Search

Hyper-trabeculation or non-compaction in the left ventricle of the myocardium (LVNC) is a recently classified form of cardiomyopathy. Several methods have been proposed to quantify the trabeculae accurately in the left ventricle, but there is no general agreement in the medical community to use a particular approach. In the previous work, we proposed DL-LVTQ, a deep-learning approach for left ventricular trabecular quantification based on a U-Net CNN architecture. In this work, we have extended and adapted DL-LVTQ to cope with patients with different particularities and cardiomyopathies. Patient images were taken from different scanners and hospitals. We have modified and adapted the U-Net convolutional neural network to account for the different particularities of a heterogeneous group of patients with multiple cardiomyopathies and inherited cardiomyopathies. The inclusion of new groups of patients has increased the accuracy, specificity and Kappa values while maintaining the sensitivity of the proposed method. Therefore, a better-prepared diagnosis tool is ready for various cardiomyopathies with different characteristics. Cardiologists have considered that 98.9% of the evaluated outputs are verified clinically for diagnosis. Therefore, the high precision to segment the different cardiac structures allows us to make a robust diagnostic system objective and faster, decreasing human error and time spent. [ABSTRACT FROM AUTHOR]

Hyper-trabeculation or non-compaction in the left ventricle of the myocardium (LVNC) is a recently classified form of cardiomyopathy. Several methods have been proposed to quantify the trabeculae accurately in the left ventricle, but there is no general agreement in the medical community to use a particular approach. In the previous work, we proposed DL-LVTQ, a deep-learning approach for left ventricular trabecular quantification based on a U-Net CNN architecture. In this work, we have extended and adapted DL-LVTQ to cope with patients with different particularities and cardiomyopathies. Patient images were taken from different scanners and hospitals. We have modified and adapted the U-Net convolutional neural network to account for the different particularities of a heterogeneous group of patients with multiple cardiomyopathies and inherited cardiomyopathies. The inclusion of new groups of patients has increased the accuracy, specificity and Kappa values while maintaining the sensitivity of the proposed method. Therefore, a better-prepared diagnosis tool is ready for various cardiomyopathies with different characteristics. Cardiologists have considered that 98.9% of the evaluated outputs are verified clinically for diagnosis. Therefore, the high precision to segment the different cardiac structures allows us to make a robust diagnostic system objective and faster, decreasing human error and time spent.

Sports plays a pivotal role in national development. To accurately predict college students' sports performance and motivate them to improve their physical fitness, this study constructs a sports achievement prediction system by using a U-Net Convolutional Neural Network (CNN) in machine learning. Firstly, the current state of physical education teachers’ instructional proficiency is investigated and analyzed to identify existing problems. Secondly, an improved U-Net-based sports achievement prediction system is proposed. This method enhances the utilization and propagation of network features by incorporating dense connections, thus addressing gradient disappearance issues. Simultaneously, an improved mixed loss function is introduced to alleviate class imbalance. Finally, the effectiveness of the proposed system is validated through testing, demonstrating that the improved U-Net CNN algorithm yields superior results. Specifically, the prediction accuracy of the improved network for sports performance surpasses that of the original U-Net by 4.22 % and exceeds that of DUNet by 5.22 %. Compared with other existing prediction networks, the improved U-Net CNN model exhibits a superior achievement prediction ability. Consequently, the proposed system enhances teaching and learning efficiency and offers insights into applying artificial intelligence technology to smart classroom development.

Perfusion cardiovascular magnetic resonance imaging is used to quantify the heart’s blood flow, which requires the segmentation of the myocardium, a laborious task. Deep learning-based methods, the most accurate to accomplish this task, still rely on expensive motion correction steps and require large labeled datasets. This paper presents an innovative, efficient approach to myocardial perfusion segmentation, utilizing deep learning techniques without motion correction and with minimal data requirements. Through transfer learning, this methodology leverages the wealth of information available from large, publicly accessible cine magnetic resonance datasets, which provide anatomically analogous images to perfusion ones. This methodology includes normalization and cropping of cine images using a Region-of-Interest detector based on a Markovian, graph-based visual saliency algorithm improved by a sequence of morphological operations. After pretraining a U-net convolutional neural network, a special fine-tuning scheme optimizes its performance. The parameters learned are the starting point for training on a smaller perfusion dataset from the Clinical Hospital of the University of Chile. After an ablation study, the best model is obtained when using both cropping and fine-tuning from the cine dataset, segmenting the left ventricle endocardium with Dice, IoU, and Hausdorff distance of 92.2%, 85.9%, and 5.1 mm respectively, and 95.6%, 91.7%, and 4.6 mm for the left ventricle epicardium. Notably, fine-tuning achieves a Dice of 91.8% for endocardium and 95.2% for epicardium when only 289 perfusion training images are available. These are promising results for developing targeted implementations in real healthcare settings when only small datasets are available.

In industry, metal workpieces are often heat-treated to improve their mechanical properties, which leads to unwanted deformations and changes in their geometry. Due to their high hardness (60 HRC or more), conventional bending and rolling straightening approaches are not effective, as a failure of the material occurs. The aim of the research was to develop a predictive model that predicts the change in the form of a hardened workpiece as a function of the arbitrary set of strikes that deform the surface plastically. A large-scale laboratory experiment was carried out in which a database of 3063 samples was prepared, based on the controlled application of plastic deformations on the surface of the workpiece and high-resolution capture of the workpiece geometry. The different types of input data, describing, on the one hand, the performed plastic surface deformations on the workpieces, and on the other hand the point cloud of the workpiece geometry, were combined appropriately into a form that is a suitable input for a U-Net convolutional neural network. The U-Net model's performance was investigated using three statistical indicators. These indicators were: relative absolute error (RAE), root mean squared error (RMSE), and relative squared error (RSE). The results showed that the model had excellent prediction performance, with the mean values of RMSE less than 0.013, RAE less than 0.05, and RSE less than 0.004 on test data. Based on the results, we concluded that the proposed model could be a useful tool for designing an optimal straightening strategy for high-hardness metal workpieces. Our results will open the doors to implementing digital sustainability techniques, since more efficient handling will result in fewer subsequent heat treatments and shorter handling times. An important goal of digital sustainability is to reduce electricity consumption in production, which this approach will certainly do. [ABSTRACT FROM AUTHOR]

This study proposed a spatial wave measurement method based on a U-net convolutional neural network. First, frame images are extracted from a video collected by a physical model experiment, and a dataset of spatial wave measurements is created and extended using a data enhancement method. A U-net convolutional neural network is built to extract the spatial wave information of the images; evidently, the segmented water level is close to that of the original image. Next, the U-net convolutional neural network is compared with the sensor, pixel recognition, and Canny edge detection methods. Pixel recognition results reveal that the maximum and minimum errors of the U-net convolutional neural network are 3.92% and 1.05%, those of the Canny edge detection are 5.97% and 1.33%, and those of the sensor are 11.8% and 1.6%, respectively. Finally, the nonlinear characteristic quantities of waves are measured using the proposed U-net convolutional neural network. The kurtosis and asymmetry calculated in the spatial domain are slightly larger than those calculated in the time domain, whereas the skewness calculated in the spatial domain is smaller than that calculated in the time domain. The asymmetry and kurtosis increase with an increase in wave height and period, whereas the skewness increases with an increase in wave height but decreases with an increase in period. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) have become the core of modern machine learning approaches. In addition to its inspiring interior design idea, the success of CNN depends mainly on two factors, the first is the availability of training data and the second is the computing power of the used devices. In the field of remote sensing, data availability is difficult and expensive. Furthermore, processing large remote sensing data to accommodate different models is a laborious process. At the same time, training data is often collected in the form of points distributed over crop fields rather than regions, which results in the scarcity of training data. To specifically address the scarcity of training points, in this paper we present a sparse pixel-based training of U-Net convolutional neural networks for land cover classification. Training images are reconstructed from the points’ collection in a random manner, they are used as an input for the convolution networks. Based on this proposed method, the amount of training data is reproduced from the different spectral signals for each land cover. We conducted extensive experiments on eight classes, using ground truth data collected from several locations in Fayoum Governorate, Egypt. The obtained results showed the superiority of the proposed method over other methods.

Large-scale and high-intensity mining underground coal has resulted in serious land subsidence. It has caused a lot of ecological environment problems and has a serious impact on the sustainable development of economy. Land subsidence cannot be accurately monitored by InSAR (interferometric synthetic aperture radar) due to the low coherence in the mining area, excessive deformation gradient, and the atmospheric effect. In order to solve this problem, a novel phase unwrapping method based on U-Net convolutional neural network was constructed. Firstly, the U-Net convolutional neural network is used to extract edge to automatically obtain the boundary information of the interferometric fringes in the region of subsidence basin. Secondly, an edge-linking algorithm is constructed based on edge growth and predictive search. The interrupted interferometric fringes are connected automatically. The whole and continuous edges of interferometric fringes are obtained. Finally, the correct phase unwrapping results are obtained according to the principle of phase unwrapping and the wrap-count (integer jump of 2π) at each pixel by edge detection. The Huaibei Coalfield in China was taken as the study area. The real interferograms from D-InSAR (differential interferometric synthetic aperture radar) processing used Sentinel-1A data which were used to verify the performance of the new method. Subsidence basins with clear interferometric fringes, interrupted interferometric fringes, and confused interferometric fringes are selected for experiments. The results were compared with the other methods, such as MCF (minimum cost flow) method. The tests showed that the new method based on U-Net convolutional neural network can resolve the problem that is difficult to obtain the correct unwrapping phase due to interrupted or partially confused interferometric fringes caused by low coherence or other reasons in the coal mining area. Hence, the new method can help to accurately monitor the subsidence in mining areas under different conditions using InSAR technology.

The antibiotic resistance of bacterial pathogens has become one of the most serious global health issues due to misusing and overusing of antibiotics. Recently, different technologies were developed to determine bacteria susceptibility towards antibiotics; however, each of these technologies has its advantages and limitations in clinical applications. In this contribution, we aim to assess and automate the detection of bacterial susceptibilities towards three antibiotics; i.e. ciprofloxacin, cefotaxime and piperacillin using a combination of image processing and machine learning algorithms. Therein, microscopic images were collected from different E. coli strains, then the convolutional neural network U-Net was implemented to segment the areas showing bacteria. Subsequently, the encoder part of the trained U-Net was utilized as a feature extractor, and the U-Net bottleneck features were utilized to predict the antibiotic susceptibility of E. coli strains using a one-class support vector machine (OCSVM). This one-class model was always trained on images of untreated controls of each bacterial strain while the image labels of treated bacteria were predicted as control or non-control images. If an image of treated bacteria is predicted as control, we assume that these bacteria resist this antibiotic. In contrast, the sensitive bacteria show different morphology of the control bacteria; therefore, images collected from these treated bacteria are expected to be classified as non-control. Our results showed 83% area under the receiver operating characteristic (ROC) curve when OCSVM models were built using the U-Net bottleneck features of control bacteria images only. Additionally, the mean sensitivities of these one-class models are 91.67% and 86.61% for cefotaxime and piperacillin; respectively. The mean sensitivity for the prediction of ciprofloxacin is only 59.72% as the bacteria morphology was not fully detected by the proposed method.

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.

The satellite remote-sensing-based damage-mapping technique has played an indispensable role in rapid disaster response practice, whereas the current disaster response practice remains subject to the low damage assessment accuracy and lag in timeliness, which dramatically reduces the significance and feasibility of extending the present method to practical operational applications. Therefore, a highly efficient and intelligent remote-sensing image-processing framework is urgently required to mitigate these challenges. In this article, a deep learning algorithm for the semantic segmentation of high-resolution remote-sensing images using the U-net convolutional network was proposed to map the damage rapidly. The algorithm was implemented within a Microsoft Cognitive Toolkit framework in the GeoAI platform provided by Microsoft. The study takes the 2011 Tohoku Earthquake-Tsunami as a case study, for which the pre- and post-disaster high-resolution WorldView-2 image is used. The performance of the proposed U-net model is compared with that of deep residual U-net. The comparison highlights the superiority U-net for tsunami damage mapping in this work. Our proposed method achieves the overall accuracy of 70.9% in classifying the damage into “washed away,” “collapsed,” and “survived” at the pixel level. In future disaster scenarios, our proposed model can generate the damage map in approximately 2–15 min when the preprocessed remote-sensing datasets are available. Our proposed damage-mapping framework has significantly improved the application value in operational disaster response practice by substantially reducing the manual operation steps required in the actual disaster response. Besides, the proposed framework is highly flexible to extend to other scenarios and various disaster types, which can accelerate operational disaster response practice.

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models' performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery. [ABSTRACT FROM AUTHOR]