Purpose
COVID-19 has infected millions of people worldwide. One of the most important hurdles in controlling the spread of this disease is the inefficiency and lack of medical tests. Computed tomography (CT) scans are promising in providing accurate and fast detection of COVID-19. However, determining COVID-19 requires highly trained radiologists and suffers from inter-observer variability. To remedy these limitations, this paper introduces an automatic methodology based on an ensemble of deep transfer learning for the detection of COVID-19.
Methods
A total of 15 pre-trained convolutional neural networks (CNNs) architectures: EfficientNets(B0-B5), NasNetLarge, NasNetMobile, InceptionV3, ResNet-50, SeResnet 50, Xception, DenseNet121, ResNext50 and Inception_resnet_v2 are used and then fine-tuned on the target task. After that, we built an ensemble method based on majority voting of the best combination of deep transfer learning outputs to further improve the recognition performance. We have used a publicly available dataset of CT scans, which consists of 349 CT scans labeled as being positive for COVID-19 and 397 negative COVID-19 CT scans that are normal or contain other types of lung diseases.
Results
The experimental results indicate that the majority voting of 5 deep transfer learning architecture with EfficientNetB0, EfficientNetB3, EfficientNetB5, Inception_resnet_v2, and Xception has the higher results than the individual transfer learning structure and among the other models based on precision (0.857), recall (0.854) and accuracy (0.85) metrics in diagnosing COVID-19 from CT scans.
Conclusion
Our study based on an ensemble deep transfer learning system with different pre-trained CNNs architectures can work well on a publicly available dataset of CT images for the diagnosis of COVID-19 based on CT scans.
Accurate and noninvasive monitoring of the depth of anesthesia (DoA) is highly desirable. Since the anesthetic drugs act mainly on the central nervous system, the analysis of brain activity using electroencephalogram (EEG) is very useful. This paper proposes a novel automated method for assessing the DoA using EEG. First, 11 features including spectral, fractal, and entropy are extracted from EEG signal and then, by applying an algorithm according to exhaustive search of all subsets of features, a combination of the best features (Beta-index, sample entropy, shannon permutation entropy, and detrended fluctuation analysis) is selected. Accordingly, we feed these extracted features to a new neurofuzzy classification algorithm, adaptive neurofuzzy inference system with linguistic hedges (ANFIS-LH). This structure can successfully model systems with nonlinear relationships between input and output, and also classify overlapped classes accurately. ANFIS-LH, which is based on modified classical fuzzy rules, reduces the effects of the insignificant features in input space, which causes overlapping and modifies the output layer structure. The presented method classifies EEG data into awake, light, general, and deep states during anesthesia with sevoflurane in 17 patients. Its accuracy is 92% compared to a commercial monitoring system (response entropy index) successfully. Moreover, this method reaches the classification accuracy of 93% to categorize EEG signal to awake and general anesthesia states by another database of propofol and volatile anesthesia in 50 patients. To sum up, this method is potentially applicable to a new real-time monitoring system to help the anesthesiologist with continuous assessment of DoA quickly and accurately.
The automatic detection of end-diastole and end-systole frames of echocardiography images is the first step for calculation of the ejection fraction, stroke volume and some other features related to heart motion abnormalities. In this paper, the manifold learning algorithm is applied on 2D echocardiography images to find out the relationship between the frames of one cycle of heart motion. By this approach the nonlinear embedded information in sequential images is represented in a two-dimensional manifold by the LLE algorithm and each image is depicted by a point on reconstructed manifold. There are three dense regions on the manifold which correspond to the three phases of cardiac cycle ('isovolumetric contraction', 'isovolumetric relaxation', 'reduced filling'), wherein there is no prominent change in ventricular volume. By the fact that the end-systolic and end-diastolic frames are in isovolumic phases of the cardiac cycle, the dense regions can be used to find these frames. By calculating the distance between consecutive points in the manifold, the isovolumic frames are mapped on the three minimums of the distance diagrams which were used to select the corresponding images. The minimum correlation between these images leads to detection of end-systole and end-diastole frames. The results on six healthy volunteers have been validated by an experienced echo cardiologist and depict the usefulness of the presented method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.