PE-Ynet: a novel attention-based multi-task model for pulmonary embolism detection using CT pulmonary angiography (CTPA) scan images.

Pulmonary Embolism (PE) has diverse manifestations with different etiologies such as venous thromboembolism, septic embolism, and paradoxical embolism. In this study, a novel attention-based multi-task model is proposed for PE segmentation and detection from Computed Tomography Pulmonary Angiography (CTPA) images. A Y-Net architecture is used to implement this model, which facilitates segmentation and classification jointly, improving performance and efficiency. It is leveraged with Multi Head Attention (MHA), which allows the model to focus on important regions of the image while suppressing irrelevant information, improving the accuracy of the segmentation and detection tasks. The proposed PE-YNet model is tested with two public datasets, achieving a maximum mean detection and segmentation accuracy of 99.89% and 99.83%, respectively, on the CAD-PE challenge dataset. Similarly, it also achieves a detection accuracy of 99.75% and a segmentation accuracy of 99.81% on the FUMPE dataset. Additionally, sensitivity analysis also shows a high sensitivity of 0.9885 for the localization error ɛ = 0 for the CAD-PE dataset, demonstrating the model's robustness against false predictions compared to state-of-the-art models. Further, this model also exhibits lower inference time, size, and memory usage compared to representative models. An automated PE-YNet tool can assist physicians with PE diagnosis, treatment, and prognosis monitoring in the clinical management of CoVID-19.

Automated semantic lung segmentation in chest CT images using deep neural network.

Lung segmentation algorithms play a significant role in segmenting theinfected regions in the lungs. This work aims to develop a computationally efficient and robust deep learning model for lung segmentation using chest computed tomography (CT) images with DeepLabV3 + networks for two-class (background and lung field) and four-class (ground-glass opacities, background, consolidation, and lung field). In this work, we investigate the performance of the DeepLabV3 + network with five pretrained networks: Xception, ResNet-18, Inception-ResNet-v2, MobileNet-v2 and ResNet-50. A publicly available database for COVID-19 that contains 750 chest CT images and corresponding pixel-labeled images are used to develop the deep learning model. The segmentation performance has been assessed using five performance measures: Intersection of Union (IoU), Weighted IoU, Balance F1 score, pixel accu-racy, and global accuracy. The experimental results of this work confirm that the DeepLabV3 + network with ResNet-18 and a batch size of 8 have a higher performance for two-class segmentation. DeepLabV3 + network coupled with ResNet-50 and a batch size of 16 yielded better results for four-class segmentation compared to other pretrained networks. Besides, the ResNet with a fewer number of layers is highly adequate for developing a more robust lung segmentation network with lesser computational complexity compared to the conventional DeepLabV3 + network with Xception. This present work proposes a unified DeepLabV3 + network to delineate the two and four different regions automatically using CT images for CoVID-19 patients. Our developed automated segmented model can be further developed to be used as a clinical diagnosis system for CoVID-19 as well as assist clinicians in providing an accurate second opinion CoVID-19 diagnosis.

Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation.

The evolution the novel corona virus disease (COVID-19) as a pandemic has inflicted several thousand deaths per day endangering the lives of millions of people across the globe. In addition to thermal scanning mechanisms, chest imaging examinations provide valuable insights to the detection of this virus, diagnosis and prognosis of the infections. Though Chest CT and Chest X-ray imaging are common in the clinical protocols of COVID-19 management, the latter is highly preferred, attributed to its simple image acquisition procedure and mobility of the imaging mechanism. However, Chest X-ray images are found to be less sensitive compared to Chest CT images in detecting infections in the early stages. In this paper, we propose a deep learning based framework to enhance the diagnostic values of these images for improved clinical outcomes. It is realized as a variant of the conventional SqueezeNet classifier with segmentation capabilities, which is trained with deep features extracted from the Chest X-ray images of a standard dataset for binary and multi class classification. The binary classifier achieves an accuracy of 99.53% in the discrimination of COVID-19 and Non COVID-19 images. Similarly, the multi class classifier performs classification of COVID-19, Viral Pneumonia and Normal cases with an accuracy of 99.79%. This model called the COVID-19 Super pixel SqueezNet (COVID-SSNet) performs super pixel segmentation of the activation maps to extract the regions of interest which carry perceptual image features and constructs an overlay of the Chest X-ray images with these regions. The proposed classifier model adds significant value to the Chest X-rays for an integral examination of the image features and the image regions influencing the classifier decisions to expedite the COVID-19 treatment regimen.

Co-cultivation of Beta vulgaris limits the pre-harvest colonization of foodborne pathogen (Salmonella spp.) on tomato.

Soil-borne Salmonella is associated with a large number of food-related disease outbreaks linked to pre-harvest contamination of plants (like tomato) in agricultural fields. Controlling the spread of Salmonella at field is very important in order to prevent various food-borne illnesses. One such approach involves the utilization of antimicrobial secondary metabolite of plant origin. We screened common salad vegetables for anti-Salmonella activity. Beta vulgaris root (beetroot) had very low colonization of Salmonella under in vitro conditions. We hypothesized that beetroot can be used to reclaim the soil contaminated with Salmonella. Cultivation of B. vulgaris in Salmonella treated soil brings down its CFU significantly. Since these antimicrobial effects are non-specific, a co-cultivation system of beet and tomato (a Salmonella susceptible plant) was used to analyze the effect on soil and its microbiota. The soil physicochemical properties and bacterial diversity were unaffected when tomato and beet co-cultivation was used. However, Salmonella burden on the tomato was reduced and its yield was restored. Thus, the inclusion of these crops in the crop-rotation or as a mixed/intercrop or as a bio-control crop can be a fruitful tool to reclaim the Salmonella contaminated soil.

Genetic analysis of scattered populations of the Indian eri silkworm, Samia cynthia ricini Donovan: Differentiation of subpopulations.

Deforestation and exploitation has led to the fragmentation of habitats and scattering of populations of the economically important eri silkworm, Samia cynthia ricini, in north-east India. Genetic analysis of 15 eri populations, using ISSR markers, showed 98% inter-population, and 23% to 58% intra-population polymorphism. Nei's genetic distance between populations increased significantly with altitude (R(2) = 0.71) and geographic distance (R(2) = 0.78). On the dendrogram, the lower and upper Assam populations were clustered separately, with intermediate grouping of those from Barpathar and Chuchuyimlang, consistent with geographical distribution. The Nei's gene diversity index was 0.350 in total populations and 0.121 in subpopulations. The genetic differentiation estimate (Gst) was 0.276 among scattered populations. Neutrality tests showed deviation of 118 loci from Hardy-Weinberg equilibrium. The number of loci that deviated from neutrality increased with altitude (R(2) = 0.63). Test of linkage disequilibrium showed greater contribution of variance among eri subpopulations to total variance. D('2)IS exceeded D('2)ST, showed significant contribution of random genetic drift to the increase in variance of disequilibrium in subpopulations. In the Lakhimpur population, the peripheral part was separated from the core by a genetic distance of 0.260. Patchy habitats promoted low genetic variability, high linkage disequilibrium and colonization by new subpopulations. Increased gene flow and habitat-area expansion are required to maintain higher genetic variability and conservation of the original S. c. ricini gene pool.

Development of a multiplex polymerase chain reaction for the simultaneous detection of microsporidians, nucleopolyhedrovirus, and densovirus infecting silkworms.

We have developed a novel PCR-based assay for individual and simultaneous detection of three major pathogens (microsporidians, nucleopolyhedrovirus (NPV) and densovirus (DNV)) infecting the silkworm, Bombyx mori. Multiplex PCR, using three primer pairs, two of which were designed from the conserved regions of 16S small subunit ribosomal RNA gene of microsporidians, and polyhedrin gene of NPVs respectively, and a third primer pair designed from the internal sequences of B. mori DNVs (BmDNV), showed discrete and pathogen specific PCR products. The assay showed high specificity and sensitivity for the pathogenic DNA. Under optimized PCR conditions, the assay yielded a 794bp DNA fragment from Nosema bombycis, 471bp fragment from B. mori NPV (BmNPV) and 391bp fragment from BmDNV. Further, this detection method was successfully applied to other silkworm species such as Antheraea mylitta and Samia cynthia ricini, in detecting same or similar pathogens infecting them. This method is a valuable supplement to the conventional microscopic diagnostic methods and can be used for the early detection of pathogens infecting silkworms. Furthermore it can assist research and extension centers for the safe supply of disease-free silkworms to farmers.

Genetic analysis of scattered populations of the Indian eri silkworm, Samia cynthia ricini Donovan: differentiation of subpopulations

Deforestation and exploitation has led to the fragmentation of habitats and scattering of populations of the economically important eri silkworm, Samia cynthia ricini, in north-east India. Genetic analysis of 15 eri populations, using ISSR markers, showed 98 percent inter-population, and 23 percent to 58 percent intra-population polymorphism. Nei's genetic distance between populations increased significantly with altitude (R² = 0.71) and geographic distance (R² = 0.78). On the dendrogram, the lower and upper Assam populations were clustered separately, with intermediate grouping of those from Barpathar and Chuchuyimlang, consistent with geographical distribution. The Nei's gene diversity index was 0.350 in total populations and 0.121 in subpopulations. The genetic differentiation estimate (Gst) was 0.276 among scattered populations. Neutrality tests showed deviation of 118 loci from Hardy-Weinberg equilibrium. The number of loci that deviated from neutrality increased with altitude (R² = 0.63). Test of linkage disequilibrium showed greater contribution of variance among eri subpopulations to total variance. D'2IS exceeded D'2ST, showed significant contribution of random genetic drift to the increase in variance of disequilibrium in subpopulations. In the Lakhimpur population, the peripheral part was separated from the core by a genetic distance of 0.260. Patchy habitats promoted low genetic variability, high linkage disequilibrium and colonization by new subpopulations. Increased gene flow and habitat-area expansion are required to maintain higher genetic variability and conservation of the original S. c. ricini gene pool.

Persistence and degradation of monocrotophos in cabbage.

Foliar application of monocrotophos in cabbage resulted in high initial residues of 6.00 and 7.54 microg g(-1) for the recommended dose (2 mL L(-1)) and double the recommended dose of monocrotophos (4 mL L(-1)) respectively. However, in farmer's practice treatment, it was found to be 2.54 microg g(-1) where it was sprayed once as fourth spray. Monocrotophos residues in cabbage after spray persisted for more than 30 days at both recommended and double the recommended dose of monocrotophos. The farmer's practice showed persistence of monocrotophos for only 15 days. Degradation of monocrotophos residues in cabbage followed first order exponential equation. Monocrotophos residues in cabbage degraded with a half-life of 2.87 to 3.05 days for four sprays at the recommended and double the recommended level of application. However, showed a half-life of 1.99 days for one spray of monocrotophos according to farmer's practice. Waiting periods /safe intervals for monocrotophos on cabbage were found to be 13.79, 15.90 and 8.55 days for the recommended, double the recommended dose and farmer's practice of monocrotophos application respectively.

Candidate genes for drought tolerance and improved productivity in rice (Oryza sativa L.).

Candidate genes are sequenced genes of known biological action involved in the development or physiology of a trait. Twenty-one putative candidate genes were designed after an exhaustive search in the public databases along with an elaborate literature survey for candidate gene products and/or regulatory sequences associated with enhanced drought resistance. The downloaded sequences were then used to design primers considering the flanking sequences as well. Polymerase chain reaction (PCR) performed on 10 diverse cultivars that involved Japonica, Indica and local accessions, revealed 12 polymorphic candidate genes. Seven polymorphic candidate genes were then utilized to genotype 148 individuals of CT9993 x IR62266 doubled haploid (DH) mapping population. The segregation data were tested for deviation from the expected Mendelian ratio (1:1) using a Chi-square test (less than 1%). Based on this, four candidate genes were assessed to be significant and the remaining three, as non-significant. All the significant candidate genes were biased towards CT9993, the female parent in the DH mapping population. Single-marker analysis strongly associated (less than 1%) them to different traits under both well-watered and low-moisture stress conditions. Two candidate genes, EXP15 and EXP13, were found to be associated with root number and silicon content in the stem respectively, under both well-watered and low-moisture stress conditions.