Background The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, especially in underdeveloped countries. There is a clear need to develop novel computer-assisted diagnosis tools to provide rapid and cost-effective screening in places where massive traditional testing is not feasible. Lung ultrasound is a portable, easy to disinfect, low cost and non-invasive tool that can be used to identify lung diseases. Computer-assisted analysis of lung ultrasound imagery is a relatively recent approach that has shown great potential for diagnosing pulmonary conditions, being a viable alternative for screening and diagnosing COVID-19. Objective To evaluate and compare the performance of deep-learning techniques for detecting COVID-19 infections from lung ultrasound imagery. Methods We adapted different pre-trained deep learning architectures, including VGG19, InceptionV3, Xception, and ResNet50. We used the publicly available POCUS dataset comprising 3326 lung ultrasound frames of healthy, COVID-19, and pneumonia patients for training and fine-tuning. We conducted two experiments considering three classes (COVID-19, pneumonia, and healthy) and two classes (COVID-19 versus pneumonia and COVID-19 versus non-COVID-19) of predictive models. The obtained results were also compared with the POCOVID-net model. For performance evaluation, we calculated per-class classification metrics (Precision, Recall, and F1-score) and overall metrics (Accuracy, Balanced Accuracy, and Area Under the Receiver Operating Characteristic Curve). Lastly, we performed a statistical analysis of performance results using ANOVA and Friedman tests followed by post-hoc analysis using the Wilcoxon signed-rank test with the Holm’s step-down correction. Results InceptionV3 network achieved the best average accuracy (89.1%), balanced accuracy (89.3%), and area under the receiver operating curve (97.1%) for COVID-19 detection from bacterial pneumonia and healthy lung ultrasound data. The ANOVA and Friedman tests found statistically significant performance differences between models for accuracy, balanced accuracy and area under the receiver operating curve. Post-hoc analysis showed statistically significant differences between the performance obtained with the InceptionV3-based model and POCOVID-net, VGG19-, and ResNet50-based models. No statistically significant differences were found in the performance obtained with InceptionV3- and Xception-based models. Conclusions Deep learning techniques for computer-assisted analysis of lung ultrasound imagery provide a promising avenue for COVID-19 screening and diagnosis. Particularly, we found that the InceptionV3 network provides the most promising predictive results from all AI-based techniques evaluated in this work. InceptionV3- and Xception-based models can be used to further develop a viable computer-assisted screening tool for COVID-19 based on ultrasound imagery.
Multioriented text detection and recognition in natural scene images are still challenges in the document analysis and computer vision communities. In particular, character segmentation plays an important role in the complete end-to-end recognition system performance. In this work, a robust multioriented text detection and segmentation method based on a biological visual system model is proposed. The proposed method exploits the local energy model instead of a common approach based on variations of local image pixel intensities. Features such as lines and edges are obtained by searching for the maximum local energy utilizing the scale-space monogenic signal framework. The candidate text components are extracted from maximally stable extremal regions of the local phase information of the image. The candidate regions are filtered by their phase congruency and classified as text and nontext components by the AdaBoost classifier. Finally, misclassified characters are restored, and all final characters are grouped into words. Experimental results show that the proposed text detection and segmentation method is invariant to scale and rotation changes and robust to perspective distortions, blurring, low resolution, and illumination variations (low contrast, high brightness, shadows, and nonuniform illumination). Besides, the proposed method achieves often a better performance compared with state-of-the-art methods on typical natural scene datasets.
Electrical resistance tomography (ERT) is a nondestructive evaluation technique that uses the internal conductivity variations of materials to assess structural integrity. Due to the low instrumentation required, the widespread use of ERT in the aerospace industry for monitoring the accumulation of damage in aircraft components can lead to significant reductions in inspections and maintenance costs. However, implementing the ERT method for mapping the damage state of structural components made of carbon fiber reinforced polymeric (CFRP) composites is challenging due to the inability of this method to distinguish between damage modes such as delamination and matrix cracking. This article explores the combined use of ERT and machine learning algorithms such as neural networks, random forests, k-nearest neighbors, and support vector machines to classify and characterize delamination and matrix cracking damage in CFRP laminates. Results show that the proposed classification algorithms can successfully estimate the damage severity of delaminated composites in the presence of matrix cracking. Similarly, the classification algorithms can characterize these independent damage modes with an accuracy of 95%. The algorithms showed robustness to predict the electrical resistance variations of damaged composites and characterize delamination and matrix cracking damage even when intrinsic noise was considered. Although neural networks characterized damage with the highest accuracy, these algorithms were also the most sensitive to noise. For applications where instrumentation noise cannot be completely removed from the ERT signals, the use of nearest neighbors is thus recommended.
Illumination-invariant method for computing local feature points and descriptors, referred to as LUminance Invariant Feature Transform (LUIFT), is proposed. The method helps us to extract the most significant local features in images degraded by nonuniform illumination, geometric distortions, and heavy scene noise. The proposed method utilizes image phase information rather than intensity variations, as most of the state-of-the-art descriptors. Thus, the proposed method is robust to nonuniform illuminations and noise degradations. In this work, we first use the monogenic scale-space framework to compute the local phase, orientation, energy, and phase congruency from the image at different scales. Then, a modified Harris corner detector is applied to compute the feature points of the image using the monogenic signal components. The final descriptor is created from the histograms of oriented gradients of phase congruency. Computer simulation results show that the proposed method yields a superior feature detection and matching performance under illumination change, noise degradation, and slight geometric distortions comparing with that of the state-of-the-art descriptors.
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.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.