Deep learning methods have been successfully used in various computer vision tasks. Inspired by that success, deep learning has been explored in magnetic resonance imaging (MRI) reconstruction. In particular, integrating deep learning and model-based optimization methods has shown considerable advantages. However, a large amount of labeled training data is typically needed for high reconstruction quality, which is challenging for some MRI applications. In this paper, we propose a novel reconstruction method, named DURED-Net, that enables interpretable self-supervised learning for MR image reconstruction by combining a self-supervised denoising network and a plug-and-play method. We aim to boost the reconstruction performance of Noise2Noise in MR reconstruction by adding an explicit prior that utilizes imaging physics. Specifically, the leverage of a denoising network for MRI reconstruction is achieved using Regularization by Denoising (RED). Experiment results demonstrate that the proposed method requires a reduced amount of training data to achieve high reconstruction quality among the state-of-art of MR reconstruction utilizing the Noise2Noise method.
The arguably most widely employed algorithm to train deep neural networks with Differential Privacy is DPSGD, which requires clipping and noising of per-sample gradients. This introduces a reduction in model utility compared to non-private training. Empirically, it can be observed that this accuracy degradation is strongly dependent on the model architecture. We investigated this phenomenon and, by combining components which exhibit good individual performance, distilled a new model architecture termed SmoothNet, which is characterised by increased robustness to the challenges of DP-SGD training. Experimentally, we benchmark SmoothNet against standard architectures on two benchmark datasets and observe that our architecture outperforms others, reaching an accuracy of 73.5\% on CIFAR-10 at $\varepsilon=7.0$ and 69.2\% at $\varepsilon=7.0$ on ImageNette, a state-of-the-art result compared to prior architectural modifications for DP.
Deep learning methods driven by the low-rank regularization have achieved attractive performance in dynamic magnetic resonance (MR) imaging. However, most of these methods represent low-rank prior by hand-crafted nuclear norm, which cannot accurately approximate the low-rank prior over the entire dataset through a fixed regularization parameter. In this paper, we propose a learned low-rank method for dynamic MR imaging. In particular, we unrolled the semi-quadratic splitting method (HQS) algorithm for the partially separable (PS) model to a network, in which the low-rank is adaptively characterized by a learnable null-space transform. Experiments on the cardiac cine dataset show that the proposed model outperforms the state-of-the-art compressed sensing (CS) methods and existing deep learning methods both quantitatively and qualitatively.
Today, finger vein identification is gaining popularity as a potential biometric identification framework solution. Machine learning-based unsupervised, supervised, and deep learning algorithms have had a significant influence on finger vein detection and recognition at the moment. Deep learning, on the other hand, necessitates a large number of training datasets that must be manually produced and labeled. In this research, we offer a completely automated unsupervised learning strategy for training dataset creation. Our method is intended to extract and build a decent binary mask training dataset completely automated. In this technique, two optimization steps are devised and employed. The initial stage of optimization is to create a completely automated unsupervised image clustering based on finger vein image localization. Worldwide finger vein pattern orientation estimation is employed in the second optimization to optimize the retrieved finger vein lines. Finally, the proposed system achieves 99.6 - percent pattern extraction accuracy, which is significantly higher than other common unsupervised learning methods like k-means and Fuzzy C-Means (FCM).
This thesis tackles the subject of spatio-temporal forecasting with deep learning. The motivating application at Electricity de France (EDF) is short-term solar energy forecasting with fisheye images. We explore two main research directions for improving deep forecasting methods by injecting external physical knowledge. The first direction concerns the role of the training loss function. We show that differentiable shape and temporal criteria can be leveraged to improve the performances of existing models. We address both the deterministic context with the proposed DILATE loss function and the probabilistic context with the STRIPE model. Our second direction is to augment incomplete physical models with deep data-driven networks for accurate forecasting. For video prediction, we introduce the PhyDNet model that disentangles physical dynamics from residual information necessary for prediction, such as texture or details. We further propose a learning framework (APHYNITY) that ensures a principled and unique linear decomposition between physical and data-driven components under mild assumptions, leading to better forecasting performances and parameter identification.
Automated disease detection in neuroimaging holds promise to improve the diagnostic ability of radiologists, but routinely collected clinical data frequently contains technical and demographic confounding factors that cause data to both differ between sites and be systematically associated with the disease of interest, thus negatively affecting the robustness of diagnostic models. There is a critical need for diagnostic deep learning models that can train on such imbalanced datasets without being influenced by these confounds. In this work, we introduce a novel deep learning architecture, MUCRAN (Multi-Confound Regression Adversarial Network), to train a deep learning model on clinical brain MRI while regressing demographic and technical confounding factors. We trained MUCRAN using 17,076 clinical T1 Axial brain MRIs collected from Massachusetts General Hospital before 2019 and demonstrated that MUCRAN could successfully regress major confounding factors in the vast clinical data. We also applied a method for quantifying uncertainty across an ensemble of these models to automatically exclude out-of-distribution data in the AD detection. By combining MUCRAN and the uncertainty quantification method, we showed consistent and significant increases in the AD detection accuracy for newly collected MGH data (post-2019) and for data from other hospitals. MUCRAN offers a generalizable approach for heterogenous clinical data for deep-learning-based automatic disease detection.
Background. Pre-operative risk assessments used in clinical practice are limited in their ability to identify risk for post-operative mortality. We hypothesize that electrocardiograms contain hidden risk markers that can help prognosticate post-operative mortality. Methods. In a derivation cohort of 45,969 pre-operative patients (age 59+- 19 years, 55 percent women), a deep learning algorithm was developed to leverage waveform signals from pre-operative ECGs to discriminate post-operative mortality. Model performance was assessed in a holdout internal test dataset and in two external hospital cohorts and compared with the Revised Cardiac Risk Index (RCRI) score. Results. In the derivation cohort, there were 1,452 deaths. The algorithm discriminates mortality with an AUC of 0.83 (95% CI 0.79-0.87) surpassing the discrimination of the RCRI score with an AUC of 0.67 (CI 0.61-0.72) in the held out test cohort. Patients determined to be high risk by the deep learning model's risk prediction had an unadjusted odds ratio (OR) of 8.83 (5.57-13.20) for post-operative mortality as compared to an unadjusted OR of 2.08 (CI 0.77-3.50) for post-operative mortality for RCRI greater than 2. The deep learning algorithm performed similarly for patients undergoing cardiac surgery with an AUC of 0.85 (CI 0.77-0.92), non-cardiac surgery with an AUC of 0.83 (0.79-0.88), and catherization or endoscopy suite procedures with an AUC of 0.76 (0.72-0.81). The algorithm similarly discriminated risk for mortality in two separate external validation cohorts from independent healthcare systems with AUCs of 0.79 (0.75-0.83) and 0.75 (0.74-0.76) respectively. Conclusion. The findings demonstrate how a novel deep learning algorithm, applied to pre-operative ECGs, can improve discrimination of post-operative mortality.
Deep learning has a great potential for estimating biomarkers in diffusion weighted magnetic resonance imaging (dMRI). Atlases, on the other hand, are a unique tool for modeling the spatio-temporal variability of biomarkers. In this paper, we propose the first framework to exploit both deep learning and atlases for biomarker estimation in dMRI. Our framework relies on non-linear diffusion tensor registration to compute biomarker atlases and to estimate atlas reliability maps. We also use nonlinear tensor registration to align the atlas to a subject and to estimate the error of this alignment. We use the biomarker atlas, atlas reliability map, and alignment error map, in addition to the dMRI signal, as inputs to a deep learning model for biomarker estimation. We use our framework to estimate fractional anisotropy and neurite orientation dispersion from down-sampled dMRI data on a test cohort of 70 newborn subjects. Results show that our method significantly outperforms standard estimation methods as well as recent deep learning techniques. Our method is also more robust to stronger measurement down-sampling factors. Our study shows that the advantages of deep learning and atlases can be synergistically combined to achieve unprecedented accuracy in biomarker estimation from dMRI data.
Surgery is a high-stakes domain where surgeons must navigate critical anatomical structures and actively avoid potential complications while achieving the main task at hand. Such surgical activity has been shown to affect long-term patient outcomes. To better understand this relationship, whose mechanics remain unknown for the majority of surgical procedures, we hypothesize that the core elements of surgery must first be quantified in a reliable, objective, and scalable manner. We believe this is a prerequisite for the provision of surgical feedback and modulation of surgeon performance in pursuit of improved patient outcomes. To holistically quantify surgeries, we propose a unified deep learning framework, entitled Roboformer, which operates exclusively on videos recorded during surgery to independently achieve multiple tasks: surgical phase recognition (the what of surgery), gesture classification and skills assessment (the how of surgery). We validated our framework on four video-based datasets of two commonly-encountered types of steps (dissection and suturing) within minimally-invasive robotic surgeries. We demonstrated that our framework can generalize well to unseen videos, surgeons, medical centres, and surgical procedures. We also found that our framework, which naturally lends itself to explainable findings, identified relevant information when achieving a particular task. These findings are likely to instill surgeons with more confidence in our framework's behaviour, increasing the likelihood of clinical adoption, and thus paving the way for more targeted surgical feedback.
Decision making algorithms are used in a multitude of different applications. Conventional approaches for designing decision algorithms employ principled and simplified modelling, based on which one can determine decisions via tractable optimization. More recently, deep learning approaches that use highly parametric architectures tuned from data without relying on mathematical models, are becoming increasingly popular. Model-based optimization and data-centric deep learning are often considered to be distinct disciplines. Here, we characterize them as edges of a continuous spectrum varying in specificity and parameterization, and provide a tutorial-style presentation to the methodologies lying in the middle ground of this spectrum, referred to as model-based deep learning. We accompany our presentation with running examples in super-resolution and stochastic control, and show how they are expressed using the provided characterization and specialized in each of the detailed methodologies. The gains of combining model-based optimization and deep learning are demonstrated using experimental results in various applications, ranging from biomedical imaging to digital communications.
Deep neural networks are rapidly emerging as data analysis tools, often outperforming the conventional techniques used in complex microfluidic systems. One fundamental analysis frequently desired in microfluidic experiments is counting and tracking the droplets. Specifically, droplet tracking in dense emulsions is challenging as droplets move in tightly packed configurations. Sometimes the individual droplets in these dense clusters are hard to resolve, even for a human observer. Here, two deep learning-based cutting-edge algorithms for object detection (YOLO) and object tracking (DeepSORT) are combined into a single image analysis tool, DropTrack, to track droplets in microfluidic experiments. DropTrack analyzes input videos, extracts droplets' trajectories, and infers other observables of interest, such as droplet numbers. Training an object detector network for droplet recognition with manually annotated images is a labor-intensive task and a persistent bottleneck. This work partly resolves this problem by training object detector networks (YOLOv5) with hybrid datasets containing real and synthetic images. We present an analysis of a double emulsion experiment as a case study to measure DropTrack's performance. For our test case, the YOLO networks trained with 60% synthetic images show similar performance in droplet counting as with the one trained using 100% real images, meanwhile saving the image annotation work by 60%. DropTrack's performance is measured in terms of mean average precision (mAP), mean square error in counting the droplets, and inference speed. The fastest configuration of DropTrack runs inference at about 30 frames per second, well within the standards for real-time image analysis.
The disturbance storm time (Dst) index is an important and useful measurement in space weather research. It has been used to characterize the size and intensity of a geomagnetic storm. A negative Dst value means that the Earth's magnetic field is weakened, which happens during storms. In this paper, we present a novel deep learning method, called the Dst Transformer, to perform short-term, 1-6 hour ahead, forecasting of the Dst index based on the solar wind parameters provided by the NASA Space Science Data Coordinated Archive. The Dst Transformer combines a multi-head attention layer with Bayesian inference, which is capable of quantifying both aleatoric uncertainty and epistemic uncertainty when making Dst predictions. Experimental results show that the proposed Dst Transformer outperforms related machine learning methods in terms of the root mean square error and R-squared. Furthermore, the Dst Transformer can produce both data and model uncertainty quantification results, which can not be done by the existing methods. To our knowledge, this is the first time that Bayesian deep learning has been used for Dst index forecasting.
As Deep Learning (DL) systems are widely deployed for mission-critical applications, debugging such systems becomes essential. Most existing works identify and repair suspicious neurons on the trained Deep Neural Network (DNN), which, unfortunately, might be a detour. Specifically, several existing studies have reported that many unsatisfactory behaviors are actually originated from the faults residing in DL programs. Besides, locating faulty neurons is not actionable for developers, while locating the faulty statements in DL programs can provide developers with more useful information for debugging. Though a few recent studies were proposed to pinpoint the faulty statements in DL programs or the training settings (e.g. too large learning rate), they were mainly designed based on predefined rules, leading to many false alarms or false negatives, especially when the faults are beyond their capabilities. In view of these limitations, in this paper, we proposed DeepFD, a learning-based fault diagnosis and localization framework which maps the fault localization task to a learning problem. In particular, it infers the suspicious fault types via monitoring the runtime features extracted during DNN model training and then locates the diagnosed faults in DL programs. It overcomes the limitations by identifying the root causes of faults in DL programs instead of neurons and diagnosing the faults by a learning approach instead of a set of hard-coded rules. The evaluation exhibits the potential of DeepFD. It correctly diagnoses 52% faulty DL programs, compared with around half (27%) achieved by the best state-of-the-art works. Besides, for fault localization, DeepFD also outperforms the existing works, correctly locating 42% faulty programs, which almost doubles the best result (23%) achieved by the existing works.
Some recent visual-based relocalization algorithms rely on deep learning methods to perform camera pose regression from image data. This paper focuses on the loss functions that embed the error between two poses to perform deep learning based camera pose regression. Existing loss functions are either difficult-to-tune multi-objective functions or present unstable reprojection errors that rely on ground truth 3D scene points and require a two-step training. To deal with these issues, we introduce a novel loss function which is based on a multiplane homography integration. This new function does not require prior initialization and only depends on physically interpretable hyperparameters. Furthermore, the experiments carried out on well established relocalization datasets show that it minimizes best the mean square reprojection error during training when compared with existing loss functions.
The investigation of uncertainty is of major importance in risk-critical applications, such as medical image segmentation. Belief function theory, a formal framework for uncertainty analysis and multiple evidence fusion, has made significant contributions to medical image segmentation, especially since the development of deep learning. In this paper, we provide an introduction to the topic of medical image segmentation methods using belief function theory. We classify the methods according to the fusion step and explain how information with uncertainty or imprecision is modeled and fused with belief function theory. In addition, we discuss the challenges and limitations of present belief function-based medical image segmentation and propose orientations for future research. Future research could investigate both belief function theory and deep learning to achieve more promising and reliable segmentation results.
Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms have been proposed as effective and efficient strategies. Understanding current algorithms is essential to find suitable methods or develop novel techniques for given tasks. In this paper, we perform a comprehensive survey on image augmentation for deep learning with a novel informative taxonomy. To get the basic idea why we need image augmentation, we introduce the challenges in computer vision tasks and vicinity distribution. Then, the algorithms are split into three categories; model-free, model-based, and optimizing policy-based. The model-free category employs image processing methods while the model-based method leverages trainable image generation models. In contrast, the optimizing policy-based approach aims to find the optimal operations or their combinations. Furthermore, we discuss the current trend of common applications with two more active topics, leveraging different ways to understand image augmentation, such as group and kernel theory, and deploying image augmentation for unsupervised learning. Based on the analysis, we believe that our survey gives a better understanding helpful to choose suitable methods or design novel algorithms for practical applications.
Training deep learning models takes an extremely long execution time and consumes large amounts of computing resources. At the same time, recent research proposed systems and compilers that are expected to decrease deep learning models runtime. An effective optimisation methodology in data processing is desirable, and the reduction of compute requirements of deep learning models is the focus of extensive research. In this paper, we address the neural network sub-graph transformation by exploring reinforcement learning (RL) agents to achieve performance improvement. Our proposed approach RLFlow can learn to perform neural network subgraph transformations, without the need for expertly designed heuristics to achieve a high level of performance. Recent work has aimed at applying RL to computer systems with some success, especially using model-free RL techniques. Model-based reinforcement learning methods have seen an increased focus in research as they can be used to learn the transition dynamics of the environment; this can be leveraged to train an agent using a hallucinogenic environment such as World Model (WM), thereby increasing sample efficiency compared to model-free approaches. WM uses variational auto-encoders and it builds a model of the system and allows exploring the model in an inexpensive way. In RLFlow, we propose a design for a model-based agent with WM which learns to optimise the architecture of neural networks by performing a sequence of sub-graph transformations to reduce model runtime. We show that our approach can match the state-of-the-art performance on common convolutional networks and outperforms by up to 5% those based on transformer-style architectures
With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity is readily available nowadays, which renders researchers an opportunity to tackle current geoscience applications in a fresh way. With the joint utilization of EO data, much research on multimodal RS data fusion has made tremendous progress in recent years, yet these developed traditional algorithms inevitably meet the performance bottleneck due to the lack of the ability to comprehensively analyse and interpret these strongly heterogeneous data. Hence, this non-negligible limitation further arouses an intense demand for an alternative tool with powerful processing competence. Deep learning (DL), as a cutting-edge technology, has witnessed remarkable breakthroughs in numerous computer vision tasks owing to its impressive ability in data representation and reconstruction. Naturally, it has been successfully applied to the field of multimodal RS data fusion, yielding great improvement compared with traditional methods. This survey aims to present a systematic overview in DL-based multimodal RS data fusion. More specifically, some essential knowledge about this topic is first given. Subsequently, a literature survey is conducted to analyse the trends of this field. Some prevalent sub-fields in the multimodal RS data fusion are then reviewed in terms of the to-be-fused data modalities, i.e., spatiospectral, spatiotemporal, light detection and ranging-optical, synthetic aperture radar-optical, and RS-Geospatial Big Data fusion. Furthermore, We collect and summarize some valuable resources for the sake of the development in multimodal RS data fusion. Finally, the remaining challenges and potential future directions are highlighted.
In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights. The number of approaches and applications in code understanding is growing, with deep learning techniques being used in many of them to better capture the information in code data. In this survey, we present a comprehensive overview of the structures formed from code data. We categorize the models for understanding code in recent years into two groups: sequence-based and graph-based models, further make a summary and comparison of them. We also introduce metrics, datasets and the downstream tasks. Finally, we make some suggestions for future research in structural code understanding field.
This book is intended for beginners who have no familiarity with deep learning. Our only expectation from readers is that they already have the basic programming skills in Python.