Search

Simple Summary: Accurately grading gliomas, which are the most common and aggressive malignant brain tumors in adults, poses a significant challenge for radiologists. This study explores the application of Deep Learning techniques in assisting tumor grading using Magnetic Resonance Images (MRIs). By analyzing a glioma database sourced from multiple public datasets and comparing different settings, the aim of this study is to develop a robust and reliable grading system. The study demonstrates that by focusing on the tumor region of interest and augmenting the available data, there is a significant improvement in both the accuracy and confidence of tumor grade classifications. While successful in differentiating low-grade gliomas from high-grade gliomas, the accurate classification of grades 2, 3, and 4 remains challenging. The research findings have significant implications for advancing the development of a non-invasive, robust, and trustworthy data-driven system to support clinicians in the diagnosis and therapy planning of glioma patients. Glioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for radiologists and one in which they could be assisted by machine-learning-based decision support. However, the machine learning analytical pipeline is also fraught with perils stemming from different sources, such as inadvertent data leakage, adequacy of 2D image sampling, or classifier assessment biases. In this paper, we analyze a glioma database sourced from multiple datasets using a simple classifier, aiming to obtain a reliable tumor grading and, on the way, we provide a few guidelines to ensure such reliability. Our results reveal that by focusing on the tumor region of interest and using data augmentation techniques we significantly enhanced the accuracy and confidence in tumor classifications. Evaluation on an independent test set resulted in an AUC-ROC of 0.932 in the discrimination of low-grade gliomas from high-grade gliomas, and an AUC-ROC of 0.893 in the classification of grades 2, 3, and 4. The study also highlights the importance of providing, beyond generic classification performance, measures of how reliable and trustworthy the model's output is, thus assessing the model's certainty and robustness. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to identify the factors affecting the intention to use peer-to-peer (P2P) mobile payment. Although mobile technology has become part of everyday life, certain actions and services, such as mobile payments, are still used relatively infrequently. In this paper, we analyse consumers' adoption of P2P mobile payment services. Following a review of previous literature in this field, we identify the main factors that determine the adoption of mobile payments, and then perform a logistic regression (LR) analysis and propose a neural network to predict this adoption. From the logistic regression results obtained we conclude that six variables significantly influence intentions to use P2P payment: ease of use, perceived risk, personal innovativeness, perceived usefulness, subjective norms and perceived enjoyment. With respect to the nonparametric technique, we find that the multilayer perceptrons (MLP) prediction model for the use of P2P payment obtains higher AUC values, and thus is more accurate, than the LR model. This paper is a pioneer study of intention to use with mobile payment using these methodologies. The outcome of this research has important implications for the theory and practice of the adoption of P2P mobile payment services. [ABSTRACT FROM AUTHOR]

In this paper, we develop a detection module with strong training testing to develop a dense convolutional neural network model. The model is designed in such a way that it is trained with necessary features for optimal modelling of the cancer detection. The method involves preprocessing of computerized tomography (CT) images for optimal classification at the testing stages. A 10-fold cross-validation is conducted to test the reliability of the model for cancer detection. The experimental validation is conducted in python to validate the effectiveness of the model. The result shows that the model offers robust detection of cancer instances that novel approaches on large image datasets. The simulation result shows that the proposed method provides analyzes with 94% accuracy than other methods. Also, it helps to reduce the detection errors while classifying the cancer instances than other methods the several existing methods. [ABSTRACT FROM AUTHOR]

The sudden rise in the ability of machine learning methodology, such as deep neural networks, to identify and predict with great accuracy instances of malignant cell growth from radiological images has led prominent developers of this technology, such as Geoffrey Hinton, to hold the view that "[...] we should stop training radiologists." Similar views exist in other contexts regarding the replacement of humans with artificial intelligence (AI) technologies. The assumption in these kinds of views is that deep neural networks are better than human radiologists in that they are more accurate, less costly, and have more predictive power than their human counterparts. In this paper, I argue that these considerations, even if true, are simply inadequate as reasons for us to allocate the kind of trust suggested by Hinton and others to these sorts of artifacts. In particular, I show that if the same considerations were true of something other than an AI device, say a pigeon, we would not have sufficient reason to trust them in the same way as suggested of deep neural networks in a medical setting. If this is the case then these considerations are also insufficient to trust AI enough to replace radiologists. Furthermore, I argue that the reliability of AI methodologies such as deep neural networks—which are at the center of this argument—is something that has not yet been established, and doing so faces fundamental challenges. Because of these challenges, it is not possible to ascribe the level of reliability expected from the deployment of a medical device. So, not only are the reasons cited in favor of the deployment of AI technologies in medical settings not sufficient/adequate even if they are true, but knowing whether they are true or not faces non‐trivial epistemic challenges. If this is so, then we have no good reasons to advocate replacing radiologists with AI methodologies such as deep neural networks. [ABSTRACT FROM AUTHOR]

This paper presents an advanced version of the failure mode effects and criticality analysis (FMECA), whose capabilities are enhanced; in that the criticality assessment takes into account possible interactions among the principal causes of failure. This is obtained by integrating FMECA and Analytic Network Process, a multi-criteria decision making technique. Severity, Occurrence and Detectability are split into sub-criteria and arranged in a hybrid (hierarchy/network) decision-structure that, at the lowest level, contains the causes of failure. Starting from this decision-structure, the Risk Priority Number is computed making pairwise comparisons, so that qualitative judgements and reliable quantitative data can be easily included in the analysis, without using vague and unreliable linguistic conversion tables. Pairwise comparison also facilitates the effort of the design/maintenance team, since it is easier to place comparative rather than absolute judgments, to quantify the importance of the causes of failure. In order to clarify and to make evident the rational of the final results, a graphical tool, similar to the House of Quality, is also presented. At the end of the paper, a case study, which confirms the quality of the approach and shows its capability to perform robust and comprehensive criticality analyses, is reported. Copyright © 2011 John Wiley and Sons Ltd. [ABSTRACT FROM AUTHOR]

Uncertainty is usually modeled using random variable with certain probability distribution. However, the probability distributions of many random variables are often truncated in engineering applications. In the procedure of reliability based design optimization for structural systems with truncated random variables, repeated function evaluations are required for different design points where the computational costs are extremely huge. In this paper, an efficient as well as novel reliability method is proposed for structural systems with truncated random variables which does not require repeated function evaluations for the different design points. Uniformly distributed samples are generated for truncated random variables in the supported intervals and design variables in the specified intervals to approximate cover the entire uncertain space fully. In order to avoid repeated function evaluations and improve computational efficiency, a surrogate model is established using back-propagation (BP) neural networks which can approximate the relationships between the inputs and system responses properly in almost entire uncertain space using the proposed given available data. The main advantages of the proposed method are high accuracy and effectiveness in estimating the probability of failure under different design points which requires neither large samples nor the repeated function evaluations when compared to the existing reliability methods. Four numerical examples are investigated to demonstrate the effectiveness and accuracy of the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents an application of artificial neural network (ANN) technique for conducting the reliability analysis of Boeing 737 tires. For this purpose, an ANN model utilizing the feed-forward back-propagation algorithm as a learning rule is developed. The inputs to the neural network are the flight operational time and the number of landings as independent variables and the output is the failure rate of the tires. Two years of data are used for failure rate prediction model and validation. Model validation, which reflects the suitability of the model for future predictions, is performed by comparing the predictions of the model with that of Weibull regression model. The results show that the failure rate predicted by the ANN is closer in agreement with the actual data than the failure rate predicted by the Weibull model. The present work also identifies some of the common tire failures and presents representative results based on the established model for the most frequently occurring tire failure. Copyright © 2010 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Abstract: The inverse first-order reliability method (FORM) is one of the most widely used methods in inverse reliability analysis. However, this method has two drawbacks in the solution of inverse reliability problems with implicit response functions. First, it requires the evaluation of the derivatives of the response functions with respect to the random variables. When these functions are implicit functions of the random variables, derivatives of these response functions are not readily available. Second, it usually involves repeated deterministic response analyses of complicated structures due to the variation of the basic variables, and therefore requires a relatively long computation time. To overcome these drawbacks of the inverse FORM, an artificial neural network (ANN)-based inverse FORM is proposed in this paper. In this method, an ANN model is used to approximate the structural response function so that the number of deterministic response analyses can be dramatically reduced. The explicit formulation of structural response is derived by using the parameters of the ANN model. After the explicit response function is determined, the inverse FORM is applied to solve the inverse reliability problem. The accuracy and efficiency of the proposed method is demonstrated through two numerical examples. Some important parameters in the proposed method are also discussed. [Copyright &y& Elsevier]