Ultrasound imaging (US) often suffers from distinct image artifacts from various sources. Classic approaches for solving these problems are usually model-based iterative approaches that have been developed specifically for each type of artifact, which are often computationally intensive. Recently, deep learning approaches have been proposed as computationally efficient and high performance alternatives. Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type. This poses a fundamental limitation in the practical use of deep learning for US, since large number of models should be stored to deal with various US image artifacts. Inspired by the recent success of multi-domain image transfer, here we propose a novel, unsupervised, deep learning approach in which a single neural network can be used to deal with different types of US artifacts simply by changing a mask vector that switches between different target domains. Our algorithm is rigorously derived using an optimal transport (OT) theory for cascaded probability measures. Experimental results using phantom and in vivo data demonstrate that the proposed method can generate high quality image by removing distinct artifacts, which are comparable to those obtained by separately trained multiple neural networks.
Prognostic models aim to predict the future course of a disease or condition and are a vital component of personalized medicine. Statistical models make use of longitudinal data to capture the temporal aspect of disease progression; however, these models require prior feature extraction. Deep learning avoids explicit feature extraction, meaning we can develop models for images where features are either unknown or impossible to quantify accurately. Previous prognostic models using deep learning with imaging data require annotation during training or only utilize a single time point. We propose a novel deep learning method to predict the progression of diseases using longitudinal imaging data with uneven time intervals, which requires no prior feature extraction. Given previous images from a patient, our method aims to predict whether the patient will progress onto the next stage of the disease. The proposed method uses InceptionV3 to produce feature vectors for each image. In order to account for uneven intervals, a novel interval scaling is proposed. Finally, a Recurrent Neural Network is used to prognosticate the disease. We demonstrate our method on a longitudinal dataset of color fundus images from 4903 eyes with age-related macular degeneration (AMD), taken from the Age-Related Eye Disease Study, to predict progression to late AMD. Our method attains a testing sensitivity of 0.878, a specificity of 0.887, and an area under the receiver operating characteristic of 0.950. We compare our method to previous methods, displaying superior performance in our model. Class activation maps display how the network reaches the final decision.
Pathologist-defined labels are the gold standard for histopathological data sets, regardless of well-known limitations in consistency for some tasks. To date, some datasets on mitotic figures are available and were used for development of promising deep learning-based algorithms. In order to assess robustness of those algorithms and reproducibility of their methods it is necessary to test on several independent datasets. The influence of different labeling methods of these available datasets is currently unknown. To tackle this, we present an alternative set of labels for the images of the auxiliary mitosis dataset of the TUPAC16 challenge. Additional to manual mitotic figure screening, we used a novel, algorithm-aided labeling process, that allowed to minimize the risk of missing rare mitotic figures in the images. All potential mitotic figures were independently assessed by two pathologists. The novel, publicly available set of labels contains 1,999 mitotic figures (+28.80%) and additionally includes 10,483 labels of cells with high similarities to mitotic figures (hard examples). We found significant difference comparing F_1 scores between the original label set (0.549) and the new alternative label set (0.735) using a standard deep learning object detection architecture. The models trained on the alternative set showed higher overall confidence values, suggesting a higher overall label consistency. Findings of the present study show that pathologists-defined labels may vary significantly resulting in notable difference in the model performance. Comparison of deep learning-based algorithms between independent datasets with different labeling methods should be done with caution.
In this brief paper, a learning algorithm is developed for Deep Learning Neuro-Skin Neural Network to improve their learning properties. Neuroskin is a new type of neural network presented recently by the authors. It is comprised of a cellular membrane which has a neuron attached to each cell. The neuron is the cells nucleus. A neuroskin is modelled using finite elements. Each element of the finite element represents a cell. Each cells neuron has dendritic fibers which connects it to the nodes of the cell. On the other hand, its axon is connected to the nodes of a number of different neurons. The neuroskin is trained to contract upon receiving an input. The learning takes place during updating iterations using sensitivity analysis. It is shown that while the neuroskin can not present the desirable response, it improves gradually to the desired level.
Denoising of clinical CT images is an active area for deep learning research. Current clinically approved methods use iterative reconstruction methods to reduce the noise in CT images. Iterative reconstruction techniques require multiple forward and backward projections, which are time-consuming and computationally expensive. Recently, deep learning methods have been successfully used to denoise CT images. However, conventional deep learning methods suffer from the 'black box' problem. They have low accountability, which is necessary for use in clinical imaging situations. In this paper, we use a Joint Bilateral Filter (JBF) to denoise our CT images. The guidance image of the JBF is estimated using a deep residual convolutional neural network (CNN). The range smoothing and spatial smoothing parameters of the JBF are tuned by a deep reinforcement learning task. Our actor first chooses a parameter, and subsequently chooses an action to tune the value of the parameter. A reward network is designed to direct the reinforcement learning task. Our denoising method demonstrates good denoising performance, while retaining structural information. Our method significantly outperforms state of the art deep neural networks. Moreover, our method has only two parameters, which makes it significantly more interpretable and reduces the 'black box' problem. We experimentally measure the impact of our intelligent parameter optimization and our reward network. Our studies show that our current setup yields the best results in terms of structural preservation.
The uprising trend of deep learning in computer vision and artificial intelligence can simply not be ignored. On the most diverse tasks, from recognition and detection to segmentation, deep learning is able to obtain state-of-the-art results, reaching top notch performance. In this paper we explore how deep convolutional neural networks dedicated to the task of object detection can improve our industrial-oriented object detection pipelines, using state-of-the-art open source deep learning frameworks, like Darknet. By using a deep learning architecture that integrates region proposals, classification and probability estimation in a single run, we aim at obtaining real-time performance. We focus on reducing the needed amount of training data drastically by exploring transfer learning, while still maintaining a high average precision. Furthermore we apply these algorithms to two industrially relevant applications, one being the detection of promotion boards in eye tracking data and the other detecting and recognizing packages of warehouse products for augmented advertisements.
The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the variance of average mini-batch gradient with stratified sampling. We prove that the variance of average mini-batch gradient is minimized if the elements are sampled from a weighted clustering in the gradient space. We measure the gradient variance on common deep learning benchmarks and observe that, contrary to common assumptions, gradient variance increases during training, and smaller learning rates coincide with higher variance. In addition, we introduce normalized gradient variance as a statistic that better correlates with the speed of convergence compared to gradient variance.
Network security applications, including intrusion detection systems of deep neural networks, are increasing rapidly to make detection task of anomaly activities more accurate and robust. With the rapid increase of using DNN and the volume of data traveling through systems, different growing types of adversarial attacks to defeat them create a severe challenge. In this paper, we focus on investigating the effectiveness of different evasion attacks and how to train a resilience deep learning-based IDS using different Neural networks, e.g., convolutional neural networks (CNN) and recurrent neural networks (RNN). We use the min-max approach to formulate the problem of training robust IDS against adversarial examples using two benchmark datasets. Our experiments on different deep learning algorithms and different benchmark datasets demonstrate that defense using an adversarial training-based min-max approach improves the robustness against the five well-known adversarial attack methods.
While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues remain with other aspects of their performance including their ability to quantify uncertainty and their robustness. Recent advances in approximate Bayesian inference hold significant promise for addressing these concerns, but the computational scalability of these methods can be problematic when applied to large-scale models. In this paper, we describe initial work on the development ofURSABench(the Uncertainty, Robustness, Scalability, and Accu-racy Benchmark), an open-source suite of bench-marking tools for comprehensive assessment of approximate Bayesian inference methods with a focus on deep learning-based classification tasks
The last decade has witnessed growth in the computational requirements for training deep neural networks. Current approaches (e.g., data/model parallelism, pipeline parallelism) parallelize training tasks onto multiple devices. However, these approaches always rely on specific deep learning frameworks and requires elaborate manual design, which make it difficult to maintain and share between different type of models. In this paper, we propose Auto-MAP, a framework for exploring distributed execution plans for DNN workloads, which can automatically discovering fast parallelization strategies through reinforcement learning on IR level of deep learning models. Efficient exploration remains a major challenge for reinforcement learning. We leverage DQN with task-specific pruning strategies to help efficiently explore the search space including optimized strategies. Our evaluation shows that Auto-MAP can find the optimal solution in two hours, while achieving better throughput on several NLP and convolution models.
The notion of integrated circuit split manufacturing which delegates the front-end-of-line (FEOL) and back-end-of-line (BEOL) parts to different foundries, is to prevent overproduction, piracy of the intellectual property (IP), or targeted insertion of hardware Trojans by adversaries in the FEOL facility. In this work, we challenge the security promise of split manufacturing by formulating various layout-level placement and routing hints as vector- and image-based features. We construct a sophisticated deep neural network which can infer the missing BEOL connections with high accuracy. Compared with the publicly available network-flow attack [1], for the same set of ISCAS-85 benchmarks, we achieve 1.21X accuracy when splitting on M1 and 1.12X accuracy when splitting on M3 with less than 1% running time.
Distributed deep learning systems (DDLS) train deep neural network models by utilizing the distributed resources of a cluster. Developers of DDLS are required to make many decisions to process their particular workloads in their chosen environment efficiently. The advent of GPU-based deep learning, the ever-increasing size of datasets and deep neural network models, in combination with the bandwidth constraints that exist in cluster environments require developers of DDLS to be innovative in order to train high quality models quickly. Comparing DDLS side-by-side is difficult due to their extensive feature lists and architectural deviations. We aim to shine some light on the fundamental principles that are at work when training deep neural networks in a cluster of independent machines by analyzing the general properties associated with training deep learning models and how such workloads can be distributed in a cluster to achieve collaborative model training. Thereby we provide an overview of the different techniques that are used by contemporary DDLS and discuss their influence and implications on the training process. To conceptualize and compare DDLS, we group different techniques into categories, thus establishing a taxonomy of distributed deep learning systems.
Deep learning is fast emerging as a potential disruptive tool to tackle longstanding research problems across the sciences. Notwithstanding its success across disciplines, the recent trend of the overuse of deep learning is concerning to many machine learning practitioners. Recently, seismologists have also demonstrated the efficacy of deep learning algorithms in detecting low magnitude earthquakes. Here, we revisit the problem of seismic event detection but using a logistic regression model with feature extraction. We select well-discriminating features from a huge database of time-series operations collected from interdisciplinary time-series analysis methods. Using a simple learning model with only five trainable parameters, we detect several low-magnitude induced earthquakes from the Groningen gas field that are not present in the catalog. We note that the added advantage of simpler models is that the selected features add to our understanding of the noise and event classes present in the dataset. Since simpler models are easy to maintain, debug, understand, and train, through this study we underscore that it might be a dangerous pursuit to use deep learning without carefully weighing simpler alternatives.
Deep learning models usually require a huge amount of data. However, these large datasets are not always attainable. This is common in many challenging NLP tasks. Consider Neural Machine Translation, for instance, where curating such large datasets may not be possible specially for low resource languages. Another limitation of deep learning models is the demand for huge computing resources. These obstacles motivate research to question the possibility of knowledge transfer using large trained models. The demand for transfer learning is increasing as many large models are emerging. In this survey, we feature the recent transfer learning advances in the field of NLP. We also provide a taxonomy for categorizing different transfer learning approaches from the literature.
We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse autoencoders, which reduce the dimensionality of the full order model to a set of sparse latent variables with no prior knowledge of the coded space dimensionality. Then, a second neural network is trained to learn the metriplectic structure of those reduced physical variables and predict its time evolution with a so-called structure-preserving neural network. This data-based integrator is guaranteed to conserve the total energy of the system and the entropy inequality, and can be applied to both conservative and dissipative systems. The integrated paths can then be decoded to the original full-dimensional manifold and be compared to the ground truth solution. This method is tested with two examples applied to fluid and solid mechanics.
Diseases and pests cause huge economic loss to the apple industry every year. The identification of various apple diseases is challenging for the farmers as the symptoms produced by different diseases may be very similar, and may be present simultaneously. This paper is an attempt to provide the timely and accurate detection and identification of apple diseases. In this study, we propose a deep learning based approach for identification and classification of apple diseases. The first part of the study is dataset creation which includes data collection and data labelling. Next, we train a Convolutional Neural Network (CNN) model on the prepared dataset for automatic classification of apple diseases. CNNs are end-to-end learning algorithms which perform automatic feature extraction and learn complex features directly from raw images, making them suitable for wide variety of tasks like image classification, object detection, segmentation etc. We applied transfer learning to initialize the parameters of the proposed deep model. Data augmentation techniques like rotation, translation, reflection and scaling were also applied to prevent overfitting. The proposed CNN model obtained encouraging results, reaching around 97.18% of accuracy on our prepared dataset. The results validate that the proposed method is effective in classifying various types of apple diseases and can be used as a practical tool by farmers.
X-ray photon-counting detectors (PCDs) are drawing an increasing attention in recent years due to their low noise and energy discrimination capabilities. The energy/spectral dimension associated with PCDs potentially brings great benefits such as for material decomposition, beam hardening and metal artifact reduction, as well as low-dose CT imaging. However, X-ray PCDs are currently limited by several technical issues, particularly charge splitting (including charge sharing and K-shell fluorescence re-absorption or escaping) and pulse pile-up effects which distort the energy spectrum and compromise the data quality. Correction of raw PCD measurements with hardware improvement and analytic modeling is rather expensive and complicated. Hence, here we proposed a deep neural network based PCD data correction approach which directly maps imperfect data to the ideal data in the supervised learning mode. In this work, we first establish a complete simulation model incorporating the charge splitting and pulse pile-up effects. The simulated PCD data and the ground truth counterparts are then fed to a specially designed deep adversarial network for PCD data correction. Next, the trained network is used to correct separately generated PCD data. The test results demonstrate that the trained network successfully recovers the ideal spectrum from the distorted measurement within $\pm6\%$ relative error. Significant data and image fidelity improvements are clearly observed in both projection and reconstruction domains.
Since the past few decades, human trajectory forecasting has been a field of active research owing to its numerous real-world applications: evacuation situation analysis, deployment of intelligent transport systems, traffic operations, to name a few. Early works handcrafted this representation based on domain knowledge. However, social interactions in crowded environments are not only diverse but often subtle. Recently, deep learning methods have outperformed their handcrafted counterparts, as they learned about human-human interactions in a more generic data-driven fashion. In this work, we present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two knowledge-based data-driven methods to effectively capture these social interactions. To objectively compare the performance of these interaction-based forecasting models, we develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting. We propose novel performance metrics that evaluate the ability of a model to output socially acceptable trajectories. Experiments on TrajNet++ validate the need for our proposed metrics, and our method outperforms competitive baselines on both real-world and synthetic datasets.
This compendium gathers all the accepted extended abstracts from the Third International Conference on Medical Imaging with Deep Learning (MIDL 2020), held in Montreal, Canada, 6-9 July 2020. Note that only accepted extended abstracts are listed here, the Proceedings of the MIDL 2020 Full Paper Track are published in the Proceedings of Machine Learning Research (PMLR).
In this work, we try to address the challenging problem of dimple detection and segmentation in Titanium alloys using machine learning methods, especially neural networks. The images i.e. fractographs are obtained using a Scanning Election Microscope (SEM). To determine the cause of fracture in metals we address the problem of segmentation of dimples in fractographs i.e. the fracture surface of metals using supervised machine learning methods. Determining the cause of fracture would help us in material property, mechanical property prediction and development of new fracture-resistant materials. This method would also help in correlating the topography of the fracture surface with the mechanical properties of the material. Our proposed novel model achieves the best performance as compared to other previous approaches. To the best of our knowledge, this is one the first work in fractography using fully convolutional neural networks with self-attention for supervised learning of dimple fractography, though it can be easily extended to account for brittle characteristics as well.