Software Reliability Analysis by Using the Bidirectional Attention Based Zeiler-Fergus Convolutional Neural Network

Designing of VehiNet Using Convolutional Neural Networks and Deep Learning Techniques

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

The aim of this study is to develop a predictive model utilizing deep learning and machine learning techniques that will inform clinical decision-making by predicting the 1-year postoperative recovery of patients with lumbar disk herniation. The clinical data of 470 inpatients who underwent tubular microdiscectomy (TMD) between January 2018 and January 2021 were retrospectively analyzed as variables. The dataset was randomly divided into a training set (n = 329) and a test set (n = 141) using a 10-fold cross-validation technique. Various deep learning and machine learning algorithms including Random Forests, Extreme Gradient Boosting, Support Vector Machines, Extra Trees, K-Nearest Neighbors, Logistic Regression, Light Gradient Boosting Machine, and MLP (Artificial Neural Networks) were employed to develop predictive models for the recovery of patients with lumbar disk herniation 1 year after surgery. The cure rate score of lumbar JOA score 1 year after TMD was used as an outcome indicator. The primary evaluation metric was the area under the receiver operating characteristic curve (AUC), with additional measures including decision curve analysis (DCA), accuracy, sensitivity, specificity, and others. The heat map of the correlation matrix revealed low inter-feature correlation. The predictive model employing both machine learning and deep learning algorithms was constructed using 15 variables after feature engineering. Among the eight algorithms utilized, the MLP algorithm demonstrated the best performance. Our study findings demonstrate that the MLP algorithm provides superior predictive performance for the recovery of patients with lumbar disk herniation 1 year after surgery.

Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis

Deep learning has become a popular method in the last ten years with its superior performance in many fields, especially in health. Although it is a sub-branch of machine learning, one of the most important reasons for researchers to use this method is that it automates the difficult processes of feature extraction stages in traditional machine learning methods. With the advancement of technology every year, it has become easier to create large data sets or to access large data sets that have been used before on the web. Researchers who want to work on large data sets use deep learning methods effectively because of their advantages instead of using traditional machine learning methods. The foundations of deep learning were laid with the deep belief networks method, which was first developed in 2006. Later, with the significant success of the Convolutional Neural Network (CNN) method developed in 2012 in image classification, deep learning methods have been used in many applications in other disciplines. The success of the deep reinforcement learning algorithm that defeated Alpha Go champion Lee Sedol in 2016, the remarkable success of the contentious generating networks in creating their own unique images, the success of the Siamese networks with the ability to learn from little data in signature verification and facial recognition systems, the success of the artificial intelligence chat bot ChatGPT, which was launched in the last months of 2022, attracted attention in a short time, and the ability of DALL-E, a similar language model, to create images from texts, shows that deep learning is in constant innovation and development. This study aims to give an idea to researchers who will work in this field in the future by talking about the basic concepts of deep learning and the innovative and popular approaches used.

The proposed book chapter focuses on development of an efficient AI based medical imaging solution for COVID-19 by leveraging the easily available COVID X-Ray Images (CXR). For this the experimentation with different deep learning and machine learning algorithms is performed. A convolution network (CNN) is one of the widely used deep learning algorithms used for medical imaging systems. In this chapter different variants of CNN are used. Data augmentation and dropout techniques are used to avoid overfitting. Among these different variants, CNN with ten convolutional layers and 15 epochs has given the best performance of 88.23% training 85.94% validation accuracy. This is followed by the use of Alexnet for feature extraction from CXR images and the extracted features are given as the input to different machine learning classifiers including Gaussian Naïve Bays, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boost, Ada Boost for classification of input images among the classes of Covid-19, No Finding, Pneumonia. Among these machine learning classifiers, SVM has given the best performance of 86% testing accuracy. Thus, the deep learning algorithms have proven to give satisfactory performance. This performance can still be improved with the help of more images and by fine tuning the pre trained models. In addition, this chapter highlights the importance of transfer learning, brief description about medical imaging.

Vestibular Schwannoma (VS) is a rare tumor with varied incidence rates, predominantly affecting the 60–69 age group. In the era of artificial intelligence (AI), deep learning (DL) algorithms show promise in automating diagnosis. However, a knowledge gap exists in the automated segmentation of VS using DL. To address this gap, this meta-analysis aims to provide insights into the current state of DL algorithms applied to MR images of VS.MethodologyFollowing 2020 PRISMA guidelines, a search across four databases was conducted. Inclusion criteria focused on articles using DL for VS MR image segmentation. The primary metric was the Dice score, supplemented by relative volume error (RVE) and average symmetric surface distance (ASSD).ResultsThe search process identified 752 articles, leading to 11 studies for meta-analysis. A QUADAS- 2 analysis revealed varying biases. The overall Dice score for 56 models was 0.89 (CI: 0.88–0.90), with high heterogeneity (I2 = 95.9%). Subgroup analyses based on DL architecture, MRI inputs, and testing set sizes revealed performance variations. 2.5D DL networks demonstrated comparable efficacy to 3D networks. Imaging input analyses highlighted the superiority of contrast-enhanced T1-weighted imaging and mixed MRI inputs.DiscussionThis study fills a gap in systematic review in the automated segmentation of VS using DL techniques. Despite promising results, limitations include publication bias and high heterogeneity. Future research should focus on standardized designs, larger testing sets, and addressing biases for more reliable results. DL have promising efficacy in VS diagnosis, however further validation and standardization is needed.ConclusionIn conclusion, this meta-analysis provides comprehensive review into the current landscape of automated VS segmentation using DL. The high Dice score indicates promising agreement in segmentation, yet challenges like bias and heterogeneity must be addressed in the future research.

Deep convolutional neural network and IoT technology for healthcare.

Recent technological advancements allow deep learning to be employed in practically every aspect of life. Because deep learning techniques are so precise, they can be used in medicine to classify and detect various diseases. The coronavirus (SARSCoV2) epidemic has recently affected global health systems. One of the ways to diagnose SARSCoV2 is with a chest X-ray. This paper proposes a deep learning technique to distinguish SARSCoV2 positive and normal cases. In this study, we fine-tuned the deep learning models and hyperparameters, and the fine-tuned deep learning models performed significantly better. To classify X-ray images, we developed a system based on deep learning algorithms that includes five models: Xception, VGG19, ResNet50, DenseNet121, and Inception. We offer deep learning models and algorithms that have been trained and evaluated to support medical efforts and reduce medical staff workload when dealing with SARSCoV2. In addition, the classification model that was proposed yields positive results because it makes use of accurate classification of the SARSCoV2 disease based on medical images. Additionally, the performance of our proposed CNN classification method for medical imaging was evaluated using various edge-based neural networks. The accuracy of tertiary classification with CNN will decrease as the number of classes in the training network grows. In tertiary classification, which includes normal and SARSCoV2 positive images, the proposed model achieved a 0.9897 accuracy. The proposed algorithm achieves a high level of classification accuracy when using the DenseNet121 model for binary classification.

Alzheimer’s disease (AD) stands as a progressive neurodegenerative disorder with a significant global public health impact. It is imperative to establish early and accurate diagnoses of AD to facilitate effective interventions and treatments. Recent years have witnessed the emergence of machine learning (ML) and deep learning (DL) techniques, displaying promise in various medical domains, including AD diagnosis. This study undertakes a comprehensive contrast between conventional machine learning methods and advanced deep learning strategies for early AD diagnosis. Conventional ML algorithms like support vector machines, decision trees, and K nearest neighbor have been extensively employed for AD diagnosis through relevant feature extraction from heterogeneous data sources. Conversely, deep learning techniques such as multilayer perceptron (MLP) and convolutional neural networks (CNNs) have demonstrated exceptional aptitude in autonomously uncovering intricate patterns and representations from unprocessed data like EEG data. The findings reveal that while traditional ML methods may perform adequately with limited data, deep learning techniques excel when ample data is available, showcasing their potential for early and precise AD diagnosis. In conclusion, this research paper contributes to the ongoing discourse surrounding the choice of appropriate methodologies for early Alzheimer’s disease diagnosis.

Background Deep learning (DL) algorithms have shown promising results in mammographic screening either compared to a single reader or, when deployed in conjunction with a human reader, compared with double reading. Purpose To externally validate the performance of three DL algorithms as mammographic screen readers in an independent UK data set. Materials and Methods Three commercial DL algorithms (DL-1, DL-2, and DL-3) were retrospectively investigated from January 2022 to June 2022 using consecutive full-field digital mammograms collected at two UK sites during 1 year (2017). Normal cases with 3-year follow-up and histopathologically proven cancer cases detected either at screening (that round or next) or within the 3-year interval were included. A preset specificity threshold equivalent to a single reader was applied. Performance was evaluated for stand-alone DL reading compared with single human reading, and for DL reading combined with human reading compared with double reading, using sensitivity and specificity as the primary metrics. P < .025 was considered to indicate statistical significance for noninferiority testing. Results A total of 26 722 cases (median patient age, 59.0 years [IQR, 54.0-63.0 years]) with mammograms acquired using machines from two vendors were included. Cases included 332 screen-detected, 174 interval, and 254 next-round cancers. Two of three stand-alone DL algorithms achieved noninferior sensitivity (DL-1: 64.8%, P < .001; DL-2: 56.7%, P = .03; DL-3: 58.9%, P < .001) compared with the single first reader (62.8%), and specificity was noninferior for DL-1 (92.8%; P < .001) and DL-2 (96.8%; P < .001) and superior for DL-3 (97.9%; P < .001) compared with the single first reader (96.5%). Combining the DL algorithms with human readers achieved noninferior sensitivity (67.0%, 65.6%, and 65.4% for DL-1, DL-2, and DL-3, respectively; P < .001 for all) compared with double reading (67.4%), and superior specificity (97.4%, 97.6%, and 97.6%; P < .001 for all) compared with double reading (97.1%). Conclusion Use of stand-alone DL algorithms in combination with a human reader could maintain screening accuracy while reducing workload. Published under a CC BY 4.0 license. Supplemental material is available for this article.

Early prediction of student performance is a critical and challenging task in the field of Educational Data Mining (EDM), encompassing all levels of education. Although there is extensive literature on student performance within EDM, studies specifically focused on early prediction are limited and mostly rely on traditional machine learning methods. However, in recent years, the importance and use of deep learning (DL) methods have increased due to their ability to process large datasets. This systematic literature review focuses on the early prediction of student performance using DL techniques. A total of 39 articles selected from the Scopus and Web of Science databases were analyzed using systematic and bibliometric methods. The review addresses five key research questions, including the distribution of studies by publication year, type, and education level; the datasets and features used; DL models and techniques; the timing of early predictions; and the challenges, limitations, and opportunities encountered. The bibliometric analysis, conducted with the VOSviewer program, visualized relationships between keywords, authors, and articles. Overall, this review provides a comprehensive synthesis of existing research on the early prediction of student academic performance using DL, offering valuable insights into trends and opportunities for researchers, educators, and policymakers.

Automatic target recognition of synthetic aperture radar (SAR) images has been a vital issue in recent studies. The recognition methods can be divided into two main types: traditional machine learning methods and deep-learning-based methods. For most traditional machine learning methods, target features are extracted based on electromagnetic scattering characteristics which are interpretable and stable. However, the extraction process of effective recognition features is often complex and the computational efficiency is low. Compared with the traditional methods, the deep learning methods can directly learn the high-dimensional features of the target to obtain higher target recognition accuracy. However, these algorithms have poor generalization performance and are difficult to explain. In order to comprehensively consider the advantages of the two kinds of methods, this article proposes a novel method for SAR target classification based on integration parts model and deep learning algorithm. First, part convolution and modified bidirectional convolutional-recurrent network are used to extract local feature of target through parts model which is calculated based on attribute scattering centers. Then, modified all-convolutional networks are used to extract the global feature of the target. The final classification result is achieved through decision fusion of local and global features. Experimental results on the moving and stationary target acquisition and recognition show the superiority of the proposed method, especially under complex conditions. Besides, a brief analysis of target key parts with part occlusion method is given, which is helpful to the interpretability of the deep learning network.

Classification of time series is an essential requirement of various applications that demand continuous monitoring of dynamical systems such as industrial process and health care monitoring. Feature extraction plays a vital role in deciding performance of the time series models. In recent years deep learning techniques have shown an excellent performance to extract highly discriminating features for the classification of the time series. A Convolutional Neural Network (CNN) is a unified framework that performs the feature learning and classification tasks simultaneously. Using the CNN to perform the classification of the multivariate time series is still a challenging task. In this paper, we propose an attention-based multivariate convolutional neural network (AT-MVCNN) that consists of the attention feature-based input tensor scheme to encode informations across the multiple time stamps. The method is capable of learning the temporal characteristics of the multivariate time series. The efficacy of the proposed method is tested on Human Activity Recognition (HAR) and Occupancy Detection datasets. The experiments and results show the proposed method outperforms the other deep learning and traditional machine learning models.

Use of deep learning to detect personalized spatial-frequency abnormalities in EEGs of children with ADHD