Novel coronavirus (COVID-19) outbreak, has raised a calamitous situation all over the world and has become one of the most acute and severe ailments in the past hundred years. The prevalence rate of COVID-19 is rapidly rising every day throughout the globe. Although no vaccines for this pandemic have been discovered yet, deep learning techniques proved themselves to be a powerful tool in the arsenal used by clinicians for the automatic diagnosis of COVID-19. This paper aims to overview the recently developed systems based on deep learning techniques using different medical imaging modalities like Computer Tomography (CT) and X-ray. This review specifically discusses the systems developed for COVID-19 diagnosis using deep learning techniques and provides insights on well-known data sets used to train these networks. It also highlights the data partitioning techniques and various performance measures developed by researchers in this field. A taxonomy is drawn to categorize the recent works for proper insight. Finally, we conclude by addressing the challenges associated with the use of deep learning methods for COVID-19 detection and probable future trends in this research area. This paper is intended to provide experts (medical or otherwise) and technicians with new insights into the ways deep learning techniques are used in this regard and how they potentially further works in combatting the outbreak of COVID-19.
Large scale image datasets are a growing trend in the field of machine learning. However, it is hard to quantitatively understand or specify how various datasets compare to each other - i.e., if one dataset is more complex or harder to ``learn'' with respect to a deep-learning based network. In this work, we build a series of relatively computationally simple methods to measure the complexity of a dataset. Furthermore, we present an approach to demonstrate visualizations of high dimensional data, in order to assist with visual comparison of datasets. We present our analysis using four datasets from the autonomous driving research community - Cityscapes, IDD, BDD and Vistas. Using entropy based metrics, we present a rank-order complexity of these datasets, which we compare with an established rank-order with respect to deep learning.
Diabetic retinopathy (DR) screening is instrumental in preventing blindness, but faces a scaling challenge as the number of diabetic patients rises. Risk stratification for the development of DR may help optimize screening intervals to reduce costs while improving vision-related outcomes. We created and validated two versions of a deep learning system (DLS) to predict the development of mild-or-worse ("Mild+") DR in diabetic patients undergoing DR screening. The two versions used either three-fields or a single field of color fundus photographs (CFPs) as input. The training set was derived from 575,431 eyes, of which 28,899 had known 2-year outcome, and the remaining were used to augment the training process via multi-task learning. Validation was performed on both an internal validation set (set A; 7,976 eyes; 3,678 with known outcome) and an external validation set (set B; 4,762 eyes; 2,345 with known outcome). For predicting 2-year development of DR, the 3-field DLS had an area under the receiver operating characteristic curve (AUC) of 0.79 (95%CI, 0.78-0.81) on validation set A. On validation set B (which contained only a single field), the 1-field DLS's AUC was 0.70 (95%CI, 0.67-0.74). The DLS was prognostic even after adjusting for available risk factors (p<0.001). When added to the risk factors, the 3-field DLS improved the AUC from 0.72 (95%CI, 0.68-0.76) to 0.81 (95%CI, 0.77-0.84) in validation set A, and the 1-field DLS improved the AUC from 0.62 (95%CI, 0.58-0.66) to 0.71 (95%CI, 0.68-0.75) in validation set B. The DLSs in this study identified prognostic information for DR development from CFPs. This information is independent of and more informative than the available risk factors.
The growth and success of deep learning approaches can be attributed to two major factors: availability of hardware resources and availability of large number of training samples. For problems with large training databases, deep learning models have achieved superlative performances. However, there are a lot of \textit{small sample size or $S^3$} problems for which it is not feasible to collect large training databases. It has been observed that deep learning models do not generalize well on $S^3$ problems and specialized solutions are required. In this paper, we first present a review of deep learning algorithms for small sample size problems in which the algorithms are segregated according to the space in which they operate, i.e. input space, model space, and feature space. Secondly, we present Dynamic Attention Pooling approach which focuses on extracting global information from the most discriminative sub-part of the feature map. The performance of the proposed dynamic attention pooling is analyzed with state-of-the-art ResNet model on relatively small publicly available datasets such as SVHN, C10, C100, and TinyImageNet.
Current expectations from training deep learning models with gradient-based methods include: 1) transparency; 2) high convergence rates; 3) high inductive biases. While the state-of-art methods with adaptive learning rate schedules are fast, they still fail to meet the other two requirements. We suggest reconsidering neural network models in terms of single-species population dynamics where adaptation comes naturally from open-ended processes of "growth" and "harvesting". We show that the stochastic gradient descent (SGD) with two balanced pre-defined values of per capita growth and harvesting rates outperform the most common adaptive gradient methods in all of the three requirements.
In the last two decades, neuroscience has produced intriguing evidence for a central role of the claustrum in mammalian forebrain structure and function. However, relatively few in vivo studies of the claustrum exist in humans. A reason for this may be the delicate and sheet-like structure of the claustrum lying between the insular cortex and the putamen, which makes it not amenable to conventional segmentation methods. Recently, Deep Learning (DL) based approaches have been successfully introduced for automated segmentation of complex, subcortical brain structures. In the following, we present a multi-view DL-based approach to segment the claustrum in T1-weighted MRI scans. We trained and evaluated the proposed method in 181 individuals, using bilateral manual claustrum annotations by an expert neuroradiologist as the reference standard. Cross-validation experiments yielded median volumetric similarity, robust Hausdorff distance, and Dice score of 93.3%, 1.41mm, and 71.8%, respectively, representing equal or superior segmentation performance compared to human intra-rater reliability. The leave-one-scanner-out evaluation showed good transferability of the algorithm to images from unseen scanners at slightly inferior performance. Furthermore, we found that DL-based claustrum segmentation benefits from multi-view information and requires a sample size of around 75 MRI scans in the training set. We conclude that the developed algorithm allows for robust automated claustrum segmentation and thus yields considerable potential for facilitating MRI-based research of the human claustrum. The software and models of our method are made publicly available.
The LIGO and Virgo gravitational-wave observatories have detected many exciting events over the past five years. As the rate of detections grows with detector sensitivity, this poses a growing computational challenge for data analysis. With this in mind, in this work we apply deep learning techniques to perform fast likelihood-free Bayesian inference for gravitational waves. We train a neural-network conditional density estimator to model posterior probability distributions over the full 15-dimensional space of binary black hole system parameters, given detector strain data from multiple detectors. We use the method of normalizing flows---specifically, a neural spline normalizing flow---which allows for rapid sampling and density estimation. Training the network is likelihood-free, requiring samples from the data generative process, but no likelihood evaluations. Through training, the network learns a global set of posteriors: it can generate thousands of independent posterior samples per second for any strain data consistent with the prior and detector noise characteristics used for training. By training with the detector noise power spectral density estimated at the time of GW150914, and conditioning on the event strain data, we use the neural network to generate accurate posterior samples consistent with analyses using conventional sampling techniques.
While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based assessment models and shown the potential to automate the speech quality assessment. To improve the previously proposed assessment model, MOSNet, we propose three models using cluster-based modeling methods: using a global quality token (GQT) layer, using an Encoding Layer, and using both of them. We perform experiments using the evaluation results of the Voice Conversion Challenge 2018 to predict the mean opinion score of synthesized speech and similarity score between synthesized speech and reference speech. The results show that the GQT layer helps to predict human assessment better by automatically learning the useful quality tokens for the task and that the Encoding Layer helps to utilize frame-level scores more precisely.
This paper aims to solve machine learning optimization problem by using quantum circuit. Two approaches, namely the average approach and the Partial Swap Test Cut-off method (PSTC) was proposed to search for the global minimum/maximum of two different objective functions. The current cost is $O(\sqrt{|\Theta|} N)$, but there is potential to improve PSTC further to $O(\sqrt{|\Theta|} \cdot sublinear \ N)$ by enhancing the checking process.
Machine learning has been developed dramatically and witnessed a lot of applications in various fields over the past few years. This boom originated in 2009, when a new model emerged, that is, the deep artificial neural network, which began to surpass other established mature models on some important benchmarks. Later, it was widely used in academia and industry. Ranging from image analysis to natural language processing, it fully exerted its magic and now become the state-of-the-art machine learning models. Deep neural networks have great potential in medical imaging technology, medical data analysis, medical diagnosis and other healthcare issues, and is promoted in both pre-clinical and even clinical stages. In this review, we performed an overview of some new developments and challenges in the application of machine learning to medical image analysis, with a special focus on deep learning in photoacoustic imaging. The aim of this review is threefold: (i) introducing deep learning with some important basics, (ii) reviewing recent works that apply deep learning in the entire ecological chain of photoacoustic imaging, from image reconstruction to disease diagnosis, (iii) providing some open source materials and other resources for researchers interested in applying deep learning to photoacoustic imaging.
Unsupervised deep-learning (DL) models were recently proposed for deformable image registration tasks. In such models, a neural-network is trained to predict the best deformation field by minimizing some dissimilarity function between the moving and the target images. After training on a dataset without reference deformation fields available, such a model can be used to rapidly predict the deformation field between newly seen moving and target images. Currently, the training process effectively provides a point-estimate of the network weights rather than characterizing their entire posterior distribution. This may result in a potential over-fitting which may yield sub-optimal results at inference phase, especially for small-size datasets, frequently present in the medical imaging domain. We introduce a fully Bayesian framework for unsupervised DL-based deformable image registration. Our method provides a principled way to characterize the true posterior distribution, thus, avoiding potential over-fitting. We used stochastic gradient Langevin dynamics (SGLD) to conduct the posterior sampling, which is both theoretically well-founded and computationally efficient. We demonstrated the added-value of our Basyesian unsupervised DL-based registration framework on the MNIST and brain MRI (MGH10) datasets in comparison to the VoxelMorph unsupervised DL-based image registration framework. Our experiments show that our approach provided better estimates of the deformation field by means of improved mean-squared-error ($0.0063$ vs. $0.0065$) and Dice coefficient ($0.73$ vs. $0.71$) for the MNIST and the MGH10 datasets respectively. Further, our approach provides an estimate of the uncertainty in the deformation-field by characterizing the true posterior distribution.
In this paper, we introduce a deep learning model to classify children as either healthy or potentially autistic with 94.6% accuracy using Deep Learning. Autistic patients struggle with social skills, repetitive behaviors, and communication, both verbal and nonverbal. Although the disease is considered to be genetic, the highest rates of accurate diagnosis occur when the child is tested on behavioral characteristics and facial features. Patients have a common pattern of distinct facial deformities, allowing researchers to analyze only an image of the child to determine if the child has the disease. While there are other techniques and models used for facial analysis and autism classification on their own, our proposal bridges these two ideas allowing classification in a cheaper, more efficient method. Our deep learning model uses MobileNet and two dense layers in order to perform feature extraction and image classification. The model is trained and tested using 3,014 images, evenly split between children with autism and children without it. 90% of the data is used for training, and 10% is used for testing. Based on our accuracy, we propose that the diagnosis of autism can be done effectively using only a picture. Additionally, there may be other diseases that are similarly diagnosable.
Fatigue is one of the key factors in the loss of work efficiency and health-related quality of life, and most fatigue assessment methods were based on self-reporting, which may suffer from many factors such as recall bias. To address this issue, we developed an automated system using wearable sensing and machine learning techniques for objective fatigue assessment. ECG/Actigraphy data were collected from subjects in free-living environments. Preprocessing and feature engineering methods were applied, before interpretable solution and deep learning solution were introduced. Specifically, for interpretable solution, we proposed a feature selection approach which can select less correlated and high informative features for better understanding system's decision-making process. For deep learning solution, we used state-of-the-art self-attention model, based on which we further proposed a consistency self-attention (CSA) mechanism for fatigue assessment. Extensive experiments were conducted, and very promising results were achieved.
We consider the neural ODE perspective of supervised learning and study the impact of the final time $T$ (which may indicate the depth of a corresponding ResNet) in training. For the classical $L^2$--regularized empirical risk minimization problem, whenever the neural ODE dynamics are homogeneous with respect to the parameters, we show that the training error is at most of the order $\mathcal{O}\left(\frac{1}{T}\right)$. Furthermore, if the loss inducing the empirical risk attains its minimum, the optimal parameters converge to minimal $L^2$--norm parameters which interpolate the dataset. By a natural scaling between $T$ and the regularization hyperparameter $\lambda$ we obtain the same results when $\lambda\searrow0$ and $T$ is fixed. This allows us to stipulate generalization properties in the overparametrized regime, now seen from the large depth, neural ODE perspective. To enhance the polynomial decay, inspired by turnpike theory in optimal control, we propose a learning problem with an additional integral regularization term of the neural ODE trajectory over $[0,T]$. In the setting of $\ell^p$--distance losses, we prove that both the training error and the optimal parameters are at most of the order $\mathcal{O}\left(e^{-\mu t}\right)$ in any $t\in[0,T]$. The aforementioned stability estimates are also shown for continuous space-time neural networks, taking the form of nonlinear integro-differential equations. By using a time-dependent moving grid for discretizing the spatial variable, we demonstrate that these equations provide a framework for addressing ResNets with variable widths.
Advances in deep learning have led to remarkable success in augmented microscopy, enabling us to obtain high-quality microscope images without using expensive microscopy hardware and sample preparation techniques. However, current deep learning models for augmented microscopy are mostly U-Net based neural networks, thus sharing certain drawbacks that limit the performance. In this work, we introduce global voxel transformer networks (GVTNets), an advanced deep learning tool for augmented microscopy that overcomes intrinsic limitations of the current U-Net based models and achieves improved performance. GVTNets are built on global voxel transformer operators (GVTOs), which are able to aggregate global information, as opposed to local operators like convolutions. We apply the proposed methods on existing datasets for three different augmented microscopy tasks under various settings. The performance is significantly and consistently better than previous U-Net based approaches.
Purpose: AI in radiology is hindered chiefly by: 1) Requiring large annotated data sets. 2) Non-generalizability that limits deployment to new scanners / institutions. And 3) Inadequate explainability and interpretability. We believe that reinforcement learning can address all three shortcomings, with robust and intuitive algorithms trainable on small datasets. To the best of our knowledge, reinforcement learning has not been directly applied to computer vision tasks for radiological images. In this proof-of-principle work, we train a deep reinforcement learning network to predict brain tumor location. Materials and Methods: Using the BraTS brain tumor imaging database, we trained a deep Q network on 70 post-contrast T1-weighted 2D image slices. We did so in concert with image exploration, with rewards and punishments designed to localize lesions. To compare with supervised deep learning, we trained a keypoint detection convolutional neural network on the same 70 images. We applied both approaches to a separate 30 image testing set. Results: Reinforcement learning predictions consistently improved during training, whereas those of supervised deep learning quickly diverged. Reinforcement learning predicted testing set lesion locations with 85% accuracy, compared to roughly 7% accuracy for the supervised deep network. Conclusion: Reinforcement learning predicted lesions with high accuracy, which is unprecedented for such a small training set. We believe that reinforcement learning can propel radiology AI well past the inherent limitations of supervised deep learning, with more clinician-driven research and finally toward true clinical applicability.
In the world, about 7 to 10 million elderly people are suffering from Parkinson's Disease (PD) disease. Parkinson's disease is a common neurological degenerative disease, and its clinical characteristics are Tremors, rigidity, bradykinesia, and decreased autonomy. Its clinical manifestations are very similar to Multiple System Atrophy (MSA) disorders. Studies have shown that patients with Parkinson's disease often reach an irreparable situation when diagnosed, so As Parkinson's disease can be distinguished from MSA disease and get an early diagnosis, people are constantly exploring new methods. With the advent of the era of big data, deep learning has made major breakthroughs in image recognition and classification. Therefore, this study proposes to use The deep learning method to realize the diagnosis of Parkinson's disease, multiple system atrophy, and healthy people. This data source is from Istanbul University Cerrahpasa Faculty of Medicine Hospital. The processing of the original magnetic resonance image (Magnetic Resonance Image, MRI) is guided by the doctor of Istanbul University Cerrahpasa Faculty of Medicine Hospital. The focus of this experiment is to improve the existing neural network so that it can obtain good results in medical image recognition and diagnosis. An improved algorithm was proposed based on the pathological characteristics of Parkinson's disease, and good experimental results were obtained by comparing indicators such as model loss and accuracy.
Point source detection techniques are used to identify and localise point sources in radio astronomical surveys. With the development of the Square Kilometre Array (SKA) telescope, survey images will see a massive increase in size from Gigapixels to Terapixels. Point source detection has already proven to be a challenge in recent surveys performed by SKA pathfinder telescopes. This paper proposes the Point Proposal Network (PPN): a point source detector that utilises deep convolutional neural networks for fast source detection. Results measured on simulated MeerKAT images show that, although less precise when compared to leading alternative approaches, PPN performs source detection faster and is able to scale to large images, unlike the alternative approaches.
Pervasive computing involves the placement of processing services close to end users to support intelligent applications. With the advent of the Internet of Things (IoT) and the Edge Computing (EC), one can find room for placing services at various points in the interconnection of the aforementioned infrastructures. Of significant importance is the processing of the collected data. Such a processing can be realized upon the EC nodes that exhibit increased computational capabilities compared to IoT devices. An ecosystem of intelligent nodes is created at the EC giving the opportunity to support cooperative models. Nodes become the hosts of geo-distributed datasets formulated by the IoT devices reports. Upon the datasets, a number of queries/tasks can be executed. Queries/tasks can be offloaded for performance reasons. However, an offloading action should be carefully designed being always aligned with the data present to the hosting node. In this paper, we present a model to support the cooperative aspect in the EC infrastructure. We argue on the delivery of data synopses to EC nodes making them capable to take offloading decisions fully aligned with data present at peers. Nodes exchange data synopses to inform their peers. We propose a scheme that detects the appropriate time to distribute synopses trying to avoid the network overloading especially when synopses are frequently extracted due to the high rates at which IoT devices report data to EC nodes. Our approach involves a Deep Learning model for learning the distribution of calculated synopses and estimate future trends. Upon these trends, we are able to find the appropriate time to deliver synopses to peer nodes. We provide the description of the proposed mechanism and evaluate it based on real datasets. An extensive experimentation upon various scenarios reveals the pros and cons of the approach by giving numerical results.
Artificial neural networks (ANN) have been used in many applications such like handwriting recognition and speech recognition. It is well-known that learning rate is a crucial value in the training procedure for artificial neural networks. It is shown that the initial value of learning rate can confoundedly affect the final result and this value is always set manually in practice. A new parameter called beta stabilizer has been introduced to reduce the sensitivity of the initial learning rate. But this method has only been proposed for deep neural network (DNN) with sigmoid activation function. In this paper we extended beta stabilizer to long short-term memory (LSTM) and investigated the effects of beta stabilizer parameters on different models, including LSTM and DNN with relu activation function. It is concluded that beta stabilizer parameters can reduce the sensitivity of learning rate with almost the same performance on DNN with relu activation function and LSTM. However, it is shown that the effects of beta stabilizer on DNN with relu activation function and LSTM are fewer than the effects on DNN with sigmoid activation function.