Search

Applying deep learning, especially time series neural networks, to predict stock price, has become one of the important applications in quantitative finance. Recently, some GAN-based stock prediction models are proposed, where LSTM or GRU is used as the generator. However, these generators lack the function of feature extraction, and the prediction accuracies are slightly low. Meanwhile, these models choose some simple volume-price factors (such as OCHLV and OCHLVC) as inputs, without considering the impact of other factors on stock prices. In order to solve these problems, a stock prediction method based on multiple factors and GAN-TrellisNet is proposed. Instead of "OCHLV" or "OCHLVC," a multi-factor strategy with "alpha158+OCHLVC" is introduced to enrich the stock data of inputs. The proposed generative adversarial network (GAN) is a combination of two neural networks which are TrellisNet as generative model and convolutional neural network (CNN) as discriminative model for adversarial training to forecast the stock market. TrellisNet, which integrates the feature extraction capabilities of CNN and the temporal processing capabilities of recurrent neural network (RNN), will generate new predicted results based on historical data, and then CNN will distinguish between predicted results and real stock prices. In order to demonstrate the performance of our method, we selected the decade data of different stocks from four markets (A-shares, U.S. stocks, U.K. stocks and Hong Kong stocks) as dataset and conducted two groups of comparative experiments. Compared with the state-of-the-art methods based on GAN, our method has better performance in terms of MSE, MAE, RMSE and MAPE. In addition, the multi-factor strategy with "alpha158+OCHLVC" is more effective than the original strategy with OCHLVC factors. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole‐slide images (WSIs) is a very time‐consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep‐learning (DL)‐based method for automatic curation of large pathology datasets with several slides per patient. Methods: We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry‐stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro‐averaged area under the receiver operating curve (AUROCs) for detection of the type of slide. Results: In the primary dataset (FOXTROT), with an AUROC of 0.995 [95% confidence interval [CI]: 0.994–0.996] the algorithm achieved a high classification performance and was able to accurately predict the type of slide from the thumbnail image alone. In the two external test cohorts (CR07, DACHS) AUROCs of 0.982 [95% CI: 0.979–0.985] and 0.875 [95% CI: 0.864–0.887] were observed, which indicates the generalizability of the trained model on unseen datasets. With a confidence threshold of 0.95, the model reached an accuracy of 94.6% (7331 classified cases) in CR07 and 85.1% (2752 classified cases) for the DACHS cohort. Conclusion: Our findings show that using the low‐resolution thumbnail image is sufficient to accurately classify the type of slide in digital pathology. This can support researchers to make the vast resource of existing pathology archives accessible to modern AI models with only minimal manual annotations. [ABSTRACT FROM AUTHOR]

Predicting the status of train delays, a complex and dynamic problem, is crucial for railway enterprises and passengers. This paper proposes a novel hybrid deep learning model composed of convolutional neural networks (CNN) and temporal convolutional networks (TCN), named the CNN + TCN model, for predicting train delays in railway systems. First, we construct 3D data containing the spatiotemporal characteristics of real-world train data. Then, the CNN + TCN model employs a 3D CNN component, which is fed into the constructed 3D data to mine the spatiotemporal characteristics, and a TCN component that captures the temporal characteristics in railway operation data. Furthermore, the characteristic variables corresponding to the two components are selected. Finally, the model is evaluated by leveraging data from two railway lines in the United Kingdom. Numerical results show that the CNN + TCN model has greater accuracy and convergence performance in train delay prediction. [ABSTRACT FROM AUTHOR]

Highway safety researchers focus on crash injury severity, utilizing deep learning--specifically, deep neural networks (DNN), deep convolutional neural networks (D-CNN), and deep recurrent neural networks (D-RNN)--as the preferred method for modeling accident severity. Deep learning's strength lies in handling intricate relationships within extensive datasets, making it popular for accident severity level (ASL) prediction and classification. Despite prior success, there is a need for an efficient system recognizing ASL in diverse road conditions. To address this, we present an innovative Accident Severity Level Prediction Deep Learning (ASLP-DL) framework, incorporating DNN, D-CNN, and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent. The framework optimizes hidden layers and integrates data augmentation, Gaussian noise, and dropout regularization for improved generalization. Sensitivity and factor contribution analyses identify influential predictors. Evaluated on three diverse crash record databases--NCDB 2018-2019, UK 2015-2020, and US 2016-2021--the D-RNN model excels with an ACC score of 89.0281%, a Roc Area of 0.751, an F-estimate of 0.941, and a Kappa score of 0.0629 over the NCDB dataset. The proposed framework consistently outperforms traditional methods, existing machine learning, and deep learning techniques. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the deadly cancer types that causes high mortality among women globally. Meanwhile, Deep Learning (DL) emerges as the most frequently utilized and rapidly developing branch of classical machine learning. The study examines a modern Computer-Aided Diagnosis (CAD) framework that uses DL to extract features and classify them for aiding radiologists in breast cancer diagnosis. This is accomplished through four distinct experimentations aimed at identifying the most optimal method of effective classification. Here, the first uses Deep CNNs that are pre-trained, such as AlexNet, GoogleNet, ResNet50, and Dense-Net121. The second is based on experiments using Deep CNNs to extract features and applying them onto a Support Vector Machine algorithm using three different kernels. The next one involves the fusion of different deep features for demonstrating the classification improvement by fusion of these deep features. The final experiment involves Principal Component Analysis (PCA) for reducing the computational cost and for decreasing the larger feature vectors created during fusion. The abovesaid experimentations are carried out in two different mammogram datasets namely MIAS and INbreast. The classification accuracy attained for both datasets through the fuzing of deep features (97.93% for MIAS and 96.646% for INbreast) is the highest compared with the state-of-the-art frameworks. In contrast, the classification performance did not enhance while applying the PCA on combined deep features; but the decrease in execution time provides a reduced computational cost. Abbreviations: CAD: Computer Aided Diagnosis; CNN: Convolution Neural Network; CSI: Classification Success Index; DCNN: Deep Convolution Neural Network; DICOM: Digital Imaging and Communications in Medicine; DL: Deep Learning; FC layer: Fully Connected layer; FFDM: Full-Field Digital Mammograms; FN: False Negative; FP: False Positive; ICSI: Individual Classification Success Index; MIAS: Mammographic Image Analysis Society; ML: Machine Learning; MLO: Medio-Lateral Oblique; PCA: Principal Component Analysis; PGM: Portable Gray Map; PPV: Positive Predictive Value; RBF: Radial Basis Function; SGDM: Stochastic Gradient Descent with Momentum; SVM: Support Vector Machine; TN: True Negative; TP: True Positive; TPR: True Positive Rate; UK: United Kingdom [ABSTRACT FROM AUTHOR]

Breast cancer claims 11,400 lives on average every year in the UK, making it one of the deadliest diseases. Mammography is the gold standard for detecting early signs of breast cancer, which can help cure the disease during its early stages. However, incorrect mammography diagnoses are common and may harm patients through unnecessary treatments and operations (or a lack of treatment). Therefore, systems that can learn to detect breast cancer on their own could help reduce the number of incorrect interpretations and missed cases. Various deep learning techniques, which can be used to implement a system that learns how to detect instances of breast cancer in mammograms, are explored throughout this paper. Convolution Neural Networks (CNNs) are used as part of a pipeline based on deep learning techniques. A divide and conquer approach is followed to analyse the effects on performance and efficiency when utilising diverse deep learning techniques such as varying network architectures (VGG19, ResNet50, InceptionV3, DenseNet121, MobileNetV2), class weights, input sizes, image ratios, pre-processing techniques, transfer learning, dropout rates, and types of mammogram projections. This approach serves as a starting point for model development of mammography classification tasks. Practitioners can benefit from this work by using the divide and conquer results to select the most suitable deep learning techniques for their case out-of-the-box, thus reducing the need for extensive exploratory experimentation. Multiple techniques are found to provide accuracy gains relative to a general baseline (VGG19 model using uncropped 512 × 512 pixels input images with a dropout rate of 0.2 and a learning rate of 1 × 10−3) on the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) dataset. These techniques involve transfer learning pre-trained ImagetNet weights to a MobileNetV2 architecture, with pre-trained weights from a binarised version of the mini Mammography Image Analysis Society (mini-MIAS) dataset applied to the fully connected layers of the model, coupled with using weights to alleviate class imbalance, and splitting CBIS-DDSM samples between images of masses and calcifications. Using these techniques, a 5.6% gain in accuracy over the baseline model was accomplished. Other deep learning techniques from the divide and conquer approach, such as larger image sizes, do not yield increased accuracies without the use of image pre-processing techniques such as Gaussian filtering, histogram equalisation and input cropping. [ABSTRACT FROM AUTHOR]

An ongoing outbreak of monkeypox virus (MPXV) was first reported in the United Kingdom on 6 May 2022. As of 17 November, there had been a total of 80 221 confirmed MPXV cases in over 110 countries. Based on data reported between 6 May and 30 June 2022 in the United Kingdom, Spain, and Germany, we applied a deep learning approach using convolutional neural networks to evaluate the parameters of the 2022 MPXV outbreak. The basic reproduction number (R0) of MPXV was estimated to be 2.32 in the United Kingdom, which indicates the active diffusion of MPXV since the beginning of the outbreak. The data from Spain and Germany produced higher median R0 values of 2.42 and 2.88, respectively. Importantly, the estimated R0 of MPXV in the three countries tends to the previously calculated R0 of smallpox (3.50 to 6.00). Furthermore, the incubation (1/ε) and infectious (1/γ) period was predicted between 9 and 10 days and 4−5 days, respectively. The R0 value derived from MPXV is consistent with the significantly increasing number of cases, indicating the risk of a rapid spread of MPXV worldwide, which would provide important insights for the prevention and control of MPXV epidemic. [ABSTRACT FROM AUTHOR]

We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By using the differentiable properties of persistent homology, a concept used in topological data analysis, we can specify the desired topology of segmented objects in terms of their Betti numbers and then drive the proposed segmentations to contain the specified topological features. Importantly this process does not require any ground-truth labels, just prior knowledge of the topology of the structure being segmented. We demonstrate our approach in four experiments: one on MNIST image denoising and digit recognition, one on left ventricular myocardium segmentation from magnetic resonance imaging data from the UK Biobank, one on the ACDC public challenge dataset and one on placenta segmentation from 3-D ultrasound. We find that embedding explicit prior knowledge in neural network segmentation tasks is most beneficial when the segmentation task is especially challenging and that it can be used in either a semi-supervised or post-processing context to extract a useful training gradient from images without pixelwise labels. [ABSTRACT FROM AUTHOR]

Accurate daily rainfall predictions are becoming increasingly important, particularly in the era of changing climate conditions. These predictions are essential for various sectors, including agriculture, water resource management, flood preparedness, and pollution monitoring. This study delves into the complex relationship between meteorological data, with a focus on the accurate forecasting of rainfall by identifying the impact of temperature variations on rainfall patterns in different regions of the United Kingdom (UK). The meteorological data was collected from the National Aeronautics and Space Administration (NASA) and covers daily observations from January 1, 1981, to July 31, 2023, in four distinct regions of the UK: England, Wales, Scotland, and Northern Ireland. The main objective of this research is to introduce hybrid deep learning models, namely Convolutional Neural Networks (CNN) with Long Short Term Memory (LSTM) and Recurrent Neural Networks (RNN) with Long Short Term Memory (LSTM), for predicting daily rainfall using time-series data from the four UK countries, specifically designed for daily rainfall forecasting of four regions in the UK. The models are fine-tuned using the hyperparameter optimisation method. Comprehensive performance evaluations, including Loss Function, Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), are employed to compare the effectiveness of our proposed hybrid models with established baseline models, including LSTM, stacked LSTM, and Bidirectional LSTM. Additionally, a visual analysis of actual and predicted rainfall data is conducted to identify the most proficient forecasting model for each region. Results reveal that the proposed hybrid models consistently outperform other models in terms of both quantitative performance metrics and visual assessments across all four regions in the UK. This research contributes to improved rainfall forecasting methodologies, which are critical for sustainable agricultural practices and resource management. [ABSTRACT FROM AUTHOR]

Recent research shows prominent effects of pregnancy and the parenthood transition on structural brain characteristics in humans. Here, we present a comprehensive study of how parental status and number of children born/fathered links to markers of brain and cellular ageing in 36,323 UK Biobank participants (age range 44.57–82.06 years; 52% female). To assess global effects of parenting on the brain, we trained a 3D convolutional neural network on T1-weighted magnetic resonance images, and estimated brain age in a held-out test set. To investigate regional specificity, we extracted cortical and subcortical volumes using FreeSurfer, and ran hierarchical clustering to group regional volumes based on covariance. Leukocyte telomere length (LTL) derived from DNA was used as a marker of cellular ageing. We employed linear regression models to assess relationships between number of children, brain age, regional brain volumes, and LTL, and included interaction terms to probe sex differences in associations. Lastly, we used the brain measures and LTL as features in binary classification models, to determine if markers of brain and cellular ageing could predict parental status. The results showed associations between a greater number of children born/fathered and younger brain age in both females and males, with stronger effects observed in females. Volume-based analyses showed maternal effects in striatal and limbic regions, which were not evident in fathers. We found no evidence for associations between number of children and LTL. Classification of parental status showed an Area under the ROC Curve (AUC) of 0.57 for the brain age model, while the models using regional brain volumes and LTL as predictors showed AUCs of 0.52. Our findings align with previous population-based studies of middle- and older-aged parents, revealing subtle but significant associations between parental experience and neuroimaging-based surrogate markers of brain health. The findings further corroborate results from longitudinal cohort studies following parents across pregnancy and postpartum, potentially indicating that the parenthood transition is associated with long-term influences on brain health. • Reproductive history is linked to brain age in UK Biobank males and females. • Effects in striatal and limbic regions were evident in mothers only. • No significant link between number of children and leukocyte telomere length. • Findings might indicate long-term brain health impacts of the parenthood transition. [ABSTRACT FROM AUTHOR]

Deep learning has recently achieved best-in-class performance in several fields, including biomedical domains such as X-ray images. Yet, data scarcity poses a strict limit on training successful deep learning systems in many, if not most, biomedical applications, including those involving brain images. In this study, we translate state-of-the-art transfer learning techniques for single-subject prediction of simpler (sex and age) and more complex phenotypes (number of people in household, household income, fluid intelligence and smoking behavior). We fine-tuned 2D and 3D ResNet-18 convolutional neural networks for target phenotype predictions from brain images of ∼ 40,000 UK Biobank participants, after pretraining on YouTube videos from the Kinetics dataset and natural images from the ImageNet dataset. Transfer learning was effective on several phenotypes, especially sex and age classification. Additionally, transfer learning in particular outperformed deep learning models trained from scratch especially on smaller sample sizes. The out-of-sample performance using transfer learning from previously learned knowledge based on real-world images and videos could unlock the potential in many areas of imaging neuroscience where deep learning solutions are currently infeasible. • Neuroimaging faces challenges in effectively training DNNs due to data scarcity. • Transfer learning (TL) could aid in training DNNs in the data-scarce neuroimaging setting. • Using TL, we improved predictions on several phenotypes and smaller sample sizes. [ABSTRACT FROM AUTHOR]

• Individuals remain poorly predictable from population-level analyses of the brain. • The fidelity limits data scale, compute, and model flexibility impose are unknown. • We quantify these limits in multimodal, multitarget analyses across 23810 people. • We show a radical change in modelling regimes is needed for individual prediction. Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal. Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging. We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05). Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available. [ABSTRACT FROM AUTHOR]

Background: The microvasculature, the smallest blood vessels in the body, has key roles in maintenance of organ health and tumorigenesis. The retinal fundus is a window for human in vivo noninvasive assessment of the microvasculature. Large-scale complementary machine learning-based assessment of the retinal vasculature with phenome-wide and genome-wide analyses may yield new insights into human health and disease.Methods: We used 97 895 retinal fundus images from 54 813 UK Biobank participants. Using convolutional neural networks to segment the retinal microvasculature, we calculated vascular density and fractal dimension as a measure of vascular branching complexity. We associated these indices with 1866 incident International Classification of Diseases-based conditions (median 10-year follow-up) and 88 quantitative traits, adjusting for age, sex, smoking status, and ethnicity.Results: Low retinal vascular fractal dimension and density were significantly associated with higher risks for incident mortality, hypertension, congestive heart failure, renal failure, type 2 diabetes, sleep apnea, anemia, and multiple ocular conditions, as well as corresponding quantitative traits. Genome-wide association of vascular fractal dimension and density identified 7 and 13 novel loci, respectively, that were enriched for pathways linked to angiogenesis (eg, vascular endothelial growth factor, platelet-derived growth factor receptor, angiopoietin, and WNT signaling pathways) and inflammation (eg, interleukin, cytokine signaling).Conclusions: Our results indicate that the retinal vasculature may serve as a biomarker for future cardiometabolic and ocular disease and provide insights into genes and biological pathways influencing microvascular indices. Moreover, such a framework highlights how deep learning of images can quantify an interpretable phenotype for integration with electronic health record, biomarker, and genetic data to inform risk prediction and risk modification. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs)—as a type of deep learning—have been specifically designed for highly heterogeneous data, such as natural images. Neuroimaging data, however, is comparably homogeneous due to (1) the uniform structure of the brain and (2) additional efforts to spatially normalize the data to a standard template using linear and non-linear transformations. To harness spatial homogeneity of neuroimaging data, we suggest here a new CNN architecture that combines the idea of hierarchical abstraction in CNNs with a prior on the spatial homogeneity of neuroimaging data. Whereas early layers are trained globally using standard convolutional layers, we introduce patch individual filters (PIF) for higher, more abstract layers. By learning filters in individual latent space patches without sharing weights, PIF layers can learn abstract features faster and specific to regions. We thoroughly evaluated PIF layers for three different tasks and data sets, namely sex classification on UK Biobank data, Alzheimer's disease detection on ADNI data and multiple sclerosis detection on private hospital data, and compared it with two baseline models, a standard CNN and a patch-based CNN. We obtained two main results: First, CNNs using PIF layers converge consistently faster, measured in run time in seconds and number of iterations than both baseline models. Second, both the standard CNN and the PIF model outperformed the patch-based CNN in terms of balanced accuracy and receiver operating characteristic area under the curve (ROC AUC) with a maximal balanced accuracy (ROC AUC) of 94.21% (99.10%) for the sex classification task (PIF model), and 81.24% and 80.48% (88.89% and 87.35%) respectively for the Alzheimer's disease and multiple sclerosis detection tasks (standard CNN model). In conclusion, we demonstrated that CNNs using PIF layers result in faster convergence while obtaining the same predictive performance as a standard CNN. To the best of our knowledge, this is the first study that introduces a prior in form of an inductive bias to harness spatial homogeneity of neuroimaging data. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the performance of a novel convolutional neural network (CNN) for the classification of typical perifissural nodules (PFN).Methods: Chest CT data from two centers in the UK and The Netherlands (1668 unique nodules, 1260 individuals) were collected. Pulmonary nodules were classified into subtypes, including "typical PFNs" on-site, and were reviewed by a central clinician. The dataset was divided into a training/cross-validation set of 1557 nodules (1103 individuals) and a test set of 196 nodules (158 individuals). For the test set, three radiologically trained readers classified the nodules into three nodule categories: typical PFN, atypical PFN, and non-PFN. The consensus of the three readers was used as reference to evaluate the performance of the PFN-CNN. Typical PFNs were considered as positive results, and atypical PFNs and non-PFNs were grouped as negative results. PFN-CNN performance was evaluated using the ROC curve, confusion matrix, and Cohen's kappa.Results: Internal validation yielded a mean AUC of 91.9% (95% CI 90.6-92.9) with 78.7% sensitivity and 90.4% specificity. For the test set, the reader consensus rated 45/196 (23%) of nodules as typical PFN. The classifier-reader agreement (k = 0.62-0.75) was similar to the inter-reader agreement (k = 0.64-0.79). Area under the ROC curve was 95.8% (95% CI 93.3-98.4), with a sensitivity of 95.6% (95% CI 84.9-99.5), and specificity of 88.1% (95% CI 81.8-92.8).Conclusion: The PFN-CNN showed excellent performance in classifying typical PFNs. Its agreement with radiologically trained readers is within the range of inter-reader agreement. Thus, the CNN-based system has potential in clinical and screening settings to rule out perifissural nodules and increase reader efficiency.Key Points: • Agreement between the PFN-CNN and radiologically trained readers is within the range of inter-reader agreement. • The CNN model for the classification of typical PFNs achieved an AUC of 95.8% (95% CI 93.3-98.4) with 95.6% (95% CI 84.9-99.5) sensitivity and 88.1% (95% CI 81.8-92.8) specificity compared to the consensus of three readers. [ABSTRACT FROM AUTHOR]

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information to a broad range of nonexpert stakeholders a challenge. Here, we explore the applicability of deep learning approaches by adapting a pretrained convolutional neural network (CNN) to detect deformation in a national-scale velocity field. For our proof-of-concept, we focus on the U.K. where previously identified deformation is associated with coal-mining, ground water withdrawal, landslides, and tunneling. The sparsity of measurement points and the presence of spike noise make this a challenging application for deep learning networks, which involve calculations of the spatial convolution between images. Moreover, insufficient ground truth data exist to construct a balanced training data set, and the deformation signals are slower and more localized than in previous applications. We propose three enhancement methods to tackle these problems: 1) spatial interpolation with modified matrix completion; 2) a synthetic training data set based on the characteristics of the real U.K. velocity map; and 3) enhanced overwrapping techniques. Using velocity maps spanning 2015–2019, our framework detects several areas of coal mining subsidence, uplift due to dewatering, slate quarries, landslides, and tunnel engineering works. The results demonstrate the potential applicability of the proposed framework to the development of automated ground motion analysis systems. [ABSTRACT FROM AUTHOR]

Convolutional neural networks typically consist of many convolutional layers followed by one or more fully connected layers. While convolutional layers map between high-order activation tensors, the fully connected layers operate on attened activation vectors. Despite empirical success, this approach has notable drawbacks. Flattening followed by fully connected layers discards multilinear structure in the activations and requires many parameters. We address these problems by incorporating tensor algebraic operations that preserve multilinear structure at every layer. First, we introduce Tensor Contraction Layers (TCLs) that reduce the dimensionality of their input while preserving their multilinear structure using tensor contraction. Next, we introduce Tensor Regression Layers (TRLs), which express outputs through a low-rank multilinear mapping from a high-order activation tensor to an output tensor of arbitrary order. We learn the contraction and regression factors end-to-end, and produce accurate nets with fewer parameters. Additionally, our layers regularize networks by imposing low-rank constraints on the activations (TCL) and regression weights (TRL). Experiments on ImageNet show that, applied to VGG and ResNet architectures, TCLs and TRLs reduce the number of parameters compared to fully connected layers by more than 65% while maintaining or increasing accuracy. In addition to the space savings, our approach's ability to leverage topological structure can be crucial for structured data such as MRI. In particular, we demonstrate significant performance improvements over comparable architectures on three tasks associated with the UK Biobank dataset. [ABSTRACT FROM AUTHOR]

• A framework for LRV detection, segmentation in large CMR studies. • Automatic initialization of bi-ventricles for the first time frame without any user intervention. • Automatic End-diastole and End-systole phase assessments. • Supervised deep neural network employed to train and segment the heart. • 3D-ASM image search procedure improved by combining image intensity models with derived distance maps for LV and RV edge localization. The sheer volume of data generated by population imaging studies is unparalleled by current capabilities to extract objective and quantitative cardiac phenotypes; subjective and time-consuming manual image analysis remains the gold standard. Automated image analytics to compute quantitative imaging biomarkers of cardiac function are desperately needed. Data volumes and their variability pose a challenge to most state-of-the-art methods for endo- and epicardial contours, which lack robustness when applied to very large datasets. Our aim is to develop an analysis pipeline for the automatic quantification of cardiac function from cine magnetic resonance imaging data. This work adopt 4,638 cardiac MRI cases coming from UK Biobank with ground truth available for left and RV contours. A hybrid and robust algorithm is proposed to improve the accuracy of automatic left and right ventricle segmentation by harnessing the localization accuracy of deep learning and the morphological accuracy of 3D-ASM (three-dimensional active shape models). The contributions of this paper are three-fold. First, a fully automatic method is proposed for left and right ventricle initialization and cardiac MRI segmentation by taking full advantage of spatiotemporal constraint. Second, a deeply supervised network is introduced to train and segment the heart. Third, the 3D-ASM image search procedure is improved by combining image intensity models with convolutional neural network (CNN) derived distance maps improving endo- and epicardial edge localization. The proposed architecture outperformed the state of the art for cardiac MRI segmentation from UK Biobank. The statistics of RV landmarks detection errors for Triscuspid valve and RV apex are 4.17 mm and 5.58 mm separately. The overlap metric, mean contour distance, Hausdorff distance and cardiac functional parameters are calculated for the LV (Left Ventricle) and RV (Right Ventricle) contour segmentation. Bland–Altman analysis for clinical parameters shows that the results from our automated image analysis pipelines are in good agreement with results from expert manual analysis. Our hybrid scheme combines deep learning and statistical shape modeling for automatic segmentation of the LV/RV from cardiac MRI datasets is effective and robust and can compute cardiac functional indexes from population imaging. [ABSTRACT FROM AUTHOR]

Robust and reliable automatic building detection and segmentation from aerial images/point clouds has been a prominent field of research in remote sensing, computer vision and point cloud processing for a number of decades. One of the largest issues associated with deep learning methods is the high quantity of data required for training. To help address this we present a method to improve public GIS building footprint labels by using Morphological Geodesic Active Contours (MorphGACs). We demonstrate by improving the quality of building footprint labels for detection and semantic segmentation, more robust and reliable models can be obtained. We evaluate these methods over a large UK-based dataset of 24556 images containing 169835 building instances. This is achieved by training several Mask/Faster R-CNN and RetinaNet deep convolutional neural networks. Networks are supplied with both RGB and fused RGB-lidar data. We offer quantitative analysis on the benefits of the inclusion of depth data for building segmentation. By employing both methods we achieve a detection accuracy of 0.92 (mAP@0.5) and segmentation f1 scores of 0.94 over a 4911 test images ranging from urban to rural scenes. [ABSTRACT FROM AUTHOR]

• An algorithm to automatically detect motion artefacts in cardiac MR short axis images. • Use of k-space corruption to generate realistic motion artefacts to address data imbalance. • Training of a spatio-temporal convolutional neural network using curriculum learning. • Detailed comparison against a range of machine learning methods. • An area under ROC curve of 0.89 is achieved. Good quality of medical images is a prerequisite for the success of subsequent image analysis pipelines. Quality assessment of medical images is therefore an essential activity and for large population studies such as the UK Biobank (UKBB), manual identification of artefacts such as those caused by unanticipated motion is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) cine images. We compare two deep learning architectures to classify poor quality CMR images: 1) 3D spatio-temporal Convolutional Neural Networks (3D-CNN), 2) Long-term Recurrent Convolutional Network (LRCN). Though in real clinical setup motion artefacts are common, high-quality imaging of UKBB, which comprises cross-sectional population data of volunteers who do not necessarily have health problems creates a highly imbalanced classification problem. Due to the high number of good quality images compared to the relatively low number of images with motion artefacts, we propose a novel data augmentation scheme based on synthetic artefact creation in k-space. We also investigate a learning approach using a predetermined curriculum based on synthetic artefact severity. We evaluate our pipeline on a subset of the UK Biobank data set consisting of 3510 CMR images. The LRCN architecture outperformed the 3D-CNN architecture and was able to detect 2D+time short axis images with motion artefacts in less than 1ms with high recall. We compare our approach to a range of state-of-the-art quality assessment methods. The novel data augmentation and curriculum learning approaches both improved classification performance achieving overall area under the ROC curve of 0.89. [ABSTRACT FROM AUTHOR]

Grasslands are increasingly modified by anthropogenic activities, and species-rich grasslands have become rare habitats in the UK. However, grassy roadside verges often contain conservation priority plant species that should be targeted for protection. Identification of verges with high conservation potential represents a considerable challenge for ecologists, driving the development of automated methods to make up for the shortfall of relevant expertise nationally. Using survey data from 3900 km of roadside verges alongside publicly available street-view imagery, we present DeepVerge : a deep learning-based method that can automatically survey sections of roadside verge based on the presence of positive indicator species. Using images and ground truth survey data from the rural UK county of Lincolnshire, DeepVerge achieved a mean accuracy of 88% and a mean F 1 score of 0.82 based on a five-fold cross-validation. We argue that with suitable locale-specific fine-tuning, such a method may be used by local authorities to identify new local wildlife sites, and aid management and environmental planning in line with legal and government policy obligations. • A system for remote surveying of UK roadside verges was developed. • Street-view imagery was used to train a deep learning classifier. • The model can identify roadside verges with high conservation potential. • The automated system reduces the need for manual field surveys. [ABSTRACT FROM AUTHOR]

• T1w images synthesized from diffusion data using CNNs exhibit high quality. • Resultant volumetric segmentation and cortical surfaces are accurate for various diffusion analyses. • U-Net produces higher segmentation accuracy than GAN. • U-Net is generalizable to datasets with different spatial resolution and b-value and can be improved by fine-tuning. • Synthesized T1w images improve co-registration between diffusion images with geometric distortion and T1w data. Diffusion MRI is a useful neuroimaging tool for non-invasive mapping of human brain microstructure and structural connections. The analysis of diffusion MRI data often requires brain segmentation, including volumetric segmentation and cerebral cortical surfaces, from additional high-resolution T 1 -weighted (T1w) anatomical MRI data, which may be unacquired, corrupted by subject motion or hardware failure, or cannot be accurately co-registered to the diffusion data that are not corrected for susceptibility-induced geometric distortion. To address these challenges, this study proposes to synthesize high-quality T1w anatomical images directly from diffusion data using convolutional neural networks (CNNs) (entitled "DeepAnat"), including a U-Net and a hybrid generative adversarial network (GAN), and perform brain segmentation on synthesized T1w images or assist the co-registration using synthesized T1w images. The quantitative and systematic evaluations using data of 60 young subjects provided by the Human Connectome Project (HCP) show that the synthesized T1w images and results for brain segmentation and comprehensive diffusion analysis tasks are highly similar to those from native T1w data. The brain segmentation accuracy is slightly higher for the U-Net than the GAN. The efficacy of DeepAnat is further validated on a larger dataset of 300 more elderly subjects provided by the UK Biobank. Moreover, the U-Nets trained and validated on the HCP and UK Biobank data are shown to be highly generalizable to the diffusion data from Massachusetts General Hospital Connectome Diffusion Microstructure Dataset (MGH CDMD) acquired with different hardware systems and imaging protocols and therefore can be used directly without retraining or with fine-tuning for further improved performance. Finally, it is quantitatively demonstrated that the alignment between native T1w images and diffusion images uncorrected for geometric distortion assisted by synthesized T1w images substantially improves upon that by directly co-registering the diffusion and T1w images using the data of 20 subjects from MGH CDMD. In summary, our study demonstrates the benefits and practical feasibility of DeepAnat for assisting various diffusion MRI data analyses and supports its use in neuroscientific applications. [Display omitted] [ABSTRACT FROM AUTHOR]

• In this work, we embed a statistical shape model inside a convolutional neural network and leverage both phenotypic and demographic information from the cohort to infer subject-specific reconstructions of all four cardiac chambers in 3D • To the best of our knowledge, this is the first work that uses such an approach for patient-specific cardiac shape generation • Cardiac MR images from the UK Biobank were used to train and validate the proposed method. We also present the results from analysing 40,000 subjects of the UK Biobank at 50 time-frames, in total two million image volumes • Our model can generate more globally consistent heart shape than that of manual annotations in the presence of inter-slice motion and shows strong agreement with the reference ranges for cardiac structure and function across cardiac ventricles and atria [Display omitted] Accurate 3D modelling of cardiac chambers is essential for clinical assessment of cardiac volume and function, including structural, and motion analysis. Furthermore, to study the correlation between cardiac morphology and other patient information within a large population, it is necessary to automatically generate cardiac mesh models of each subject within the population. In this study, we introduce MCSI-Net (Multi-Cue Shape Inference Network), where we embed a statistical shape model inside a convolutional neural network and leverage both phenotypic and demographic information from the cohort to infer subject-specific reconstructions of all four cardiac chambers in 3D. In this way, we leverage the ability of the network to learn the appearance of cardiac chambers in cine cardiac magnetic resonance (CMR) images, and generate plausible 3D cardiac shapes, by constraining the prediction using a shape prior, in the form of the statistical modes of shape variation learned a priori from a subset of the population. This, in turn, enables the network to generalise to samples across the entire population. To the best of our knowledge, this is the first work that uses such an approach for patient-specific cardiac shape generation. MCSI-Net is capable of producing accurate 3D shapes using just a fraction (about 23% to 46%) of the available image data, which is of significant importance to the community as it supports the acceleration of CMR scan acquisitions. Cardiac MR images from the UK Biobank were used to train and validate the proposed method. We also present the results from analysing 40,000 subjects of the UK Biobank at 50 time-frames, totalling two million image volumes. Our model can generate more globally consistent heart shape than that of manual annotations in the presence of inter-slice motion and shows strong agreement with the reference ranges for cardiac structure and function across cardiac ventricles and atria. [ABSTRACT FROM AUTHOR]

• Delays in radiological reporting can result in poorer patient outcomes and inflated healthcare costs. To reduce reporting times for abnormal scans, we present a deep learning framework for detecting clinically-relevant abnormalities in minimally processed, hospital-grade axial T2-weighted and axial diffusion-weighted head MRI scans. • The models were trained at scale using a Transformer-based neuroradiology report classifier to generate a labelled dataset of > 70,000 examinations from two large UK hospital networks, and demonstrate fast, accurate, and interpretable classification, with good generalisability between hospitals. • Through a simulation study we show that our best model would considerably reduce the mean reporting time for abnormal examinations at the two hospital networks, demonstrating feasibility for use in a clinical triage environment. The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans in recent years. For many neurological conditions, this delay can result in poorer patient outcomes and inflated healthcare costs. Potentially, computer vision models could help reduce reporting times for abnormal examinations by flagging abnormalities at the time of imaging, allowing radiology departments to prioritise limited resources into reporting these scans first. To date, however, the difficulty of obtaining large, clinically-representative labelled datasets has been a bottleneck to model development. In this work, we present a deep learning framework, based on convolutional neural networks, for detecting clinically-relevant abnormalities in minimally processed, hospital-grade axial T2-weighted and axial diffusion-weighted head MRI scans. The models were trained at scale using a Transformer-based neuroradiology report classifier to generate a labelled dataset of 70,206 examinations from two large UK hospital networks, and demonstrate fast (< 5 s), accurate (area under the receiver operating characteristic curve (AUC) > 0.9), and interpretable classification, with good generalisability between hospitals (ΔAUC ≤ 0.02). Through a simulation study we show that our best model would reduce the mean reporting time for abnormal examinations from 28 days to 14 days and from 9 days to 5 days at the two hospital networks, demonstrating feasibility for use in a clinical triage environment. [Display omitted] [ABSTRACT FROM AUTHOR]

Multisource energy data, including from distributed energy resources and its multivariate nature, necessitate the integration of robust data predictive frameworks to minimise prediction error. This work presents a hybrid deep learning framework to accurately predict the energy consumption of different building types, both commercial and domestic, spanning different countries, including Canada and the UK. Specifically, we propose architectures comprising convolutional neural network (CNN), an autoencoder (AE) with bidirectional long short-term memory (LSTM), and bidirectional LSTM BLSTM). The CNN layer extracts important features from the dataset and the AE-BLSTM and LSTM layers are used for prediction. We use the individual household electric power consumption dataset from the University of California, Irvine to compare the skillfulness of the proposed framework to the state-of-the-art frameworks. Results show performance improvement in computation time of 56% and 75.2%, and mean squared error (MSE) of 80% and 98.7% in comparison with a CNN BLSTM-based framework (EECP-CBL) and vanilla LSTM, respectively. In addition, we use various datasets from Canada and the UK to further validate the generalisation ability of the proposed framework to underfitting and overfitting, which was tested on real consumers' smart boxes. The results show that the framework generalises well to varying data and constraints, giving an average MSE of ∼0.09 across all datasets, demonstrating its robustness to different building types, locations, weather, and load distributions. [ABSTRACT FROM AUTHOR]

• Applied deep learning to sex classification in UK BioBank fMRI connectomes. • Deep learning classifies sex better in resting-state than in task fMRI. • Algorithm to balance out multiple confounds from an fMRI dataset. • Adapted two deep learning visualization methods to fMRI connectome classification. • Analyzed role of three brain a priori networks in sex classification. Classification of whole-brain functional connectivity MRI data with convolutional neural networks (CNNs) has shown promise, but the complexity of these models impedes understanding of which aspects of brain activity contribute to classification. While visualization techniques have been developed to interpret CNNs, bias inherent in the method of encoding abstract input data, as well as the natural variance of deep learning models, detract from the accuracy of these techniques. We introduce a stochastic encoding method in an ensemble of CNNs to classify functional connectomes by sex. We applied our method to resting-state and task data from the UK BioBank, using two visualization techniques to measure the salience of three brain networks involved in task- and resting-states, and their interaction. To regress confounding factors such as head motion, age, and intracranial volume, we introduced a multivariate balancing algorithm to ensure equal distributions of such covariates between classes in our data. We achieved a final AUROC of 0.8459. We found that resting-state data classifies more accurately than task data, with the inner salience network playing the most important role of the three networks overall in classification of resting-state data and connections to the central executive network in task data. [ABSTRACT FROM AUTHOR]

Segmentation of the left and right ventricles in cardiac MRI (Magnetic Resonance Imaging) is a prerequisite step for evaluating global and regional cardiac function. This work presents a novel and robust schema for MRI segmentation by combining the advantages of deep learning localization and 3D-ASM (3D Active Shape Model) restriction without any user interaction. Three fundamental techniques are exploited: (1) manual 2D contours are used to build distance maps to get 3D ground truth shape, (2) derived right ventricle points are employed to rotate the coarse initial shape for a refined bi-ventricle initial estimation, (3) segmentation results from deep learning are utilised to build distance maps for the 3D-ASM matching process to help image intensity modelling. The datasets used for experimenting the cine MRI data are 1000 cases from UK Biobank, 500 subjects are selected to train CNN (Convolution Neural Network) parameters, and the remaining 500 cases are adopted for validation. Specifically, cases are used to rebuild point distribution and image intensity models, and also utilized to train CNN. In addition, the left 500 cases are used to perform the validation experiments. For the segmentation of the RV (Right Ventricle) endocardial contour, LV (Left Ventricle) endo- and epicardial contours, overlap, Jaccard similarity index, Point-to-surface errors and cardiac functional parameters are calculated. Experimental results show that the proposed method has advantages over the previous approaches. [Display omitted] • Manual 2D contours are used to build distance maps to get 3D ground truth shape. • Right ventricle points from manual and deep learning are employed to rotate the coarse initial shape for a refined bi-ventricle initial estimate. • Segmentation results from deep learning are utilized to build distance maps for the 3D-ASM matching process. [ABSTRACT FROM AUTHOR]

• A lightweight deep learning model, Simple Fully Convolutional Network (SFCN), is presented, achieving state-of-the-art brain age prediction and sex classification performance in UK Biobank MRI brain imaging data. • Even with limited number of training subjects (e.g., 50), SFCN performs better than widely-used regression models. • A semi-multimodal ensemble strategy is proposed and achieved first place in the PAC 2019 brain age prediction challenge. • Linear regression can remove brain age prediction bias (even on unlabelled data) while maintaining state-of-the-art performance. Deep learning has huge potential for accurate disease prediction with neuroimaging data, but the prediction performance is often limited by training-dataset size and computing memory requirements. To address this, we propose a deep convolutional neural network model, Simple Fully Convolutional Network (SFCN), for accurate prediction of brain age using T1-weighted structural MRI data. Compared with other popular deep network architectures, SFCN has fewer parameters, so is more compatible with small dataset size and 3D volume data. The network architecture was combined with several techniques for boosting performance, including data augmentation, pre-training, model regularization, model ensemble and prediction bias correction. We compared our overall SFCN approach with several widely-used machine learning models. It achieved state-of-the-art performance in UK Biobank data (N = 14,503), with mean absolute error (MAE) = 2.14y in brain age prediction and 99.5% in sex classification. SFCN also won (both parts of) the 2019 Predictive Analysis Challenge for brain age prediction, involving 79 competing teams (N = 2,638, MAE = 2.90y). We describe here the details of our approach, and its optimisation and validation. Our approach can easily be generalised to other tasks using different image modalities, and is released on GitHub. [ABSTRACT FROM AUTHOR]

Cybersecurity mainly prevents the hardware, software, and data present in the system that has an active internet connection from external attacks. Organizations mainly deploy cybersecurity for their databases and systems to prevent it from unauthorized access. Different forms of attacks like phishing, spear-phishing, a drive-by attack, a password attack, denial of service, etc. are responsible for these security problems In this survey, we analyzed and reviewed the usage of deep learning algorithms for Cybersecurity applications. Deep learning which is also known as Deep Neural Networks includes machine learning techniques that enable the network to learn from unsupervised data and solve complex problems. Here, 80 papers from 2014 to 2019 have been used and successfully analyzed. Deep learning approaches such as Convolutional Neural Network (CNN), Auto Encoder (AE), Deep Belief Network (DBN), Recurrent Neural Network (RNN), Generative Adversal Network (GAN) and Deep Reinforcement Learning (DIL) are used to categorize the papers referred. Each specific technique is effectively discussed with its algorithms, platforms, dataset, and potential benefits. The paper related to deep learning with cybersecurity is mainly published in the year 2018 in a large number and 18% of published articles originate from the UK. In addition, the papers are selected from a variety of journals, and 30% of papers used are from the Elsevier journal. From the experimental analysis, it is clear that the deep learning model improved the accuracy, scalability, reliability, and performance of the cybersecurity applications when applied in realtime. [ABSTRACT FROM AUTHOR]

A major goal of neuroimaging studies is to develop predictive models to analyze the relationship between whole brain functional connectivity patterns and behavioural traits. However, there is no single widely-accepted standard pipeline for analyzing functional connectivity. The common procedure for designing functional connectivity based predictive models entails three main steps: parcellating the brain, estimating the interaction between defined parcels, and lastly, using these integrated associations between brain parcels as features fed to a classifier for predicting non-imaging variables e.g., behavioural traits, demographics, emotional measures, etc. There are also additional considerations when using correlation-based measures of functional connectivity, resulting in three supplementary steps: utilising Riemannian geometry tangent space parameterization to preserve the geometry of functional connectivity; penalizing the connectivity estimates with shrinkage approaches to handle challenges related to short time-series (and noisy) data; and removing confounding variables from brain-behaviour data. These six steps are contingent on each-other, and to optimise a general framework one should ideally examine these various methods simultaneously. In this paper, we investigated strengths and short-comings, both independently and jointly, of the following measures: parcellation techniques of four kinds (categorized further depending upon number of parcels), five measures of functional connectivity, the decision of staying in the ambient space of connectivity matrices or in tangent space, the choice of applying shrinkage estimators, six alternative techniques for handling confounds and finally four novel classifiers/predictors. For performance evaluation, we have selected two of the largest datasets, UK Biobank and the Human Connectome Project resting state fMRI data, and have run more than 9000 different pipeline variants on a total of ∼ 14000 individuals to determine the optimum pipeline. For independent performance validation, we have run some best-performing pipeline variants on ABIDE and ACPI datasets (∼ 1000 subjects) to evaluate the generalisability of proposed network modelling methods. Image 1 [ABSTRACT FROM AUTHOR]