Transcriptome Dynamic Analysis Reveals New Candidate Genes Associated with Resistance to Fusarium Head Blight in Two Chinese Contrasting Wheat Genotypes.

In recent years, Fusarium head blight (FHB) has developed into a global disease that seriously affects the yield and quality of wheat. Effective measures to solve this problem include exploring disease-resistant genes and breeding disease-resistant varieties. In this study, we conducted a comparative transcriptome analysis to identify the important genes that are differentially expressed in FHB medium-resistant (Nankang 1) and FHB medium-susceptible (Shannong 102) wheat varieties for various periods after Fusarium graminearum infection using RNA-seq technology. In total, 96,628 differentially expressed genes (DEGs) were identified, 42,767 from Shannong 102 and 53,861 from Nankang 1 (FDR < 0.05 and |log2FC| > 1). Of these, 5754 and 6841 genes were found to be shared among the three time points in Shannong 102 and Nankang 1, respectively. After inoculation for 48 h, the number of upregulated genes in Nankang 1 was significantly lower than that of Shannong 102, but at 96 h, the number of DEGs in Nankang 1 was higher than that in Shannong 102. This indicated that Shannong 102 and Nankang 1 had different defensive responses to F. graminearum in the early stages of infection. By comparing the DEGs, there were 2282 genes shared at the three time points between the two strains. GO and KEGG analyses of these DEGs showed that the following pathways were associated with disease resistance genes: response to stimulus pathway in GO, glutathione metabolism, phenylpropanoid biosynthesis, plant hormone signal transduction, and plant-pathogen interaction in KEGG. Among them, 16 upregulated genes were identified in the plant-pathogen interaction pathway. There were five upregulated genes, TraesCS5A02G439700, TraesCS5B02G442900, TraesCS5B02G443300, TraesCS5B02G443400, and TraesCS5D02G446900, with significantly higher expression levels in Nankang 1 than in Shannong 102, and these genes may have an important role in regulating the resistance of Nankang 1 to F. graminearum infection. The PR proteins they encode are PR protein 1-9, PR protein 1-6, PR protein 1-7, PR protein 1-7, and PR protein 1-like. In addition, the number of DEGs in Nankang 1 was higher than that in Shannong 102 on almost all chromosomes, except chromosomes 1A and 3D, but especially on chromosomes 6B, 4B, 3B, and 5A. These results indicate that gene expression and the genetic background must be considered for FHB resistance in wheat breeding.

Local stereo matching with adaptive shape support window based cost aggregation.

Cost aggregation is the most important step in a local stereo algorithm. In this work, a novel local stereo-matching algorithm with a cost-aggregation method based on adaptive shape support window (ASSW) is proposed. First, we compute the initial cost volume, which uses both absolute intensity difference and gradient similarity to measure dissimilarity. Second, we apply an ASSW-based cost-aggregation method to get the aggregated cost within the support window. There are two main parts: at first we construct a local support skeleton anchoring each pixel with four varying arm lengths decided on color similarity; as a result, the support window integral of multiple horizontal segments spanned by pixels in the neighboring vertical is established. Then we utilize extended implementation of guided filter to aggregate cost volume within the ASSW, which has better edge-preserving smoothing property than bilateral filter independent of the filtering kernel size. In this way, the number of bad pixels located in the incorrect depth regions can be effectively reduced through finding optimal support windows with an arbitrary shape and size adaptively. Finally, the initial disparity value of each pixel is selected using winner takes all optimization and post processing symmetrically, considering both the reference and the target image, is adopted. The experimental results demonstrate that the proposed algorithm achieves outstanding matching performance compared with other existing local algorithms on the Middlebury stereo benchmark, especially in depth discontinuities and piecewise smooth regions.

Optimizing vitiligo diagnosis with ResNet and Swin transformer deep learning models: a study on performance and interpretability.

Vitiligo is a hypopigmented skin disease characterized by the loss of melanin. The progressive nature and widespread incidence of vitiligo necessitate timely and accurate detection. Usually, a single diagnostic test often falls short of providing definitive confirmation of the condition, necessitating the assessment by dermatologists who specialize in vitiligo. However, the current scarcity of such specialized medical professionals presents a significant challenge. To mitigate this issue and enhance diagnostic accuracy, it is essential to build deep learning models that can support and expedite the detection process. This study endeavors to establish a deep learning framework to enhance the diagnostic accuracy of vitiligo. To this end, a comparative analysis of five models including ResNet (ResNet34, ResNet50, and ResNet101 models) and Swin Transformer series (Swin Transformer Base, and Swin Transformer Large models), were conducted under the uniform condition to identify the model with superior classification capabilities. Moreover, the study sought to augment the interpretability of these models by selecting one that not only provides accurate diagnostic outcomes but also offers visual cues highlighting the regions pertinent to vitiligo. The empirical findings reveal that the Swin Transformer Large model achieved the best performance in classification, whose AUC, accuracy, sensitivity, and specificity are 0.94, 93.82%, 94.02%, and 93.5%, respectively. In terms of interpretability, the highlighted regions in the class activation map correspond to the lesion regions of the vitiligo images, which shows that it effectively indicates the specific category regions associated with the decision-making of dermatological diagnosis. Additionally, the visualization of feature maps generated in the middle layer of the deep learning model provides insights into the internal mechanisms of the model, which is valuable for improving the interpretability of the model, tuning performance, and enhancing clinical applicability. The outcomes of this study underscore the significant potential of deep learning models to revolutionize medical diagnosis by improving diagnostic accuracy and operational efficiency. The research highlights the necessity for ongoing exploration in this domain to fully leverage the capabilities of deep learning technologies in medical diagnostics.

Recent Advancements and Perspectives in the Diagnosis of Skin Diseases Using Machine Learning and Deep Learning: A Review.

OBJECTIVE: Skin diseases constitute a widespread health concern, and the application of machine learning and deep learning algorithms has been instrumental in improving diagnostic accuracy and treatment effectiveness. This paper aims to provide a comprehensive review of the existing research on the utilization of machine learning and deep learning in the field of skin disease diagnosis, with a particular focus on recent widely used methods of deep learning. The present challenges and constraints were also analyzed and possible solutions were proposed. METHODS: We collected comprehensive works from the literature, sourced from distinguished databases including IEEE, Springer, Web of Science, and PubMed, with a particular emphasis on the most recent 5-year advancements. From the extensive corpus of available research, twenty-nine articles relevant to the segmentation of dermatological images and forty-five articles about the classification of dermatological images were incorporated into this review. These articles were systematically categorized into two classes based on the computational algorithms utilized: traditional machine learning algorithms and deep learning algorithms. An in-depth comparative analysis was carried out, based on the employed methodologies and their corresponding outcomes. CONCLUSIONS: Present outcomes of research highlight the enhanced effectiveness of deep learning methods over traditional machine learning techniques in the field of dermatological diagnosis. Nevertheless, there remains significant scope for improvement, especially in improving the accuracy of algorithms. The challenges associated with the availability of diverse datasets, the generalizability of segmentation and classification models, and the interpretability of models also continue to be pressing issues. Moreover, the focus of future research should be appropriately shifted. A significant amount of existing research is primarily focused on melanoma, and consequently there is a need to broaden the field of pigmented dermatology research in the future. These insights not only emphasize the potential of deep learning in dermatological diagnosis but also highlight directions that should be focused on.

Genome-wide association analysis of type II resistance to Fusarium head blight in common wheat.

Background: Fusarium head blight (FHB) is a disease affecting wheat spikes caused by some Fusarium species and leads to cases of severe yield reduction and seed contamination. Identifying resistance genes/QTLs from wheat germplasm may help to improve FHB resistance in wheat production. Methods: Our study evaluated 205 elite winter wheat cultivars for FHB resistance. A high-density 90K SNP array was used for genotyping the panel. A genome-wide association study (GWAS) from cultivars from three different environments was performed using a mixed linear model (MLM). Results: Sixty-six significant marker-trait associations (MTAs) were identified (P < 0.001) on fifteen chromosomes that explained the phenotypic variation ranging from 5.4 to 11.2%. Some important new MTAs in genomic regions involving FHB resistance were found on chromosomes 2A, 3B, 5B, 6A, and 7B. Six MTAs at 92 cM on chromosome 7B were found in cultivars from two different environments. Moreover, there were 11 MTAs consistently associated with diseased spikelet rate and diseased rachis rate as pleiotropic effect loci and D_contig74317_533 on chromosome 5D was novel for FHB resistance. Eight new candidate genes of FHB resistance were predicated in wheat in this study. Three candidate genes, TraesCS5D02G006700, TraesCS6A02G013600, and TraesCS7B02G370700 on chromosome 5DS, 6AS, and 7BL, respectively, were perhaps important in defending against FHB by regulating intramolecular transferase activity, GTP binding, or chitinase activity in wheat, but further validation in needed. In addition, a total of five favorable alleles associated with wheat FHB resistance were discovered. These results provide important genes/loci for enhancing FHB resistance in wheat breeding by marker-assisted selection.

SurRF: Unsupervised Multi-View Stereopsis by Learning Surface Radiance Field.

The recent success in supervised multi-view stereopsis (MVS) relies on the onerously collected real-world 3D data. While the latest differentiable rendering techniques enable unsupervised MVS, they are restricted to discretized (e.g., point cloud) or implicit geometric representation, suffering from either low integrity for a textureless region or less geometric details for complex scenes. In this paper, we propose SurRF, an unsupervised MVS pipeline by learning Surface Radiance Field, i.e., a radiance field defined on a continuous and explicit 2D surface. Our key insight is that, in a local region, the explicit surface can be gradually deformed from a continuous initialization along view-dependent camera rays by differentiable rendering. That enables us to define the radiance field only on a 2D deformable surface rather than in a dense volume of 3D space, leading to compact representation while maintaining complete shape and realistic texture for large-scale complex scenes. We experimentally demonstrate that the proposed SurRF produces competitive results over the-state-of-the-art on various real-world challenging scenes, without any 3D supervision. Moreover, SurRF shows great potential in owning the joint advantages of mesh (scene manipulation), continuous surface (high geometric resolution), and radiance field (realistic rendering).

GigaMVS: A Benchmark for Ultra-Large-Scale Gigapixel-Level 3D Reconstruction.

Multiview stereopsis (MVS) methods, which can reconstruct both the 3D geometry and texture from multiple images, have been rapidly developed and extensively investigated from the feature engineering methods to the data-driven ones. However, there is no dataset containing both the 3D geometry of large-scale scenes and high-resolution observations of small details to benchmark the algorithms. To this end, we present GigaMVS, the first gigapixel-image-based 3D reconstruction benchmark for ultra-large-scale scenes. The gigapixel images, with both wide field-of-view and high-resolution details, can clearly observe both the Palace-scale scene structure and Relievo-scale local details. The ground-truth geometry is captured by the laser scanner, which covers ultra-large-scale scenes with an average area of 8667 m 2 and a maximum area of 32007 m 2. Owing to the extremely large scale, complex occlusion, and gigapixel-level images, GigaMVS exposes problems that emerge from the poor scalability and efficiency of the existing MVS algorithms. We thoroughly investigate the state-of-the-art methods in terms of geometric and textural measurements, which point to the weakness of the existing methods and promising opportunities for future works. We believe that GigaMVS can benefit the community of 3D reconstruction and support the development of novel algorithms balancing robustness, scalability and accuracy.

The Influence of Host Aphids on the Performance of Aphelinus asychis.

The aphid parasitoid Aphelinus asychis Walker is an important biological control agent against many aphid species. In this study, we examined whether the rearing host aphid species (the pea aphid, Acyrthosiphon pisum and the grain aphid, Sitobion avenae) affect the performance of A. asychis. We found that A. pisum-reared A. asychis showed a significantly larger body size (body length and hind tibia length) and shorter developmental time than S. avenae-reared A. asychis. There was no difference in the sex ratio between them. The longevity of A. pisum-reared A. asychis was also significantly longer than that of S. aveane-reared A. asychis. Furthermore, A. pisum-reared A. asychis presented stronger parasitic capacity and starvation resistance than S. aveane-reared A. asychi. In addition, host aphid alteration experiments showed that A. asychis only takes two generations to adapt to its new host. Taken together, these results revealed that A. pisum is a better alternative host aphid for mass-rearing and releasing of A. asychis. The body size plasticity of A. asychis is also discussed.

SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-View Stereopsis.

Multi-view stereopsis (MVS) tries to recover the 3D model from 2D images. As the observations become sparser, the significant 3D information loss makes the MVS problem more challenging. Instead of only focusing on densely sampled conditions, we investigate sparse-MVS with large baseline angles since the sparser sensation is more practical and more cost-efficient. By investigating various observation sparsities, we show that the classical depth-fusion pipeline becomes powerless for the case with a larger baseline angle that worsens the photo-consistency check. As another line of the solution, we present SurfaceNet+, a volumetric method to handle the 'incompleteness' and the 'inaccuracy' problems induced by a very sparse MVS setup. Specifically, the former problem is handled by a novel volume-wise view selection approach. It owns superiority in selecting valid views while discarding invalid occluded views by considering the geometric prior. Furthermore, the latter problem is handled via a multi-scale strategy that consequently refines the recovered geometry around the region with the repeating pattern. The experiments demonstrate the tremendous performance gap between SurfaceNet+ and state-of-the-art methods in terms of precision and recall. Under the extreme sparse-MVS settings in two datasets, where existing methods can only return very few points, SurfaceNet+ still works as well as in the dense MVS setting.

Boosting Single Image Super-Resolution Learnt From Implicit Multi-Image Prior.

Learning-based single image super-resolution (SISR) aims to learn a versatile mapping from low resolution (LR) image to its high resolution (HR) version. The critical challenge is to bias the network training towards continuous and sharp edges. For the first time in this work, we propose an implicit boundary prior learnt from multi-view observations to significantly mitigate the challenge in SISR we outline. Specifically, the multi-image prior that encodes both disparity information and boundary structure of the scene supervise a SISR network for edge-preserving. For simplicity, in the training procedure of our framework, light field (LF) serves as an effective multi-image prior, and a hybrid loss function jointly considers the content, structure, variance as well as disparity information from 4D LF data. Consequently, for inference, such a general training scheme boosts the performance of various SISR networks, especially for the regions along edges. Extensive experiments on representative backbone SISR architectures constantly show the effectiveness of the proposed method, leading to around 0.6 dB gain without modifying the network architecture.

A modular hierarchical array camera.

Array cameras removed the optical limitations of a single camera and paved the way for high-performance imaging via the combination of micro-cameras and computation to fuse multiple aperture images. However, existing solutions use dense arrays of cameras that require laborious calibration and lack flexibility and practicality. Inspired by the cognition function principle of the human brain, we develop an unstructured array camera system that adopts a hierarchical modular design with multiscale hybrid cameras composing different modules. Intelligent computations are designed to collaboratively operate along both intra- and intermodule pathways. This system can adaptively allocate imagery resources to dramatically reduce the hardware cost and possesses unprecedented flexibility, robustness, and versatility. Large scenes of real-world data were acquired to perform human-centric studies for the assessment of human behaviours at the individual level and crowd behaviours at the population level requiring high-resolution long-term monitoring of dynamic wide-area scenes.

Genome wide association study of the whiteness and colour related traits of flour and dough sheets in common wheat.

Flour whiteness and colour are important factors that influence the quality of wheat flour and end-use products. In this study, a genome wide association study focusing on flour and dough sheet colour using a high density genetic map constructed with 90K single nucleotide polymorphism arrays in a panel of 205 elite winter wheat accessions was conducted in two different locations in 2 years. Eighty-six significant marker-trait associations (MTAs) were detected for flour whiteness and the brightness index (L* value), the redness index (a* value), and the yellowness index (b* value) of flour and dough sheets (P < 10-4) on homologous group 1, 2, 5 and 7, and chromosomes 3A, 3B, 4A, 6A and 6B. Four, three, eleven, eleven MTAs for the flour whiteness, L* value, a* value, b* value, and one MTA for the dough sheet L* value were identified in more than one environment. Based on MATs, some important new candidate genes were identified. Of these, two candidate genes, TraesCS5D01G004300 and Gsp-1D, for BS00000020_51 were found in wheat, relating to grain hardness. Other candidate genes were associated with proteins, the fatty acid biosynthetic process, the ketone body biosynthetic process, etc.

Erratum: A Learning-Based Model to Evaluate Hospitalization Priority in COVID-19 Pandemics.

[This corrects the article DOI: 10.1016/j.patter.2020.100092.].

A Learning-Based Model to Evaluate Hospitalization Priority in COVID-19 Pandemics.

The emergence of the novel coronavirus disease 2019 (COVID-19) is placing an increasing burden on healthcare systems. Although the majority of infected patients experience non-severe symptoms and can be managed at home, some individuals develop severe symptoms and require hospital admission. Therefore, it is critical to efficiently assess the severity of COVID-19 and identify hospitalization priority with precision. In this respect, a four-variable assessment model, including lymphocyte, lactate dehydrogenase, C-reactive protein, and neutrophil, is established and validated using the XGBoost algorithm. This model is found to be effective in identifying severe COVID-19 cases on admission, with a sensitivity of 84.6%, a specificity of 84.6%, and an accuracy of 100% to predict the disease progression toward rapid deterioration. It also suggests that a computation-derived formula of clinical measures is practically applicable for healthcare administrators to distribute hospitalization resources to the most needed in epidemics and pandemics.