Automatic detection of the carotid lumen axis in B-mode ultrasound images

A new approach is introduced for the automatic detection of the lumen axis of the common carotid artery in B-mode ultrasound images. The image is smoothed using a Gaussian filter and then a dynamic programming scheme extracts the dominant paths of local minima of the intensity and the dominant paths of local maxima of the gradient magnitude with the gradient pointing downwards. Since these paths are possible estimates of the lumen axis and the far wall of a blood vessel, respectively, they are grouped together into pairs. Then, a pattern of two features is computed from each pair of paths and used as input to a linear discriminant classifier in order to select the pair of paths that correspond to the common carotid artery. The estimated lumen axis is the path of local minima of the intensity that belongs to the selected pair of paths. The proposed method is suited to real time processing, no user interaction is required and the number of parameters is minimal and easy to determine.     

Automated segmentation of RGB-D images into a comprehensive set of building components using deep learning

Building information modeling (BIM) has a semantic scope that encompasses all building systems, e.g. architectural, structural, mechanical, electrical, and plumbing. Automated, comprehensive digital modeling of buildings will require methods for semantic segmentation of images and 3D reconstructions capable of recognizing all building component classes. However, prior building component recognition methods have had limited semantic coverage and are not easily combined or scaled. Here we show that a deep neural network can semantically segment RGB-D (i.e. color and depth) images into 13 building component classes simultaneously despite the use of a small training dataset with only 1490 object instances. For this task, the method achieves an average intersection over union (IoU) of 0.5. The dataset was designed using a common building taxonomy to ensure comprehensive semantic coverage and was collected from a diversity of buildings to ensure intra-class diversity. As a consequence of its semantic scope, it was necessary to perform pre-segmentation and 3D to 2D projection as leverage for dataset annotation. In creating our deep learning pipeline, we found that transfer learning, class balancing, and prevention of overfitting effectively overcame the dataset’s borderline adequate class representation. Our results demonstrate how the semantic coverage of a building component recognition method can be scaled to include a larger diversity of building systems. We anticipate our method to be a starting point for broadening the scope of the semantic segmentation methods involved in digital modeling of buildings.     

Electrocardiogram soft computing using hybrid deep learning CNN-ELM

Electrocardiogram (ECG) can reflect the state of human heart and is widely used in clinical cardiac examination. However, the electrocardiogram signal is very weak, the anti-interference ability is poor, easy to be affected by the noise. Doctors face difficulties in diagnosing arrhythmias. Therefore, automatic recognition and classification of ECG signals is an important and indispensable task. Since the beginning of the 21 st century, deep learning has developed rapidly and has shown the most advanced performance in various fields. This paper presents a method of combining (Convolutional neural network) CNN and ELM (extreme learning machine). The accuracy rate is 97.50%. Compared with the state-of-the-art methods, this method improves the accuracy of ECG automatic classification and has good generalization ability.     

Segmentation of ultrasound images of the carotid using RANSAC and cubic splines

A new algorithm is proposed for the semi-automatic segmentation of the near-end and the far-end adventitia boundary of the common carotid artery in ultrasound images. It uses the random sample consensus method to estimate the most significant cubic splines fitting the edge map of a longitudinal section. The consensus of the geometric model (a spline) is evaluated through a new gain function, which integrates the responses to different discriminating features of the carotid boundary: the proximity of the geometric model to any edge or to valley shaped edges; the consistency between the orientation of the normal to the geometric model and the intensity gradient; and the distance to a rough estimate of the lumen boundary.A set of 50 longitudinal B-mode images of the common carotid and their manual segmentations performed by two medical experts were used to assess the performance of the method. The image set was taken from 25 different subjects, most of them having plaques of different classes (class II to class IV), sizes and shapes.The quantitative evaluation showed promising results, having detection errors similar to the ones observed in manual segmentations for 95% of the far-end boundaries and 73% of the near-end boundaries.     

Bone age estimation from carpal radiography images using deep learning

Bone age estimation has been used in medicine to verify whether the bone structure development degree of a person corresponds to their chronological age. Such estimate is useful for prognosis about the development of children and adolescents, as well as for the diagnosis of endocrinological diseases. This work proposes a fully automated methodology for bone age estimation from carpal radiography images. The methodology comprises two steps, the preprocessing of the image and the classification using a convolutional neural network. The system accuracy for different types of preprocessing is evaluated. We compare the accuracy achieved using the full radiography image as input for the neural network and using only parts of the image corresponding to the Phalangeal region, the Epiphyseal region, and the concatenation of these parts with a crop around the wrist. Digital image processing techniques are employed to segment these regions. Experiments are performed using radiography images from the California University Database. The impact of using different pre-trained neural networks for transfer learning is evaluated.     

A reinforcement agent for object segmentation in ultrasound images

The principal contribution of this work is to design a general framework for an intelligent system to extract one object of interest from ultrasound images. This system is based on reinforcement learning. The input image is divided into several sub-images, and the proposed system finds the appropriate local values for each of them so that it can extract the object of interest. The agent uses some images and their ground-truth (manually segmented) version to learn from. A reward function is employed to measure the similarities between the output and the manually segmented images, and to provide feedback to the agent. The information obtained can be used as valuable knowledge stored in the Q-matrix. The agent can then use this knowledge for new input images. The experimental results for prostate segmentation in trans-rectal ultrasound images show high potential of this approach in the field of ultrasound image segmentation.     

Efficient surface defect detection using self-supervised learning strategy and segmentation network

Surface defect detection plays a crucial role in the production process to ensure product quality. With the development of Industry 4.0 and smart manufacturing, traditional manual defect detection becomes no longer satisfactory, and deep learning-based technologies are gradually applied to surface defect detection tasks. However, the application of deep learning-based defect detection methods in actual production lines is often constrained by insufficient data, expensive annotations, and limited computing resources. Detection methods are expected to require fewer annotations as well as smaller computational consumption. In this paper, we propose the Self-Supervised Efficient Defect Detector (SEDD), a high-efficiency defect defector based on self-supervised learning strategy and image segmentation. The self-supervised learning strategy with homographic enhancement is employed to ensure that defective samples with annotations are no longer needed in our pipeline, while competitive performance can still be achieved. Based on this strategy, a new surface defect simulation dataset generation method is proposed to solve the problem of insufficient training data. Also, a lightweight structure with the attention module is designed to reduce the computation cost without incurring accuracy. Furthermore, a multi-task auxiliary strategy is employed to reduce segmentation errors of edges. The proposed model has been evaluated with three typical datasets and achieves competitive performance compared with other tested methods, with 98.40% AUC and 74.84% AP on average. Experimental results show that our network has the smallest computational consumption and the highest running speed among the networks tested.     

Segmentation of the carotid intima-media region in B-mode ultrasound images

This paper proposes a new approach for the segmentation of both near-end and far-end intima-media regions of the common carotid artery in ultrasound images. The method requires minimal user interaction and is able to segment the near-end wall in arteries with large, hypoechogenic and irregular plaques, issues usually not considered previously due to the increased segmentation difficulty.     

A tutorial on the segmentation of metallographic images: Taxonomy,new MetalDAM dataset,deep learning-based ensemble model,experimental analysis and challenges

Image segmentation is an important issue in many industrial processes, with high potential to enhance the manufacturing process derived from raw material imaging. For example, metal phases contained in microstructures yield information on the physical properties of the steel. Existing prior literature has been devoted to develop specific computer vision techniques able to tackle a single problem involving a particular type of metallographic image. However, the field lacks a comprehensive tutorial on the different types of techniques, methodologies, their generalizations and the algorithms that can be applied in each scenario. This paper aims to fill this gap. First, the typologies of computer vision techniques to perform the segmentation of metallographic images are reviewed and categorized in a taxonomy. Second, the potential utilization of pixel similarity is discussed by introducing novel deep learning-based ensemble techniques that exploit this information. Third, a thorough comparison of the reviewed techniques is carried out in two openly available real-world datasets, one of them being a newly published dataset directly provided by ArcelorMittal, which opens up the discussion on the strengths and weaknesses of each technique and the appropriate application framework for each one. Finally, the open challenges in the topic are discussed, aiming to provide guidance in future research to cover the existing gaps.     

基于深度学习的超声图像左心耳自动分割方法

从超声图像中分割出左心耳（LAA）是得出临床诊断指标的重要步骤,而准确自动分割的首要步骤和难点就是实现目标的自动定位。针对这一问题,提出了一种结合基于深度学习框架的自动定位和基于模型的分割算法的方法来实现超声图像中LAA的自动分割。首先,训练YOLO模型作为LAA自动定位的网络架构;其次,通过验证集确定最优的权重文件,并预测出LAA的最小包围盒;最后,在正确定位的基础上,将YOLO预测的最小包围盒放大1.5倍作为初始轮廓,利用C-V模型完成LAA的自动分割。分割结果用5项指标加以评价：正确性、敏感性、特异性、阴性、阳性。实验结果表明,所提方法能够实现不同分辨率条件和不同显示模式下LAA的自动定位,小样本数据在1000次迭代时已经达到最优的定位效果,正确定位率达到72.25%,并且在正确定位的基础上,C-V模型的分割准确率能够达到98.09%。因此,深度学习技术在实现LAA超声图像的自动分割上具备较大的潜力,能够为基于轮廓的分割算法提供良好的初始轮廓。     

On learning effective ensembles of deep neural networks for intrusion detection

Classification-oriented Machine Learning methods are a precious tool, in modern Intrusion Detection Systems (IDSs), for discriminating between suspected intrusion attacks and normal behaviors. Many recent proposals in this field leveraged Deep Neural Network (DNN) methods, capable of learning effective hierarchical data representations automatically. However, many of these solutions were validated on data featuring stationary distributions and/or large amounts of training examples. By contrast, in real IDS applications different kinds of attack tend to occur over time, and only a small fraction of the data instances is labeled (usually with far fewer examples of attacks than of normal behavior). A novel ensemble-based Deep Learning framework is proposed here that tries to face the challenging issues above. Basically, the non-stationary nature of IDS log data is faced by maintaining an ensemble consisting of a number of specialized base DNN classifiers, trained on disjoint chunks of the data instances’ stream, plus a combiner model (reasoning on both the base classifiers predictions and original instance features). In order to learn deep base classifiers effectively from small training samples, an ad-hoc shared DNN architecture is adopted, featuring a combination of dropout capabilities, skip-connections, along with a cost-sensitive loss (for dealing with unbalanced data). Tests results, conducted on two benchmark IDS datasets and involving several competitors, confirmed the effectiveness of our proposal (in terms of both classification accuracy and robustness to data scarcity), and allowed us to evaluate different ensemble combination schemes.     

Automatic data clustering using continuous action-set learning automata and its application in segmentation of images

Most of the proposed algorithms to solve the dynamic clustering problem are based on nature inspired meta-heuristic algorithms. In this paper a different reinforcement based optimization approach called continuous action-set learning automata (CALA) is used and a novel dynamic clustering approach called ACCALA is proposed. CALA is an optimization tool interacting with a random environment and learn the optimal action from the environment feedbacks. In this paper the dynamic clustering problem considered as a noisy optimization problem and the team of CALAs is used to solve this noisy optimization problem. To build such a team of CALAs this paper proposed a new representation of CALAs. Each automaton in this team uses its continuous action-set and defining a suitable action-set for each automaton has a great impact on the CALAs search behavior. In this paper we used the statistical property of data-sets and proposed a new method to automatically find an action-set for each automaton. The performance of ACCALA is evaluated and the results are compared with seven well-known automatic clustering techniques. Also ACCALA is used to perform automatic segmentation. The experimental results are promising and show that the proposed algorithm produced compact and well-separated clusters.     

Cascaded re-ranking modelling of translation hypotheses using extreme learning machines

In statistical machine translation (SMT), re-ranking of huge amount of randomly generated translation hypotheses is one of the essential components in determining the quality of translation result. In this work, a novel re-ranking modelling framework called cascaded re-ranking modelling (CRM) is proposed by cascading a classification model and a regression model. The proposed CRM effectively and efficiently selects the good but rare hypotheses in order to alleviate simultaneously the issues of translation quality and computational cost. CRM can be partnered with any classifier such as support vector machines (SVM) and extreme learning machine (ELM). Compared to other state-of-the-art methods, experimental results show that CRM partnered with ELM (CRM-ELM) can raise at most 11.6% of translation quality over the popular benchmark Chinese–English corpus (IWSLT 2014) and French–English parallel corpus (WMT 2015) with extremely fast training time for huge corpus.     

Predictive maintenance using cox proportional hazard deep learning

Predictive maintenance (PdM) has become prevalent in the industry in order to reduce maintenance cost and to achieve sustainable operational management. The core of PdM is to predict the next failure so corresponding maintenance can be scheduled before it happens. The purpose of this study is to establish a Time-Between-Failure (TBF) prediction model through a data-driven approach. For PdM, data sparsity is regarded as a critical issue which can jeopardize algorithm performance for the modelling based on maintenance data. Meanwhile, data censoring has imposed another challenge for handling maintenance data because the censored data is only partially labelled. Furthermore, data sparsity may affect algorithm performance of existing approaches when addressing the data censoring issue. In this study, a new approach called Cox proportional hazard deep learning (CoxPHDL) is proposed to tackle the aforementioned issues of data sparsity and data censoring that are common in the analysis of operational maintenance data. The idea is to offer an integrated solution by taking advantage of deep learning and reliability analysis. To start with, an autoencoder is adopted to convert the nominal data into a robust representation. Secondly, a Cox proportional hazard model (Cox PHM) is researched to estimate the TBF of the censored data. A long-short-term memory (LSTM) network is then established to train the TBF prediction model based on the pre-processed maintenance data. Experimental studies using a sizable real-world fleet maintenance data set provided by a UK fleet company have demonstrated the merits of the proposed approach where the algorithm performance based on the proposed LSTM network has been improved respectively in terms of MCC and RMSE.     

A supervised learning approach for heading detection

As the popularity of the portable document format (PDF) file format increases, research that facilitates PDF text analysis or extraction is necessary. Heading detection is a crucial component of PDF-based text classification processes. This research involves training a supervised learning model to detect headings by systematically testing and selecting classifier features using recursive feature elimination. Results indicate that decision tree is the best classifier with an accuracy of 95.83%, sensitivity of 0.981, and a specificity of 0.946. This research into heading detection contributes to the field of PDF-based text extraction and can be applied to the automation of large scale PDF text analysis in a variety of professional and policy-based contexts.     

Multi-label fault recognition framework using deep reinforcement learning and curriculum learning mechanism

In the actual working site, the equipment often works in different working conditions while the manufacturing system is rather complicated. However, traditional multi-label learning methods need to use the pre-defined label sequence or synchronously predict all labels of the input sample in the fault diagnosis domain. Deep reinforcement learning (DRL) combines the perception ability of deep learning and the decision-making ability of reinforcement learning. Moreover, the curriculum learning mechanism follows the learning approach of humans from easy to complex. Consequently, an improved proximal policy optimization (PPO) method, which is a typical algorithm in DRL, is proposed as a novel method on multi-label classification in this paper. The improved PPO method could build a relationship between several predicted labels of input sample because of designing an action history vector, which encodes all history actions selected by the agent at current time step. In two rolling bearing experiments, the diagnostic results demonstrate that the proposed method provides a higher accuracy than traditional multi-label methods on fault recognition under complicated working conditions. Besides, the proposed method could distinguish the multiple labels of input samples following the curriculum mechanism from easy to complex, compared with the same network using the pre-defined label sequence.     

Image fusion meets deep learning: A survey and perspective

Image fusion, which refers to extracting and then combining the most meaningful information from different source images, aims to generate a single image that is more informative and beneficial for subsequent applications. The development of deep learning has promoted tremendous progress in image fusion, and the powerful feature extraction and reconstruction capabilities of neural networks make the fused results promising. Recently, several latest deep learning technologies have made image fusion explode, e.g., generative adversarial networks, autoencoder, etc. However, a comprehensive review and analysis of latest deep-learning methods in different fusion scenarios is lacking. To this end and in this survey, we first introduce the concept of image fusion, and classify the methods from the perspectives of the deep architectures adopted and fusion scenarios. Then, we review the state-of-the-art on the use of deep learning in various types of image fusion scenarios, including the digital photography image fusion, the multi-modal image fusion and the sharpening fusion. Subsequently, the evaluation for some representative methods in specific fusion tasks are performed qualitatively and quantitatively. Moreover, we briefly introduce several typical applications of image fusion, including photography visualization, RGBT object tracking, medical diagnosis, and remote sensing monitoring. Finally, we provide the conclusion, highlight the challenges in image fusion, and look forward to potential future research directions.     

Securing social platform from misinformation using deep learning

People are easily duped by fake news and start to share it on their networks. With high frequency, fake news causes panic and forces people to engage in unethical behavior such as strikes, roadblocks, and similar actions. Thus, counterfeit news detection is highly needed to secure people from misinformation on social platforms. Filtering fake news manually from social media platforms is nearly impossible, as such an act raises security and privacy concerns for users. As a result, it is critical to assess the quality of news early on and prevent it from spreading. In this article, we propose an automated model to identify fake news at an early stage. Machine learning-based models such as Random Forest, Logistic Regression, Naïve Bayes, and K-Nearest Neighbor are used as baseline models, implemented with the features extracted using countvectorizer and tf–idf. The baseline and other existing model outcomes are compared with the proposed deep learning-based Long–Short Term Memory (LSTM) network. Experimental results show that different settings achieved an accuracy of 99.82% and outperformed the baseline and existing models.