identify the best of those plausible PDC configurations as the final design. This technique not only minimizes the hop paths between PMUs and PDCs, but also ensures network resiliency against single PMU, PDC, or communication link failure by incorporating the roles of PMUs in power grid observability into routing policy. Simulation results on the IEEE 57-bus test power system and the 2000-bus test power system demonstrate the effectiveness and scalability of the proposed technique.

Density-based ship detection in SAR images: Extension to a self-similarity perspective

Nonlocal self-similarity is an important property of Synthetic Aperture Radar (SAR) images to characterize the repetitiveness of features embodied by SAR images within nonlocal areas and has been used for enhancement of SAR images. Existing SAR ship detectors often independently handle small sub-images cropped from a large marine SAR image and do not exploit the nonlocal self-similarity therein. In this paper, we propose a new ship detector from the perspective of nonlocal self-similarity in SAR images to improve the ship detection performance, basically including three stages: prescreening, intra-cue calculation, and inter-cue calculation. In the pre-screening stage, we design a new Histogram-based Density (HD) feature to rapidly select candidate sub-images potentially containing ship targets from a large SAR image. In the intra-cue calculation stage, target cues within a single candidate sub-image are extracted. In the inter-cue calculation stage, thanks to the nonlocal self-similarity among different candidate sub-images in terms of density features, we innovatively extract a weighted superpixel-HD map to obtain accumulated intra-cues across all the candidate sub-images. Finally, for each candidate sub-image, we fuse its inter-cue and intra-cue to obtain final detection results. Experimental results based on real SAR images show that our newly proposed method provides a better target-to-clutter contrast and ship detection performance than those of other state-of-the-art detection approaches.

Seroprevalence of Viral Hepatitis C on Donations of Blood at Moulay Ismail Military Hospital in Meknes

Introduction: Hepatitis C is an infection with hepatocellular tropism, transmitted by the hepatitis C virus via fecal-oral, parenteral or mother-to-child transmission. Her active chronic carriage may be the cause of cirrhosis. Objective: The purpose of this study was to determine the seroprevalence of HCV in blood donations collected at the Moulay Ismail military hospital in Meknes in order to protect the recipients. Material and Methods: This is a retrospective study of 8639 military blood donors. All donors have gone through a pre-screening stage involving an anamnesis and pre-donation clinical examination associated with a biological screening performed by the 4th generation recombinant ELISA and confirmed on the Abott Architect system. Result: The study is focused on 8639 blood donors, mostly male, with extreme ages of 18 to 56 years. We found an HCV seroprevalence of 0.17%. No case of co-infection has been recorded. Discussion and conclusion: The HCV seroprevalence rate in our series remains relatively low in comparison with the data of the literature, this could be related to the campaigns of sensitization, to the exposure of the preventive measures for the military population as well as to the success of the pre-selection stage at Moulay Ismail hospital in Meknes.

Deep learning-based classification model for GPR151 activator activity prediction

BackgroundGPR151 is a kind of protein belonging to G protein-coupled receptor family that is closely associated with a variety of physiological and pathological processes.The potential use of GPR151 as a therapeutic target for the management of metabolic disorders has been demonstrated in several studies, highlighting the demand to explore its activators further. Activity prediction serves as a vital preliminary step in drug discovery, which is both costly and time-consuming. Thus, the development of reliable activity classification model has become an essential way in the process of drug discovery, aiming to enhance the efficiency of virtual screening.ResultsWe propose a learning-based method based on feature extractor and deep neural network to predict the activity of GPR151 activators. We first introduce a new molecular feature extraction algorithm which utilizes the idea of bag-of-words model in natural language to densify the sparse fingerprint vector. Mol2vec method is also used to extract diverse features. Then, we construct three classical feature selection algorithms and three types of deep learning model to enhance the representational capacity of molecules and predict activity label by five different classifiers. We conduct experiments using our own dataset of GPR151 activators. The results demonstrate high classification accuracy and stability, with the optimal model Mol2vec-CNN significantly improving performance across multiple classifiers. The svm classifier achieves the best accuracy of 0.92 and F1 score of 0.76 which indicates promising applications for our method in the field of activity prediction.ConclusionThe results suggest that the experimental design of this study is appropriate and well-conceived. The deep learning-based feature extraction algorithm established in this study outperforms traditional feature selection algorithm for activity prediction. The model developed can be effectively utilized in the pre-screening stage of drug virtual screening.

Combined molecular dynamics and coordinate driving method for automatically searching complicated reaction pathways.

The combined molecular dynamics and coordinate driving (MD/CD) method is updated and generalized in this work to broaden its applications in automatically searching reaction pathways for complicated reactions. In this updated version, MD simulations are performed with the GFN's family of methods to systematically sample conformers for almost any systems with atomic numbers Z ≤ 86. The improved CD procedure is greatly accelerated by applying a pre-screening stage at the semiempirical GFN2-xTB level. An automatic module based on the Marcus theory and its improved version (the Wolynes theory) is designed to include single electron transfer (SET) processes into reaction pathways. The capabilities of this method are demonstrated by exploring the most possible reaction pathways of three experimentally reported reactions: the organophosphine-catalyzed trans phosphinoboration, the Fe(II) complex-mediated C(sp2)-H borylation reaction, and the SET-triggered deaminative radical cross-coupling reaction. Comprehensive reaction networks are obtained for all three reactions with reasonable computational costs. Detailed mechanisms for these reactions can account for the reported experimental facts.

Development of a Method and a Scheme for the Use of a Live Recombinant Vaccine "GamLPV". Safety and Tolerability of Double Intranasal Vaccination of Healthy Adult Volunteers

Introduction. The increase in the incidence of whooping cough in children and adults of different age groups justifies the need for their revaccination and the development of new, acceptable for these purposes. This work is devoted to substantiating the design of a clinical trial and describing the results of a comparative study of the safety and tolerability of the drug "GamLPV" with two-fold intranasal administration to healthy adult volunteers using two methods. The choice of the scheme and method of administration of the drug is justified. The serological structure of the population of adults aged 18–40 years living in Moscow and the Moscow region is characterized.Aim. Determination of the safety and tolerability of the drug with a double intranasal administration of the vaccine by drip method and spraying through an actuator.Materials and methods. A randomized placebo-controlled trial included 50 healthy male and female volunteers aged 18 to 40 years who met the inclusion criteria. The volunteers were divided into 2 groups of 25 people: a drip method of administration and spraying through an "actuator". By both methods, the drug was administered twice with an interval of 60 days.Results and discussion. Serological analysis of the population of healthy volunteers at the prescreening stage justified the inclusion in the study of volunteers containing anti-pertussis antibodies in the blood (IgG ≤40 Ed/ml). A comparison of the results of preclinical studies on an experimental model of non-human monkeys and the first phase of a clinical study of GamLPV allowed us to propose two methods of double administration of the drug as a promising vaccination scheme for volunteers. A comparative randomized study shows the safety of using the proposed scheme for vaccination of adult volunteers.Conclusions. Both proposed methods of double administration can be used to plan a multicenter study to research the immunogenicity and protective activity of GamLPV.

Identification of all-against-all protein–protein interactions based on deep hash learning

BackgroundProtein–protein interaction (PPI) is vital for life processes, disease treatment, and drug discovery. The computational prediction of PPI is relatively inexpensive and efficient when compared to traditional wet-lab experiments. Given a new protein, one may wish to find whether the protein has any PPI relationship with other existing proteins. Current computational PPI prediction methods usually compare the new protein to existing proteins one by one in a pairwise manner. This is time consuming.ResultsIn this work, we propose a more efficient model, called deep hash learning protein-and-protein interaction (DHL-PPI), to predict all-against-all PPI relationships in a database of proteins. First, DHL-PPI encodes a protein sequence into a binary hash code based on deep features extracted from the protein sequences using deep learning techniques. This encoding scheme enables us to turn the PPI discrimination problem into a much simpler searching problem. The binary hash code for a protein sequence can be regarded as a number. Thus, in the pre-screening stage of DHL-PPI, the string matching problem of comparing a protein sequence against a database with M proteins can be transformed into a much more simpler problem: to find a number inside a sorted array of length M. This pre-screening process narrows down the search to a much smaller set of candidate proteins for further confirmation. As a final step, DHL-PPI uses the Hamming distance to verify the final PPI relationship.ConclusionsThe experimental results confirmed that DHL-PPI is feasible and effective. Using a dataset with strictly negative PPI examples of four species, DHL-PPI is shown to be superior or competitive when compared to the other state-of-the-art methods in terms of precision, recall or F1 score. Furthermore, in the prediction stage, the proposed DHL-PPI reduced the time complexity from O(M^2) to O(Mlog M) for performing an all-against-all PPI prediction for a database with M proteins. With the proposed approach, a protein database can be preprocessed and stored for later search using the proposed encoding scheme. This can provide a more efficient way to cope with the rapidly increasing volume of protein datasets.

The Servqual Method as an Assessment Tool of the Quality of Medical Services in Selected Asian Countries.

Introduction: The Servqual (an acronym from the words “service” and “quality”) method is used to assess the quality of provided services on the basis of standardised evaluation parameters. This method is based on five gaps resulting from the discrepancy between expected and received service quality. The aim of this meta-analysis and the systematic review was to view and assess the major differences in the five dimensions of the Servqual method used to evaluate the quality of delivered health care services in selected Asian countries. Another goal of the study was to confirm the use of the Servqual method as a suitable tool for assessing the quality of health care services. Methods: This study followed the PRISMA guidelines for systemic reviews and meta-analyses. The following electronic databases for medical publications were used: PubMed, Medline, Scopus, and Cochrane were searched for articles published from January 2000 to April 2020. The databases were explored with original search queries containing the following terms: “Servqual”, “service quality”, “Servqual model”, “servqual questionnaire”, “health service quality”, “health care services”, “patients’ expectation”, “patients’ perception”, “expectation”, “perception”, and “health care services”, in combination using “AND” and “OR”. In order to minimize bias, two researchers (PK and DK) independently performed an online search for peer-reviewed papers, using the combinations of the above-mentioned words. In addition, references of eligible publications were checked. All disagreements, regarding the inclusion or exclusion of specific studies, were resolved through consultations among all the authors. Results: A total of 96 reports were identified and submitted to a preliminary screening selection. As a result of the pre-screening stage, 64 papers were qualified to further evaluation. The output of the evaluation brought 15 reported studies, meeting the pre-defined inclusion/exclusion criteria. The total number of participants was 5903 (ranging from 20 to 439 in individual reports), and 54% of them were women. Eight studies (53%) were from Iran, two from Pakistan (13%) and one each from Arabia, Malaysia, South Korea, Bangladesh, and Iraq (each-about 7%). The results showed gaps between patients’ expectations and perceptions in all five dimensions of Servqual in almost each analysed study. The highest and lowest values of the gaps in quality scores were associated with the dimensions of reliability, tangibility, empathy, and responsiveness, respectively. Conclusions: The study demonstrated that the method of Servqual is broadly used in various medical sectors to assess the quality of medical services provided. In addition, the study demonstrated that patients had significantly higher expectations of the medical services offered in the five dimensions studied. The results, obtained through the Servqual method, may help improve and monitor the quality of services provided by different institutions.

Generative adversarial U-Net for domain-free few-shot medical diagnosis

• We proposed a new data augmentation method for few-shot medical diagnosis. • The proposed method can be used in different modality medical image data. • Extensive experiments are conducted to demonstrate the superior of the proposed method. In interactive remote medical diagnosis, medical diagnosis support system plays an important role in the pre-screening stage. Deep learning methods are widely used in such system especially medical imaging area to provide an initial diagnosis to support medical professional. However, the shortage of annotated medical images is one of the biggest challenges in the field of medical image computing. Without a sufficient number of training samples, deep learning based models are very likely to suffer from over-fitting problem. The common solution is image manipulation such as image rotation , cropping, or resizing. Those methods can help relieve the over-fitting problem as more training samples are introduced. However, they do not really introduce new images with additional information and may lead to data leakage as the test set may contain similar samples which appear in the training set. To address this challenge, we propose to generate diverse images with generative adversarial network . In this paper, we develop a novel generative method named generative adversarial U-Net, which utilizes both generative adversarial network and U-Net. Different from existing approaches, our newly designed model is domain-free and generalizable to various medical images. Extensive experiments are conducted over eight diverse datasets including computed tomography (CT) scan, pathology, X-ray, etc. The visualization and quantitative results demonstrate the efficacy and good generalization of the proposed method on generating a wide array of high-quality medical images.

Fi-score: a novel approach to characterise protein topology and aid in drug discovery studies

Target evaluation is at the centre of rational drug design and biologics development. In order to successfully engineer antibodies, T-cell receptors or small molecules it is necessary to identify and characterise potential binding or contact sites on therapeutically relevant target proteins. Currently, there are numerous challenges in achieving a better docking precision as well as characterising relevant sites. We devised a first-of-its-kind in silico protein fingerprinting approach based on the dihedral angle and B-factor distribution to probe binding sites and sites of structural importance. Our derived Fi-score can be used to classify protein regions or individual structural subsets of interest and the described scoring system could be integrated into other discovery pipelines, such as protein classification databases, or applied to investigate new targets. We further demonstrated how our method can be integrated into machine learning Gaussian mixture models to predict different structural elements. Fi-score, in combination with other biophysical analytical methods depending on the research goals, could help to classify and systematically analyse not only targets but also drug candidates that bind to specific sites. The described methodology could greatly improve pre-screening stage, target selection and drug repurposing efforts in finding other matching targets. HIGHLIGHTS Description and derivation of a first-of-its-kind in silico protein fingerprinting method using B-factors and dihedral angles. Derived Fi-score allows to characterise the whole protein or selected regions of interest. Demonstration how machine learning using Gaussian mixture models on Fi-scores captures and allows to predict functional protein topology elements. Fi-score is a novel method to help evaluate therapeutic targets and engineer effective biologics. Communicated by Ramaswamy H. Sarma

A review of risk-based security and its impact on TSA PreCheck

Since September 11, 2001, the United States has invested a significant amount of resources into improving aviation security operations, with the Transportation Security Administration (TSA) assuming the responsibilities for security policy-making at commercial airports. This article reviews the literature that supports policies for risk-based passenger screening procedures and chronicles the analytical analysis leading up to the launch (in October 2011) of the TSA Precheck program, as a first step toward implementing a risk-based security strategy for passenger and baggage screening. Multi-level passenger prescreening is the basis of the mathematical framework behind TSA Precheck; the framework provides a prescriptive control of security operations in settings with limited resources. TSA Precheck assigns each passenger to a risk group, based on the initial perceived risk level (assessed in the prescreening stage), and then calibrates the security measures to mitigate the risk associated with each group. With passengers arriving in real-time and the order of their arrivals uncertain, the resource utilization problem is solved by dynamic programming. A numerical comparison between a risk-based and an equal-risk (i.e., non-risk-based) security model is presented to quantify the benefits of risk-based security.

Optimal technology selection for the biogas upgrading to biomethane

A systematic approach is developed for the conceptual optimal design of biomethane production via carbon capture. A hybrid heuristic-mathematical procedure is proposed to determine the optimal technology and operating conditions. The heuristic step consists of a literature-based screening of the available technologies. After the prescreening stage, the technologies selected are amine absorption, pressure swing adsorption (PSA), and membrane separation. The mathematical stage is composed of two steps. First, different alternatives for each technology are modelled based on first principles and rules of thumb. These models are used to select the optimal configuration for each process considered. Second, a superstructure model for biomethane production is developed integrating the pre-selected upgrading technologies to select the optimal process, as well as to determine the optimal operating conditions. Four waste sources are analyzed: cattle manure, swine manure, municipal food waste, and sludge. The results suggest that the best amine is diethanolamine (DEA), the best membrane material is the polyimide, and the suggested zeolite is 13X among the ones studied. Finally, among the three technologies, the overall results show that carbon capture using a PSA system using zeolite 13X results in lower production and investment costs, but very close to the use of membranes. The results indicate that food waste shows the lowest production cost for biomethane 0.36 €/Nm3, due to the largest organic matter content, whereas the investment costs are 67 M€, considering a biogas production rate of 0.035 kg of biomethane per kg of waste and the processing of 311 kt/yr of food waste. Credits or incentives are still needed for biomethane to be competitive with fossil natural gas.

Ship Detection for Polarimetric SAR Images Based on $\mathcal {G}_p^0$ Mixture Model

This paper presents a $\mathcal {G}_p^0$ mixture model-based ship detection method for polarimetric synthetic aperture radar (PolSAR) images. The proposed method is based on the assumption that target pixels can be regarded as a general class and that the PolSAR data contain abundant structure and textural information, which may help distinguish target from azimuth ambiguities and clutter. In the proposed method, a weighted combination of $\mathcal {G}_p^0$ distributions is used to characterize the PolSAR data to balance the complexity of parameter estimation and modeling accuracy. The proposed method is capable of automatically determining the number of class with an iterative expectation-maximization algorithm incorporating the $\mathcal {G}_p^0$ distribution. Besides, a prescreening process is integrated to realize computational acceleration. Instead of clustering all pixels in the PolSAR data, only potential target pixels selected in the prescreening stage are clustered. Therefore, fewer class is required to reach convergence due to the removal of most complex background. As a result, better computational efficiency can be achieved. After the clustering, the cluster corresponding to the targets can be distinguished conveniently with the averaged SPAN value of each cluster. The effectiveness and efficiency of the proposed method has been validated by using actual PolSAR datasets and by contrasting the proposed approach with other methods. Experimental results demonstrate its superiority in improving target detection rate while reducing false alarms caused by clutter and azimuth ambiguities.

Early diagnosis and detection of breast cancer.

Breast cancer is the most common malignancy in women. It is often characterized by a lack of early symptoms, which results in late detection of the disease. Detection at advanced stages of the decease implies the treatment is more difficult and uncertain. The appropriate screening programs have been conducted within the organized preventive examinations and have made significant contributions to the early breast cancer detection. It is necessary to improve the screening process in order to reduce the percentage of female population that is not covered by screening programs and increase the number of early-detected breast cancers. The improvement of the screening program may be reflected in the following: more efficient determination of the list of the women who have to undergo preventive examination, introduction of screening program in thermography as a diagnostic method applied in pre-screening stage, more efficient analysis of mammograms and continuous follow up of patients. The identification of target population for breast cancer screening program has been based on the age of women. The improvement of the early breast cancer diagnosis process proposed in this paper is reflected in more efficient determination of the group of women who have to undergo preventive examination based on the factors affecting the occurrence of breast cancer. Inclusion of the pre-screening phase in which thermal imaging could be applied and software support to mammographic detection of tumor are suggested. This paper describes the breast cancer, current screening program and techniques for early-stage breast cancer detection, module of medical information system MEDIS.NET for creating screening list based on the analysis of risk factors affecting the occurrence of breast cancer, mammography and role of thermal imaging in the process of early breast cancer detection. It also presents an overview on important achievements in computer-aided detection and diagnosis of breast cancer in mammography and thermography. Based on the obtained results, dynamics of preventive examinations for particular groups of women that is different from the standard two-year examinations, can be successfully defined. It can be concluded that the use of a computer system for tumor diagnosis in mammogram based on various methods of image processing can help doctors in decision-making, while the use of thermal imaging in the pre-screening phase would significantly reduce the list of women for screening mammograms.

Ship Detection in Optical Remote Sensing Images Based on Saliency and a Rotation-Invariant Descriptor

Major challenges for automatic ship detection in optical remote sensing (ORS) images include cloud, wave, island, wake clutters, and even the high variability of targets. This paper presents a practical ship detection scheme to resolve these existing issues. The scheme contains two main coarse-to-fine stages: prescreening and discrimination. In the prescreening stage, we construct a novel visual saliency detection method according to the difference of statistical characteristics between highly non-uniform regions which allude to regions of interest (ROIs) and homogeneous backgrounds. It can serve as a guide for locating candidate regions. In this way, not only can the targets be precisely detected, but false alarms are also significantly reduced. In the discrimination stage, to get a better representation of the target, both shape and texture features characterizing the ship target are extracted and concatenated as a feature vector for subsequent classification. Moreover, the combined feature is invariant to the rotation. Finally, a trainable Gaussian support vector machine (SVM) classifier is performed to validate real ships out of ship candidates. We demonstrate the superior performance of the proposed hierarchical detection method with detailed comparisons to existing efforts.

A novel target detection method for SAR images based on shadow proposal and saliency analysis

Conventional synthetic aperture radar (SAR) based target detection methods generally use high intensity pixels in the pre-screening stage while ignoring shadow information. Furthermore, they cannot accurately extract the target area and also have poor performance in cluttered environments. To solve this problem, a novel SAR target detection method which combines shadow proposal and saliency analysis is presented in this paper. The detection process is divided into shadow proposal, saliency detection and One-Class Support Vector Machine (OC-SVM) screening stages. In the shadow proposal stage, localizing targets is performed first with the detected shadow regions to generate proposal chips that may contain potential targets. Then saliency detection is conducted to extract salient regions of the proposal chips using local spatial autocorrelation and significance tests. Afterwards, in the last stage, the OC-SVM is employed to identify the real targets from the salient regions. Experimental results show that the proposed saliency detection method possesses higher detection accuracy than several state of the art methods on SAR images. Furthermore, the proposed SAR target detection method is demonstrated to be robust under different imaging environments.

Porcine Dendritic Cells as an In Vitro Model to Assess the Immunological Behaviour of Streptococcus suis Subunit Vaccine Formulations and the Polarizing Effect of Adjuvants.

An in vitro porcine bone marrow-derived dendritic cell (DC) culture was developed as a model for evaluating immune polarization induced by adjuvants when administered with immunogens that may become vaccine candidates if appropriately formulated. The swine pathogen Streptococcus suis was chosen as a prototype to evaluate proposed S. suis vaccine candidates in combination with the adjuvants Poly I:C, Quil A ®, Alhydrogel ®, TiterMax Gold ® and Stimune ®. The toll-like receptor ligand Poly I:C and the saponin Quil A ® polarized swine DC cytokines towards a type 1 phenotype, with preferential production of IL-12 and TNF-α. The water-in-oil adjuvants TiterMax Gold ® and Stimune ® favoured a type 2 profile as suggested by a marked IL-6 release. In contrast, Alhydrogel ® induced a type 1/type 2 mixed cytokine profile. The antigen type differently modified the magnitude of the adjuvant effect, but overall polarization was preserved. This is the first comparative report on swine DC immune activation by different adjuvants. Although further swine immunization studies would be required to better characterize the induced responses, the herein proposed in vitro model is a promising approach that helps assessing behaviour of the vaccine formulation rapidly at the pre-screening stage and will certainly reduce numbers of animals used while advancing vaccinology science.

Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography.

Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a linear discriminant classifier to score the detected masses. For the DCNN-based CAD system, ROIs from five consecutive slices centered at each candidate were passed through the trained DCNN and a mass likelihood score was generated. The performances of the CAD systems were evaluated using free-response ROC curves and the performance difference was analyzed using a non-parametric method. Before transfer learning, the DCNN trained only on mammograms with an AUC of 0.99 classified DBT masses with an AUC of 0.81 in the DBT training set. After transfer learning with DBT, the AUC improved to 0.90. For breast-based CAD detection in the test set, the sensitivity for the feature-based and the DCNN-based CAD systems was 83% and 91%, respectively, at 1 FP/DBT volume. The difference between the performances for the two systems was statistically significant (p-value < 0.05). The image patterns learned from the mammograms were transferred to the mass detection on DBT slices through the DCNN. This study demonstrated that large data sets collected from mammography are useful for developing new CAD systems for DBT, alleviating the problem and effort of collecting entirely new large data sets for the new modality.