Instantaneous ultrasound computed tomography using deep convolutional neural networks

Ultrasound computed tomography (USCT) is an emerging imaging modality that holds great promise for breast imaging. Full-waveform inversion (FWI)-based image reconstruction methods incorporate accurate wave physics to produce high spatial resolution quantitative images of speed of sound or other acoustic properties of the breast tissues. However, FWI reconstruction is computationally expensive, which limits its application in a clinical setting. This contribution investigates using the use of a convolutional neural network (CNN) to learn a mapping from USCT data to speed of sound estimates. The CNN was trained using a supervised approach that employed a large set of anatomically and physiologically realistic numerical breast phantoms (NBPs) and simulated USCT measurements. Once trained, this CNN can then be evaluated for real-time FWI image reconstruction from USCT data. The performance of the proposed method was assessed and compared against FWI using a hold-out sample of 41 NBPs and corresponding USCT images. Accuracy was measured using relative mean square error (RMSE) and structural self-similarity index measure (SSIM). This numerical experiment demonstrates that a supervised learning model can achieve accuracy comparable to FWI, while significantly reducing computational time and memory requirements.

The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition has received far less attention as an accelerator target. This is surprising, as video recognition is more computationally intensive than image recognition, and video traffic is predicted to be the majority of internet traffic in the coming years. This paper fills the gap between algorithmic and hardware advances for video recognition by providing a design space exploration and flexible architecture for accelerating 3D Convolutional Neural Networks (3D CNNs)—the core kernel in modern video understanding. When compared to (2D) CNNs used for image recognition, efficiently accelerating 3D CNNs poses a significant engineering challenge due to their large (and variable over time) memory footprint and higher dimensionality. To address these challenges, we design a novel accelerator called Morph, that can adaptively support different spatial and temporal tiling strategies depending on the needs of each layer of each target 3D CNN. We codesign a software infrastructure alongside the Morph hardware to find good-fit parameters to control the hardware. Evaluated on state-of-the-art 3D CNNs, Morph achieves up to 2.7× (1.9× average) reduction in energy consumption and improves performance/watt up to 4.4× (3× average) compared to a baseline 3D CNN accelerator, with an area overhead of 2%. Morph further achieves a 11.6× average energy reduction on 3D CNNs when compared to Eyeriss, a popular 2D CNN accelerator, while reducing efficiency compared to Eyeriss on a 2D CNN by 71%.

Over large areas, land cover classification has conventionally been undertaken using satellite time series. Typically temporal metric percentiles derived from single pixel location time series have been used to take advantage of spectral differences among land cover classes over time and to minimize the impact of missing observations. Deep convolutional neural networks (CNNs) have demonstrated potential for land cover classification of single date images. However, over large areas and using time series their application is complicated because they are sensitive to missing observations and they may misclassify small and spatially fragmented surface features due to their spatial patch-based implementation. This study demonstrates, for the first time, a one-dimensional (1D) CNN single pixel time series land classification approach that uses temporal percentile metrics and that does not have these issues. This is demonstrated for all the Conterminous United States (CONUS) considering two different 1D CNN structures with 5 and 8 layers, respectively. CONUS 30 m land cover classifications were derived using all the available Landsat-5 and -7 imagery over a seven-month growing season in 2011 with 3.3 million 30 m land cover class labelled samples extracted from the contemporaneous CONUS National Land Cover Database (NLCD) 16 class land cover product. The 1D CNNs and, a conventional random forest model, were trained using 10%, 50% and 90% samples, and the classification accuracies were evaluated with an independent 10% proportion. Temporal metrics were classified using 5, 7 and 9 percentiles for each of five Landsat reflective wavelength bands and their eight band ratios. The CONUS and detailed 150 × 150 km classification results demonstrate that the approach is effective at scale and locally. The 1D CNN classification land cover class boundaries were preserved for small axis dimension features, such as roads and rivers, with no stripes or anomalous spatial patterns. The 8-layer 1D CNN provided the highest overall classification accuracies and both the 5-layer and 8-layer 1D CNN architectures provided higher accuracies than the random forest by 1.9% - 2.8% which as all the accuracies were > 83% is a meaningful increase. The CONUS overall classification accuracies increased marginally with the number of percentiles (86.21%, 86.40%, and 86.43% for 5, 7 and 9 percentiles, respectively) using the 8-layer 1D-CNN. Class specific producer and user accuracies were quantified, with lower accuracies for the developed land, crop and pasture/hay classes, but no systematic pattern among classes with respect to the number of temporal percentiles used. Application of the trained model to a different year of CONUS Landsat ARD showed moderately decreased accuracy (80.79% for 7 percentiles) that we illustrate is likely due to different intra-annual surface variations between years. These encouraging results are discussed with recommended research for deep learning using temporal metric percentiles.

Gait recognition is a noncontact biometric procedure that determines the identity or health status of a person by analyzing his or her walking posture and habits, including skeletal and joint movements. The most remarkable feature of this method is the possibility of conducting recognition without demanding much cooperation from participants. Therefore, this recognition technique has attracted much attention from scholars. Additionally, because of the rapid development of graphics processing unit technology, related hardware and computation performance, the applications of deep-learning technology are considerably enhanced. The objective of this study was to apply a deep neural network (DNN), which employs deep-learning technology, to achieve gait-based automatic pedestrian detection and recognition. In contrast to using wearable devices to precisely capture skeletal and joint movements, pedestrian color-image sequences were used as input in this study. Subsequently, a pretraining convolutional neural network (CNN) was employed to capture pedestrian location and extract pedestrian dense optical flow to serve as concrete low-level feature inputs. Then, a finely-tuned DNN based on the wide residual network was employed to extract high-level abstract features. In addition, to overcome the difficulty of obtaining local temporal features by using a 2D CNN, part of the 3D convolutional structure was introduced into the CNN. This design enabled use of limited memory to acquire more effective features and enhance the DNN performance. The experimental results show that the proposed method has exceptional performance for pedestrian detection and recognition.

Automated detection of leukemia by pretrained deep neural networks and transfer learning: A comparison

An exhaustive measurement of re-sampling detection in lossy compressed images using deep learning approach

The unmanned aerial vehicles (UAVs) have been extensively used in providing intelligence such as target tracking. In our field experiments, a pre-trained deep neural network (DNN) is deployed on the UAV to identify a target from the captured video frames and enable UAV to keep tracking. However, tracking in real time by the DNN requires a lot of computational resources. This motivates us to consider offloading this type of machine learning (ML) tasks to a mobile edge computing (MEC) server. Specifically, we propose a novel hierarchical ML tasks distribution framework for the UAV tracking system, where the UAV is embedded with lower layers of the pre-trained convolutional neural network (CNN) model due to its limited computing capability, while the MEC server with rich computing resources will handle the higher layers of the CNN model. An optimization problem is formulated to minimize the CNN inference delay while taking into account the communications delay, computing time, and ML error. Insights are provided to understand the tradeoff between communications and ML computing in offloading decisions. Numerical results demonstrate the effectiveness of the proposed ML tasks distribution framework with the optimized offloading strategy.

When using convolutional neural networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice [two-dimensional (2D)] or whole volumes [three-dimensional (3D)]. One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as input and produce a prediction for at least the central slice. This approach gives the network the possibility to capture 3D spatial information, with only a minor additional computational cost. In this study, we systematically evaluate the segmentation performance and computational costs of this pseudo-3D approach as a function of the number of input slices, and compare the results to conventional end-to-end 2D and 3D CNNs, and to triplanar orthogonal 2D CNNs. The standard pseudo-3D method regards the neighboring slices as multiple input image channels. We additionally design and evaluate a novel, simple approach where the input stack is a volumetric input that is repeatably convolved in 3D to obtain a 2D feature map. This 2D map is in turn fed into a standard 2D network. We conducted experiments using two different CNN backbone architectures and on eight diverse data sets covering different anatomical regions, imaging modalities, and segmentation tasks. We found that while both pseudo-3D methods can process a large number of slices at once and still be computationally much more efficient than fully 3D CNNs, a significant improvement over a regular 2D CNN was only observed with two of the eight data sets. triplanar networks had the poorest performance of all the evaluated models. An analysis of the structural properties of the segmentation masks revealed no relations to the segmentation performance with respect to the number of input slices. A post hoc rank sum test which combined all metrics and data sets yielded that only our newly proposed pseudo-3D method with an input size of 13 slices outperformed almost all methods. In the general case, multislice inputs appear not to improve segmentation results over using 2D or 3D CNNs. For the particular case of 13 input slices, the proposed novel pseudo-3D method does appear to have a slight advantage across all data sets compared to all other methods evaluated in this work.

Traditionally, analytical methods have been used to solve imaging problems such as image restoration, inpainting, and superresolution (SR). In recent years, the fields of machine and deep learning have gained a lot of momentum in solving such imaging problems, often surpassing the performance provided by analytical approaches. Unlike analytical methods for which the problem is explicitly defined and domain-knowledge carefully engineered into the solution, deep neural networks (DNNs) do not benefit from such prior knowledge and instead make use of large data sets to learn the unknown solution to the inverse problem. In this article, we review deep-learning techniques for solving such inverse problems in imaging. More specifically, we review the popular neural network architectures used for imaging tasks, offering some insight as to how these deep-learning tools can solve the inverse problem. Furthermore, we address some fundamental questions, such as how deeplearning and analytical methods can be combined to provide better solutions to the inverse problem in addition to providing a discussion on the current limitations and future directions of the use of deep learning for solving inverse problem in imaging.

Recently, three dimensional (3D) convolutional neural networks (CNNs) have emerged as dominant methods to capture spatiotemporal representations in videos, by adding to pre-existing 2D CNNs a third, temporal dimension. Such 3D CNNs, however, are anti-causal (i.e., they exploit information from both the past and the future frames to produce feature representations, thus preventing their use in online settings), constrain the temporal reasoning horizon to the size of the temporal convolution kernel, and are not temporal resolution-preserving for video sequence-to-sequence modelling, as, for instance, in action detection. To address these serious limitations, here we present a new 3D CNN architecture for the causal/online processing of videos. Namely, we propose a novel Recurrent Convolutional Network (RCN), which relies on recurrence to capture the temporal context across frames at each network level. Our network decomposes 3D convolutions into (1) a 2D spatial convolution component, and (2) an additional hidden state 1 × 1 convolution, applied across time. The hidden state at any time t is assumed to depend on the hidden state at t - 1 and on the current output of the spatial convolution component. As a result, the proposed network: (i) produces causal outputs, (ii) provides flexible temporal reasoning, (iii) preserves temporal resolution. Our experiments on the largescale large Kinetics and MultiThumos datasets show that the proposed method performs comparably to anti-causal 3D CNNs, while being causal and using fewer parameters.

Recent work has shown that deep convolutional neural network is capable of solving inverse problems in computational imaging, and recovering the stress field of the loaded object from the photoelastic fringe pattern can also be regarded as an inverse problem solving process. However, the formation of the fringe pattern is affected by the geometry of the specimen and experimental configuration. When the loaded object produces complex fringe distribution, the traditional stress analysis methods still face difficulty in unwrapping. In this study, a deep convolutional neural network based on the encoder–decoder structure is proposed, which can accurately decode stress distribution information from complex photoelastic fringe images generated under different experimental configurations. The proposed method is validated on a synthetic dataset, and the quality of stress distribution images generated by the network model is evaluated using mean squared error (MSE), structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and other evaluation indexes. The results show that the proposed stress recovery network can achieve an average performance of more than 0.99 on the SSIM.

At present, in the field of video-based human action recognition, deep neural networks are mainly divided into two branches: the 2D convolutional neural network (CNN) and 3D CNN. However, 2D CNN’s temporal and spatial feature extraction processes are independent of each other, which means that it is easy to ignore the internal connection, affecting the performance of recognition. Although 3D CNN can extract the temporal and spatial features of the video sequence at the same time, the parameters of the 3D model increase exponentially, resulting in the model being difficult to train and transfer. To solve this problem, this article is based on 3D CNN combined with a residual structure and attention mechanism to improve the existing 3D CNN model, and we propose two types of human action recognition models (the Residual 3D Network (R3D) and Attention Residual 3D Network (AR3D)). Firstly, in this article, we propose a shallow feature extraction module and improve the ordinary 3D residual structure, which reduces the parameters and strengthens the extraction of temporal features. Secondly, we explore the application of the attention mechanism in human action recognition and design a 3D spatio-temporal attention mechanism module to strengthen the extraction of global features of human action. Finally, in order to make full use of the residual structure and attention mechanism, an Attention Residual 3D Network (AR3D) is proposed, and its two fusion strategies and corresponding model structure (AR3D_V1, AR3D_V2) are introduced in detail. Experiments show that the fused structure shows different degrees of performance improvement compared to a single structure.

Recently, several convolutional neural networks have been proposed not only for 2D images, but also for 3D and 4D volume segmentation. Nevertheless, due to the large data size of the latter, acquiring a sufficient amount of training annotations is much more strenuous than in 2D images. For 4D time-series tomograms, this is usually handled by segmenting the constituent tomograms independently through time with 3D convolutional neural networks. Inter-volume information is therefore not utilized, potentially leading to temporal incoherence. In this paper, we attempt to resolve this by proposing two hidden Markov model variants that refine 4D segmentation labels made by 3D convolutional neural networks working on each time point. Our models utilize not only inter-volume information, but also the prediction confidence generated by the 3D segmentation convolutional neural networks themselves. To the best of our knowledge, this is the first attempt to refine 4D segmentations made by 3D convolutional neural networks using hidden Markov models. During experiments we test our models, qualitatively, quantitatively and behaviourally, using prespecified segmentations. We demonstrate in the domain of time series tomograms which are typically undersampled to allow more frequent capture; a particularly challenging problem. Finally, our dataset and code is publicly available.

The convolutional neural network (CNN) is a potent and popular neural network types and has been crucial to deep learning in recent years. A standard CNN which is known as 2-dimensions CNN was first proposed to solve image classification problems at first. With advancements in science and technology, as well as the growth of the internet, tasks involving video analysis have received increased attention in recent years. As a result, it was suggested that a 3-dimensions convolutional neural network (3D CNN) be applied to tackle 3D image processing or video analysis. 3D CNN is primarily used in the field of human activity recognition, video classification, medical imaging detection, and so on. This paper offers a succinct introduction to the general architecture and representative models of 3D CNN, contrasts the variations between 2D CNN and 3D CNN, explores the widely used models derived from 3D CNN, and displays the application outcomes of 3D CNN.

In recent years, growing interest in deep learning neural networks has raised a question on how they can be used for effective processing of high-dimensional datasets produced by hyperspectral imaging (HSI). HSI, traditionally viewed as being within the scope of remote sensing, is used in non-invasive substance classification. One of the areas of potential application is forensic science, where substance classification on the scenes is important. An example problem from that area—blood stain classification—is a case study for the evaluation of methods that process hyperspectral data. To investigate the deep learning classification performance for this problem we have performed experiments on a dataset which has not been previously tested using this kind of model. This dataset consists of several images with blood and blood-like substances like ketchup, tomato concentrate, artificial blood, etc. To test both the classic approach to hyperspectral classification and a more realistic application-oriented scenario, we have prepared two different sets of experiments. In the first one, Hyperspectral Transductive Classification (HTC), both a training and a test set come from the same image. In the second one, Hyperspectral Inductive Classification (HIC), a test set is derived from a different image, which is more challenging for classifiers but more useful from the point of view of forensic investigators. We conducted the study using several architectures like 1D, 2D and 3D convolutional neural networks (CNN), a recurrent neural network (RNN) and a multilayer perceptron (MLP). The performance of the models was compared with baseline results of Support Vector Machine (SVM). We have also presented a model evaluation method based on t-SNE and confusion matrix analysis that allows us to detect and eliminate some cases of model undertraining. Our results show that in the transductive case, all models, including the MLP and the SVM, have comparative performance, with no clear advantage of deep learning models. The Overall Accuracy range across all models is 98–100% for the easier image set, and 74–94% for the more difficult one. However, in a more challenging inductive case, selected deep learning architectures offer a significant advantage; their best Overall Accuracy is in the range of 57–71%, improving the baseline set by the non-deep models by up to 9 percentage points. We have presented a detailed analysis of results and a discussion, including a summary of conclusions for each tested architecture. An analysis of per-class errors shows that the score for each class is highly model-dependent. Considering this and the fact that the best performing models come from two different architecture families (3D CNN and RNN), our results suggest that tailoring the deep neural network architecture to hyperspectral data is still an open problem.