Search

BackgroundOptimal detection and surveillance of bladder cancer (BCa) rely primarily on the cystoscopic visualization of bladder lesions. AI-assisted cystoscopy may improve image recognition and accelerate data acquisition.ObjectiveTo provide a comprehensive review of machine learning (ML), deep learning (DL) and convolutional neural network (CNN) applications in cystoscopic image recognition.Evidence acquisitionA detailed search of original articles was performed using the PubMed-MEDLINE database to identify recent English literature relevant to ML, DL and CNN applications in cystoscopic image recognition.Evidence synthesisIn total, two articles and one conference abstract were identified addressing the application of AI methods in cystoscopic image recognition. These investigations showed accuracies exceeding 90% for tumor detection; however, future work is necessary to incorporate these methods into AI-aided cystoscopy and compared to other tumor visualization tools. Furthermore, we present results from the RaVeNNA-4pi consortium initiative which has extracted 4200 frames from 62 videos, analyzed them with the U-Net network and achieved an average dice score of 0.67. Improvements in its precision can be achieved by augmenting the video/frame database.ConclusionAI-aided cystoscopy has the potential to outperform urologists at recognizing and classifying bladder lesions. To ensure their real-life implementation, however, these algorithms require external validation to generalize their results across other data sets.

The food industry has many points of vulnerability in its supply chain. It currently lacks integrated crisis management and response programs to understand the importance of decision-making during and in the aftermath of a bioterrorist attack on the food supply. Computer simulations have been used successfully in other industries as training and analysis tools. This paper describes an agent-based simulation for food defense training and analysis. Production information, consumption patterns, morbidity/mortality rates, recall costs and additional information were collected and provided to a data-driven simulation to anticipate the impact of decision-making on economic and public health during a terrorist attack. A case study is given with a representative exercise involving forty industry representatives who participated in a food defense simulation. Their decisions (recall and microbiological and toxicological testing) were derived from testing results, press releases, epidemiological data, and discussions with other industry and regulatory teams. Decisions made during the simulation resulted in over 76,000 illnesses, 45 deaths, and $132 million in recall costs. The no intervention, baseline scenario estimated to result in 91,000 illnesses and 54 deaths, indicating the improved public health outcomes resulting from players' decisions. Participants identified three key learning points: 1) communication between all groups is pertinent and challenging, 2) approaches to solve inherent food safety problems cannot be used to address food defense situations, and 3) human resource procedures regarding new hires and disgruntled employees should involve additional security measures. This computer simulation could be a valuable resource in food defense awareness and help educate companies and regulators about food defense risks and decision-making consequences.

A variety of anthropogenic compounds has been found to be capable of disrupting the endocrine systems of organisms, in laboratory studies as well as in wildlife. The most widely described endpoint is estrogenicity, but other hormonal disturbances, e.g., thyroid hormone disruption, are gaining more and more attention. Here, we present a review and chemical characterization, using principal component analysis, of organic compounds that have been tested for their capacity to bind competitively to the thyroid hormone transport protein transthyretin (TTR). The database contains 250 individual compounds and technical mixtures, of which 144 compounds are defined as TTR binders. Almost one third of these compounds (n = 52) were even more potent than the natural hormone thyroxine (T4). The database was used as a tool to assist in the identification of thyroid hormone-disrupting compounds (THDCs) in an effect-directed analysis (EDA) study of a sediment sample. Two compounds could be confirmed to contribute to the detected TTR-binding potency in the sediment sample, i.e., triclosan and nonylphenol technical mixture. They constituted less than 1 % of the TTR-binding potency of the unfractionated extract. The low rate of explained activity may be attributed to the challenges related to identification of unknown contaminants in combination with the limited knowledge about THDCs in general. This study demonstrates the need for databases containing compound-specific toxicological properties. In the framework of EDA, such a database could be used to assist in the identification and confirmation of causative compounds focusing on thyroid hormone disruption. Electronic supplementary material The online version of this article (doi:10.1007/s00216-015-8736-9) contains supplementary material, which is available to authorized users.

Formal verification aims to improve the quality of software by detecting errors before they do harm. At the basis of formal verification is the logical notion of correctness, which purports to capture whether or not a program behaves as desired. We suggest that the boolean partition of software into correct and incorrect programs falls short of the practical need to assess the behavior of software in a more nuanced fashion against multiple criteria. We therefore propose to introduce quantitative fitness measures for programs, specifically for measuring the function, performance, and robustness of reactive programs such as concurrent processes. This article describes the goals of the ERC Advanced Investigator Project QUAREM. The project aims to build and evaluate a theory of quantitative fitness measures for reactive models. Such a theory must strive to obtain quantitative generalizations of the paradigms that have been success stories in qualitative reactive modeling, such as compositionality, property-preserving abstraction and abstraction refinement, model checking, and synthesis. The theory will be evaluated not only in the context of software and hardware engineering, but also in the context of systems biology. In particular, we will use the quantitative reactive models and fitness measures developed in this project for testing hypotheses about the mechanisms behind data from biological experiments.

As a result of the increasing role of online advertising and strong competition among advertisers, intrusive techniques are commonly used to attract web users' attention. Moreover, since marketing content is usually delivered to the target audience when they are performing typical online tasks, like searching for information or reading online content, its delivery interrupts the web user's current cognitive process. The question posed by many researchers in the field of online advertising is: how should we measure the influence of interruption of cognitive processes on human behavior and emotional state? Much research has been conducted in this field; however, most of this research has focused on monitoring activity in the simulated environment, or processing declarative responses given by users in prepared questionnaires. In this paper, a more direct real-time approach is taken, and the effect of the interruption on a web user is analyzed directly by studying the activity of his brain. This paper presents the results of an experiment that was conducted to find the brain activity patterns associated with interruptions of the cognitive process by showing internet advertisements during a text-reading task. Three specific aspects were addressed in the experiment: individual patterns, the consistency of these patterns across trials, and the intra-subject correlation of the individual patterns. Two main effects were observed for most subjects: a drop in activity in the frontal and prefrontal cortical areas across all frequency bands, and significant changes in the frontal/prefrontal asymmetry index.

This paper aims to discuss various aspects of the use of reference genes in qPCR technique used in the thousands of present studies. Most frequently, these are housekeeping genes and they must meet several criteria so that they can lay claim to the name. Lots of papers report that in different conditions, for different organisms and even tissues the basic assumption—the constant level of the expression is not maintained for many genes that seem to be perfect candidates. Moreover, their transcription can not be affected by experimental factors. Sounds simple and clear but a great number of designed protocols and lack of consistency among them brings confusion on how to perform experiment properly. Since during selection of the most stable normalizing gene we can not use any reference gene, different ways and algorithms for their selection were developed. Such methods, including examples of best normalizing genes in some specific cases and possible mistakes are presented based on available sources. Numerous examples of reference genes applications, which are usually in too few numbers in relevant articles not allowing to make a solid fundament for a reader, will be shown along with instructive compilations to make an evidence for presented statements and an arrangement of future qPCR experiments. To include all the pitfalls and problems associated with the normalization methods there is no way not to begin from sample preparation and its storage going through candidate gene selection, primer design and statistical analysis. This is important because numerous short reviews available cover the topic only in lesser extent at the same time giving the reader false conviction of complete topic recognition.

Peer-review systems such as SWoRD lack intelligence for detecting and responding to problems with students’ reviewing performance. While prior work has demonstrated the feasibility of automatically identifying desirable feedback features in free-text reviews of student papers, similar methods have not yet been developed for feedback regarding argument diagrams. One desirable feedback feature is problem localization, which has been shown to positively correlate with feedback implementation in both student papers and argument diagrams. In this paper we demonstrate that features previously developed for identifying localization in paper reviews do not work well when applied to peer reviews of argument diagrams. We develop a novel algorithm tailored for reviews of argument diagrams, and demonstrate significant performance improvements in identifying problem localization in an experimental evaluation.

Monitoring on urban water environment and analysis of engineering improvement measures are intricate and time-consuming tasks. In previous studies, the integration of hydrodynamic and water quality models and geographical information system (GIS) usually takes three approaches: loose coupling, tight coupling, and full coupling. However, this paper adopted a special loose coupling approach—case-based reasoning (CBR) to develop an integrated decision support system. This was characterized by invoking the case base stored in the GIS platform as the output of the model. The fused capability of model’s water quality predication and strong spatial data processing analysis of GIS can be realized at the same time by integration. The functionality of the integrated system was illustrated through a case study of Chaohu, a medium-sized city in China, which includes case retrieval, result interpretation, and the visual display in the GIS platform. Results verified the feasibility and operability of the developed method. As a useful tool, the integrated decision support system makes it simpler and more convenient for decision makers to make decisions efficiently and quickly.

Today, diagnosis of attention deficit hyperactivity disorder (ADHD) still primarily relies on a series of subjective evaluations that highly rely on a doctor’s experiences and intuitions from diagnostic interviews and observed behavior measures. An accurate and objective diagnosis of ADHD is still a challenge and leaves much to be desired. Many children and adults are inappropriately labeled with ADHD conditions, whereas many are left undiagnosed and untreated. Recent advances in neuroimaging studies have enabled us to search for both structural (e.g., cortical thickness, brain volume) and functional (functional connectivity) abnormalities that can potentially be used as new biomarkers of ADHD. However, structural and functional characteristics of neuroimaging data, especially magnetic resonance imaging (MRI), usually generate a large number of features. With a limited sample size, traditional machine learning techniques can be problematic to discover the true characteristic features of ADHD due to the significant issues of overfitting, computational burden, and interpretability of the model. There is an urgent need of efficient approaches to identify meaningful discriminative variables from a higher dimensional feature space when sample size is small compared with the number of features. To tackle this problem, this paper proposes a novel integrated feature ranking and selection framework that utilizes normalized brain cortical thickness features extracted from MRI data to discriminate ADHD subjects against healthy controls. The proposed framework combines information theoretic criteria and the least absolute shrinkage and selection operator (Lasso) method into a two-step feature selection process which is capable of selecting a sparse model while preserving the most informative features. The experimental results showed that the proposed framework generated the highest/comparable ADHD prediction accuracy compared with the state-of-the-art feature selection approaches with minimum number of features in the final model. The selected regions of interest in our model were consistent with recent brain–behavior studies of ADHD development, and thus confirmed the validity of the selected features by the proposed approach.

It is common that students peer-review other students' writing, and these reviews are useful information to instructors, both on the particulars of the essay being reviewed, the feedback provided and the overall progress of the class. This paper describes a novel approach to summarising feedback in academic essay writing. We present a summarisation method for identifying and extracting representative opinion sentences from each feedback. Sentiment score-based techniques are employed and SentiWordNet is used as a linguistic lexical resource for sentiment summarisation. We evaluate our approach with the reviews written by a group of 50 engineering students.

We have been developed the peer review support system for a presentation rehearsal. The purpose of the systems is to refine presenter's knowledge and presentation through a review work of the peer review results as a feedback. For the review work, the system have to organize a lot of comments accumulated in the peer review process, and represent them in an easy-to-understand way. In this paper, we discuss an annotation groping method based on a presentation structure, which for a back-review process after a presentation rehearsal.

In this paper, we use supervised machine learning to automatically identify the problem localization of peer-review feedback Using five features extracted via Natural Language Processing techniques, the learned model significantly outperforms a standard baseline Our work suggests that it is feasible for future tutoring systems to generate assessments regarding the use of localization in student peer reviews.

In the context of Intelligent Tutoring Systems, there is a potential for adapting either content or its sequence to student as to enhance the learning experience. Recent theories propose the use of team-working environments to improve even further this experience. In this paper an effective matching algorithm is presented in the context of peer reviewing applied to an educational setting. The problem is formulated as an optimization problem to search a solution that satisfies a set of given criteria modeled as "profiles". These profiles represent regions of the solution space to be either favored or avoided when searching for a solution. The proposed technique was deployed in a first semester computer engineering course and proved to be both effective and well received by the students.

In this survey talk we discuss several problems related to peer to peer networks. A host of issues arises in the context of peer to peer networks, including efficiency issues, censorship issues, anonymity issues, etc. While many of these problems have been studied in the past, the file swapping application has taken over the Internet, given these problems renewed impetus. I will discuss papers co-authored with J. Saia, E. Cohen, H. Kaplan, R. Berman, A. Ta-Sham, and others.

Despite the fact the hypermedia has long been discussed as a suitable format for academic research publications, the academic community has made little progress toward realizing hypermedia publishing. In this paper, we provide an initial framework for considering the problems facing any system designed for publishing academic hypertexts, and propose some first steps our community can take toward realizing this goal.