Search

In this paper, we design and evaluate the performance of the Multi-resolution Twinned Residual Auto-Encoders (MR-TRAE) model, a deep learning (DL)-based architecture specifically designed for achieving multi-resolution super-resolved images from low-resolution (LR) inputs at various scaling factors. For this purpose, we expand on the recently introduced Twinned Residual Auto-Encoders (TRAE) paradigm for single-image super-resolution (SISR) to extend it to the multi-resolution (MR) domain. The main contributions of this work include (i) the architecture of the MR-TRAE model, which utilizes cascaded trainable up-sampling modules for progressively increasing the spatial resolution of low-resolution (LR) input images at multiple scaling factors; (ii) a novel loss function designed for the joint and semi-blind training of all MR-TRAE model components; and (iii) a comprehensive analysis of the MR-TRAE trade-off between model complexity and performance. Furthermore, we thoroughly explore the connections between the MR-TRAE architecture and broader cognitive paradigms, including knowledge distillation, the teacher-student learning model, and hierarchical cognition. Performance evaluations of the MR-TRAE benchmarked against state-of-the-art models (such as U-Net, generative adversarial network (GAN)-based, and single-resolution baselines) were conducted using publicly available datasets. These datasets consist of LR computer tomography (CT) scans from patients with COVID-19. Our tests, which explored multi-resolutions at scaling factors × (2 , 4 , 8) , showed a significant finding: the MR-TRAE model can reduce training times by up to 60 % compared to those of the baselines, without a noticeable impact on achieved performance. [ABSTRACT FROM AUTHOR]

Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks (CycleGANs) are two emerging machine learning models that, up to now, have been used as generative models, i.e., to generate output data sampled from a target probability distribution. However, these models are also equipped with encoding modules, which, after weakly supervised training, could be, in principle, exploited for the extraction of hidden features from the input data. At the present time, how these extracted features could be effectively exploited for classification tasks is still an unexplored field. Hence, motivated by this consideration, in this paper, we develop and numerically test the performance of a novel inference engine that relies on the exploitation of BiGAN and CycleGAN-learned hidden features for the detection of COVID-19 disease from other lung diseases in computer tomography (CT) scans. In this respect, the main contributions of the paper are twofold. First, we develop a kernel density estimation (KDE)-based inference method, which, in the training phase, leverages the hidden features extracted by BiGANs and CycleGANs for estimating the (a priori unknown) probability density function (PDF) of the CT scans of COVID-19 patients and, then, in the inference phase, uses it as a target COVID-PDF for the detection of COVID diseases. As a second major contribution, we numerically evaluate and compare the classification accuracies of the implemented BiGAN and CycleGAN models against the ones of some state-of-the-art methods, which rely on the unsupervised training of convolutional autoencoders (CAEs) for attaining feature extraction. The performance comparisons are carried out by considering a spectrum of different training loss functions and distance metrics. The obtained classification accuracies of the proposed CycleGAN-based (resp., BiGAN-based) models outperform the corresponding ones of the considered benchmark CAE-based models of about 16% (resp., 14%). [ABSTRACT FROM AUTHOR]

We present a probabilistic method for classifying chest computed tomography (CT) scans into COVID-19 and non-COVID-19. To this end, we design and train, in an unsupervised manner, a deep convolutional autoencoder (DCAE) on a selected training data set, which is composed only of COVID-19 CT scans. Once the model is trained, the encoder can generate the compact hidden representation (the hidden feature vectors) of the training data set. Afterwards, we exploit the obtained hidden representation to build up the target probability density function (PDF) of the training data set by means of kernel density estimation (KDE). Subsequently, in the test phase, we feed a test CT into the trained encoder to produce the corresponding hidden feature vector, and then, we utilise the target PDF to compute the corresponding PDF value of the test image. Finally, this obtained value is compared to a threshold to assign the COVID-19 label or non-COVID-19 to the test image. We numerically check our approach's performance (i.e. test accuracy and training times) by comparing it with those of some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researchers in the current century. The development of an automatic diagnostic tool, able to detect the disease in its early stage, could undoubtedly offer a great advantage to the battle against the pandemic. In this regard, most of the research efforts have been focused on the application of Deep Learning (DL) techniques to chest images, including traditional chest X-rays (CXRs) and Computed Tomography (CT) scans. Although these approaches have demonstrated their effectiveness in detecting the COVID-19 disease, they are of huge computational complexity and require large datasets for training. In addition, there may not exist a large amount of COVID-19 CXRs and CT scans available to researchers. To this end, in this paper, we propose an approach based on the evaluation of the histogram from a common class of images that is considered as the target. A suitable inter-histogram distance measures how this target histogram is far from the histogram evaluated on a test image: if this distance is greater than a threshold, the test image is labeled as anomaly, i.e., the scan belongs to a patient affected by COVID-19 disease. Extensive experimental results and comparisons with some benchmark state-of-the-art methods support the effectiveness of the developed approach, as well as demonstrate that, at least when the images of the considered datasets are homogeneous enough (i.e., a few outliers are present), it is not really needed to resort to complex-to-implement DL techniques, in order to attain an effective detection of the COVID-19 disease. Despite the simplicity of the proposed approach, all the considered metrics (i.e., accuracy, precision, recall, and F-measure) attain a value of 1.0 under the selected datasets, a result comparable to the corresponding state-of-the-art DNN approaches, but with a remarkable computational simplicity. [ABSTRACT FROM AUTHOR]

The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early exits, executed atop virtualized multi-tier Fog platforms, makes feasible the real-time and energy-efficient execution of analytics required by future Internet applications. However, until now, toolkits for the evaluation of energy-vs.-delay performance of the inference phase of CDNNs executed on such platforms, have not been available. Motivated by these considerations, in this contribution, we present DeepFogSim. It is a MATLAB-supported software toolbox aiming at testing the performance of virtualized technological platforms for the real-time distributed execution of the inference phase of CDNNs with early exits under IoT realms. The main peculiar features of the proposed DeepFogSim toolbox are that: (i) it allows the joint dynamic energy-aware optimization of the Fog-hosted computing-networking resources under hard constraints on the tolerated inference delays; (ii) it allows the repeatable and customizable simulation of the resulting energy-delay performance of the overall Fog execution platform; (iii) it allows the dynamic tracking of the performed resource allocation under time-varying operating conditions and/or failure events; and (iv) it is equipped with a user-friendly Graphic User Interface (GUI) that supports a number of graphic formats for data rendering. Some numerical results give evidence for about the actual capabilities of the proposed DeepFogSim toolbox. [ABSTRACT FROM AUTHOR]

In parallel with the vast medical research on clinical treatment of COVID-19, an important action to have the disease completely under control is to carefully monitor the patients. What the detection of COVID-19 relies on most is the viral tests, however, the study of X-rays is helpful due to the ease of availability. There are various studies that employ Deep Learning (DL) paradigms, aiming at reinforcing the radiography-based recognition of lung infection by COVID-19. In this regard, we make a comparison of the noteworthy approaches devoted to the binary classification of infected images by using DL techniques, then we also propose a variant of a convolutional neural network (CNN) with optimized parameters, which performs very well on a recent dataset of COVID-19. The proposed model's effectiveness is demonstrated to be of considerable importance due to its uncomplicated design, in contrast to other presented models. In our approach, we randomly put several images of the utilized dataset aside as a hold out set; the model detects most of the COVID-19 X-rays correctly, with an excellent overall accuracy of 99.8%. In addition, the significance of the results obtained by testing different datasets of diverse characteristics (which, more specifically, are not used in the training process) demonstrates the effectiveness of the proposed approach in terms of an accuracy up to 93%. [ABSTRACT FROM AUTHOR]