Automated Detection of COVID-19 from Multimodal Imaging Data Using Optimized Convolutional Neural Network Model

The incidence of COVID-19, a virus that is responsible for infections in the upper respiratory tract and lungs, witnessed a daily rise in fatalities throughout the pandemic. The timely identification of COVID-19 can contribute to the formulation of strategies to control the disease and the selection of an appropriate treatment pathway. Given the necessity for broader COVID-19 diagnosis, researchers have developed more advanced, rapid, and efficient detection methods. By conducting an initial comparative analysis of various widely used convolutional neural network (CNN) models, we determine an appropriate CNN model. Subsequently, we enhance the chosen CNN model using the feature fusion strategy from multi-modal imaging datasets. Moreover, the Jaya optimization technique is employed to determine the optimal weighting for merging these dual features into a single feature vector. An SVM classifier is employed to categorize samples as either COVID-19 positive or negative. For the purpose of experimentation, a standard dataset consisting of 10,000 samples is used, divided equally between COVID-19 positive and negative classes. The experimental outcomes demonstrate that the proposed fine-tuned system, coupled with optimization techniques for multi-modal data, exhibits superior performance, achieving accuracy rates of 98.7% as compared to the existing state-of-the-art network models.

Newly defined allergens in the WHO/IUIS Allergen Nomenclature Database during 01/2019-03/2021

The WHO/IUIS Allergen Nomenclature Database (http://allergen.org) provides up‐to‐date expert‐reviewed data on newly discovered allergens and their unambiguous nomenclature to allergen researchers worldwide. This review discusses the 106 allergens that were accepted by the Allergen Nomenclature Sub‐Committee between 01/2019 and 03/2021. Information about protein family membership, patient cohorts, and assays used for allergen characterization is summarized. A first allergenic fungal triosephosphate isomerase, Asp t 36, was discovered in Aspergillus terreus. Plant allergens contained 1 contact, 38 respiratory, and 16 food allergens. Can s 4 from Indian hemp was identified as the first allergenic oxygen‐evolving enhancer protein 2 and Cic a 1 from chickpeas as the first allergenic group 4 late embryogenesis abundant protein. Among the animal allergens were 19 respiratory, 28 food, and 3 venom allergens. Important discoveries include Rap v 2, an allergenic paramyosin in molluscs, and Sal s 4 and Pan h 4, allergenic fish tropomyosins. Paramyosins and tropomyosins were previously known mainly as arthropod allergens. Collagens from barramundi, Lat c 6, and salmon, Sal s 6, were the first members from the collagen superfamily added to the database. In summary, the addition of 106 new allergens to the previously listed 930 allergens reflects the continuous linear growth of the allergen database. In addition, 17 newly described allergen sources were included.

Computer-aided diagnosis system for the classification of multi-class kidney abnormalities in the noisy ultrasound images

BACKGROUND AND OBJECTIVE

The primary causes of kidney failure are chronic and polycystic kidney diseases. Cyst, stone, and tumor development lead to chronic kidney diseases that commonly impair kidney functions. The kidney diseases are asymptomatic and do not show any significant symptoms at its initial stage. Therefore, diagnosing the kidney diseases at their earlier stage is required to prevent the loss of kidney function and kidney failure.

METHODS

This paper proposes a computer-aided diagnosis (CAD) system for detecting multi-class kidney abnormalities from ultrasound images. The presented CAD system uses a pre-trained ResNet-101 model for extracting the features and support vector machine (SVM) classifier for the classification purpose. Ultrasound images usually gets affected by speckle noise that degrades the image quality and performance of the CAD system. Hence, it is necessary to remove speckle noise from the ultrasound images. Therefore, a CAD based system is proposed with the despeckling module using a deep residual learning network (RLN) to reduce speckle noise. Pre-processing of ultrasound images using deep RLN helps to drastically improve the classification performance of the CAD system. The proposed CAD system achieved better prediction results when compared to the existing state-of-the-art methods.

RESULTS

To validate the proposed CAD system performance, the experiments have been carried out in the noisy kidney ultrasound images. The designed system framework achieved the maximum classification accuracy when compared to the existing approaches. The SVM classifier is selected for the CAD system based on performance comparison with various classifiers like K-nearest neighbour, tree, discriminant, Naive Bayes, and linear.

CONCLUSIONS

The proposed CAD system outperforms in classifying the noisy kidney ultrasound images precisely as compared to the existing state-of-the-art methods. Further, the CAD system is evaluated in terms of selectivity and sensitivity scores. The presented CAD system with the pre-processing module would serve as a real-time supporting tool for diagnosing multi-class kidney abnormalities from the ultrasound images.

An ensemble of deep neural networks for kidney ultrasound image classification

BACKGROUND AND OBJECTIVE

Chronic kidney disease is a worldwide health issue which includes not only kidney failure but also complications of reduced kidney functionality. Cyst formation, nephrolithiasis or kidney stone, and renal cell carcinoma or kidney tumor are the common kidney disorders which affects the functionality of kidneys. These disorders are typically asymptomatic, therefore early and automatic diagnosis of kidney disorders are required to avoid serious complications.

METHODS

This paper proposes an automatic classification of B-mode kidney ultrasound images based on the ensemble of deep neural networks (DNNs) using transfer learning. The ultrasound images are usually affected by speckle noise and quality selection in the ultrasound image is based on perception-based image quality evaluator score. Three variant datasets are given to the pre-trained DNN models for feature extraction followed by support vector machine for classification. The ensembling of different pre-trained DNNs like ResNet-101, ShuffleNet, and MobileNet-v2 are combined and final predictions are done by using the majority voting technique. By combining the predictions from multiple DNNs the ensemble model shows better classification performance than the individual models. The presented method proved its superiority when compared to the conventional and DNN based classification methods. The developed ensemble model classifies the kidney ultrasound images into four classes, namely, normal, cyst, stone, and tumor.

RESULTS

To highlight effectiveness of the proposed approach, the ensemble based approach is compared with the existing state-of-the-art methods and tested in the variants of ultrasound images like in quality and noisy conditions. The presented method resulted in maximum classification accuracy of 96.54% in testing with quality images and 95.58% in testing with noisy images. The performance of the presented approach is evaluated based on accuracy, sensitivity, and selectivity.

CONCLUSIONS

From the experimental analysis, it is clear that the ensemble of DNNs classifies the majority of images correctly and results in maximum classification accuracy as compared to the existing methods. This automatic classification approach is a supporting tool for the radiologists and nephrologists for precise diagnosis of kidney diseases.

Despeckling of clinical ultrasound images using deep residual learning

Background and objective Ultrasound is the non-radioactive imaging modality used in the diagnosis of various diseases related to the internal organs of the body. The presence of speckle noise in ultrasound image (UI) is inevitable and may affect resolution and contrast of the image. Existence of the speckle noise degrades the visual evaluation of the image. The despeckling of UI is a desirable pre-processing step in computer-aided UI based diagnosis systems. Methods This paper proposes a novel method for despeckling UIs using pre-trained residual learning network (RLN). Initially, RLN is trained with pristine and its corresponding noisy images in order to achieve a better performance. The developed method chooses a pre-trained RLN for despeckling UIs with less computational resources. But the training procedure of RLN from scratch is computationally demanding. The pre-trained RLN is a blind despeckling approach and does not require any fine tuning and noise level estimation. The presented approach shows superiority in the removal of speckle noise as compared to the existing state-of-art methods. Results To highlight the effectiveness of the proposed method the pristine images from the Waterloo dataset has been considered. The proposed pre-trained RLN based UI despeckling method resulted in a better peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) at different speckle noise levels. The no-reference image quality approach is adopted to ensure robustness of the established method for real time UI. From results it is obvious that, the performance of the proposed method is superior than the existing methods in terms of naturalness image quality evaluator (NIQE). Conclusions From the experimental results, it is clear that the proposed method outperforms the existing despeckling methods in terms of both artificially added and naturally occurring speckle images.

In vitro selection for adhesion of Plasmodium falciparum-infected erythrocytes to ABO antigens does not affect PfEMP1 and RIFIN expression

Plasmodium falciparum causes the most severe form of malaria in humans. The adhesion of the infected erythrocytes (IEs) to endothelial receptors (sequestration) and to uninfected erythrocytes (rosetting) are considered major elements in the pathogenesis of the disease. Both sequestration and rosetting appear to involve particular members of several IE variant surface antigens (VSAs) as ligands, interacting with multiple vascular host receptors, including the ABO blood group antigens. In this study, we subjected genetically distinct P. falciparum parasites to in vitro selection for increased IE adhesion to ABO antigens in the absence of potentially confounding receptors. The selection resulted in IEs that adhered stronger to pure ABO antigens, to erythrocytes, and to various human cell lines than their unselected counterparts. However, selection did not result in marked qualitative changes in transcript levels of the genes encoding the best-described VSA families, PfEMP1 and RIFIN. Rather, overall transcription of both gene families tended to decline following selection. Furthermore, selection-induced increases in the adhesion to ABO occurred in the absence of marked changes in immune IgG recognition of IE surface antigens, generally assumed to target mainly VSAs. Our study sheds new light on our understanding of the processes and molecules involved in IE sequestration and rosetting.