Search Results (7,647)

The emerging usage of digitalized histopathological images is leading to a novel possibility for data analysis. With the help of artificial intelligence algorithms, it is now possible to detect certain structures and morphological features on whole slide images automatically. This enables algorithms to count, measure, or evaluate those areas when trained properly. To achieve suitable training, datasets must be annotated and curated by users in programs like QuPath. The extraction of this data for artificial intelligence algorithms is still rather tedious and needs to be saved on a local hard drive. We developed a toolkit for integration into existing pipelines and tools, like U-net, for the on-the-fly extraction of annotation tiles from existing QuPath projects. The tiles can be directly used as input for artificial intelligence algorithms, and the results are directly transferred back to QuPath for visual inspection. With the toolkit, we created a convenient way to incorporate QuPath into existing AI workflows. Full article

Background/Objectives: Bacterial wilt disease is a soil-borne disease caused by Ralstonia solanacearum that causes huge losses to crop economies worldwide. Methods: In this work, strain MLY102 was isolated and further identified as R. solanacearum from a diseased tobacco stalk. The genomic properties of MLY102 were explored by performing biochemical characterization, genome sequencing, compositional analysis, functional annotation and comparative genomic analysis. Results: MLY102 had a pinkish-red color in the center of the colony surrounded by a milky-white liquid with fluidity on TTC medium. The biochemical results revealed that MLY102 can utilize carbon sources, including D-glucose (dGLU), cane sugar (SAC) and D-trehalose dihydrate (dTRE). Genome sequencing through the DNBSEQ and PacBio platforms revealed a genome size of 5.72 Mb with a G+C content of 67.59%. The genome consists of a circular chromosome and a circular giant plasmid with 5283 protein-coding genes. A comparison of the genomes revealed that MLY102 is closely related to GMI1000 and CMR15 but has 498 special genes and 13 homologous genes in the species-specific gene family, indicating a high degree of genomic uniqueness. Conclusions: The unique characteristics and genomic data of MLY102 can provide important reference values for the prevention and control of bacterial wilt disease. Full article

The detection of the human mental fatigue state holds immense significance due to its direct impact on work efficiency, specifically in system operation control. Numerous approaches have been proposed to address the challenge of fatigue detection, aiming to identify signs of fatigue and alert the individual. This paper introduces an approach to human mental fatigue assessment based on the application of machine learning techniques to the video of a working operator. For validation purposes, the approach was applied to a dataset, “Human Fatigue Assessment Based on Video Data” (HFAVD) integrating video data with features computed by using our computer vision deep learning models. The incorporated features encompass head movements represented by Euler angles (roll, pitch, and yaw), vital signs (blood pressure, heart rate, oxygen saturation, and respiratory rate), and eye and mouth states (blinking and yawning). The integration of these features eliminates the need for the manual calculation or detection of these parameters, and it obviates the requirement for sensors and external devices, which are commonly employed in existing datasets. The main objective of our work is to advance research in fatigue detection, particularly in work and academic settings. For this reason, we conducted a series of experiments by utilizing machine learning techniques to analyze the dataset and assess the fatigue state based on the features predicted by our models. The results reveal that the random forest technique consistently achieved the highest accuracy and F1-score across all experiments, predominantly exceeding 90%. These findings suggest that random forest is a highly promising technique for this task and prove the strong connection and association among the predicted features used to annotate the videos and the state of fatigue. Full article

In this study, a new species of Alanomyces was isolated as an endophyte from the bark of Azadirachta indica from Mulshi, Maharashtra. The identity of this isolate was confirmed based on the asexual morphological characteristics as well as multi-gene phylogeny based on the internal transcribed spacer (ITS) and large subunit (LSU) nuclear ribosomal RNA (rRNA) regions. As this was the second species to be reported in this genus, we sequenced the genome of this species to increase our knowledge about the possible applicability of this genus to various industries. Its genome length was found to be 35.01 Mb, harboring 7870 protein-coding genes as per Augustus and 8101 genes using GeMoMa. Many genes were annotated using the Clusters of Orthologous Groups (COGs) database, the Kyoto Encyclopedia of Genes and Genomes (KEGG), Gene Ontology (GO), Swiss-Prot, NCBI non-redundant nucleotide sequences (NTs), and NCBI non-redundant protein sequences (NRs). The number of repeating sequences was predicted using Proteinmask and RepeatMasker; tRNA were detected using tRNAscan and snRNA were predicted using rfam_scan. The genome was also annotated using the Pathogen–Host Interactions Database (PHI-base) and AntiSMASH. To confirm the evolutionary history, average nucleotide identity (ANIb), phylogeny based on orthologous proteins, and single nucleotide polymorphisms (SNPs) were carried out. Metabolic profiling of the methanolic extract of dried biomass and ethyl acetate extract of the filtrate revealed a variety of compounds of great importance in the pharmaceutical and cosmetic industry. The characterization and genomic analysis of the newly discovered species Alanomyces manoharacharyi highlights its potential applicability across multiple industries, particularly in pharmaceuticals and cosmetics due to its diverse secondary metabolites and unique genetic features it possesses. Full article

Deep learning has made remarkable strides in hyperspectral image (HSI) classification, significantly improving classification performance. However, the challenge of obtaining accurately labeled training samples persists, primarily due to the subjectivity of human annotators and their limited domain knowledge. This often results in erroneous labels, commonly referred to as label noise. Such noisy labels can critically impair the performance of deep learning models, making it essential to address this issue. While previous studies focused on label noise filtering and label correction, these approaches often require estimating noise rates and may inadvertently propagate noisy labels to clean labels, especially in scenarios with high noise levels. In this study, we introduce an ensemble network-based distillation (END) method specifically designed to address the challenges posed by label noise in HSI classification. The core idea is to leverage multiple base neural networks to generate an estimated label distribution from the training data. This estimated distribution is then used alongside the ground-truth labels to train the target network effectively. Moreover, we propose a parameter-adaptive loss function that balances the impact of both the estimated and ground-truth label distributions during the training process. Our approach not only simplifies architectural requirements but also integrates seamlessly into existing deep learning frameworks. Comparative experiments on four hyperspectral datasets demonstrate the effectiveness of our method, highlighting its competitive performance in the presence of label noise. Full article

Turbot and brill are two congeneric commercial flatfish species with striking differences in skin organization. The calcified appendages in turbot skin are conical tubercles, while in brill, they are elasmoid scales. A skin injury involving epidermal and dermal levels was evaluated 72 h post-injury to compare the skin regeneration processes between both species. An immune-enriched 4x44k turbot oligo-microarray was used to characterize the skin transcriptome and gene expression profiles in both species. RNA-seq was also performed on the brill samples to improve transcriptome characterization and validate the microarray results. A total of 15,854 and 12,447 expressed genes were identified, respectively, in the turbot and brill skin (10,101 shared) using the oligo-microarray (11,953 and 9629 annotated). RNA-seq enabled the identification of 11,838 genes in brill skin (11,339 annotated). Functional annotation of skin transcriptomes was similar in both species, but in turbot, it was enriched on mechanisms related to maintenance of epithelial structure, mannosidase activity, phospholipid binding, and cell membranes, while in brill, it was enriched on biological and gene regulation mechanisms, tissue development, and transferase and catalytic activities. The number of DEGs identified after skin damage in brill and turbot was 439 and 143, respectively (only 14 shared). Functions related to catabolic and metabolic processes, visual and sensorial perception, response to wounding, and wound healing were enriched in turbot DEGs, while metabolism, immune response, oxidative stress, phospholipid binding, and response to stimulus were enriched in brill. The results indicate that differences may be related to the stage of wound repair due to their different skin architecture. This work provides a foundation for future studies directed at skin defense mechanisms, with practical implications in flatfish aquaculture. Full article

The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 ${\mathrm{km}}^2$, featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets’ effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research. Full article

The transition in medical image segmentation from fine-grained to coarse-grained annotation methods, notably scribble annotation, offers a practical and efficient preparation for deep learning applications. However, these methods often compromise segmentation precision and result in irregular contours. This study targets the enhancement of scribble-supervised segmentation to match the accuracy of fine-grained annotation. Capitalizing on the consistency of target shapes across unpaired datasets, this study introduces a shape-aware scribble-supervised learning framework (MaskMixAdv) addressing two critical tasks: (1) Pseudo label generation, where a mixup-based masking strategy enables image-level and feature-level data augmentation to enrich coarse-grained scribbles annotations. A dual-branch siamese network is proposed to generate fine-grained pseudo labels. (2) Pseudo label optimization, where a CNN-based discriminator is proposed to refine pseudo label contours by distinguishing them from external unpaired masks during model fine-tuning. MaskMixAdv works under constrained annotation conditions as a label-efficient learning approach for medical image segmentation. A case study on public cardiac MRI datasets demonstrated that the proposed MaskMixAdv outperformed the state-of-the-art methods and narrowed the performance gap between scribble-supervised and mask-supervised segmentation. This innovation cuts annotation time by at least 95%, with only a minor impact on Dice performance, specifically a 2.6% reduction. The experimental outcomes indicate that employing efficient and cost-effective scribble annotation can achieve high segmentation accuracy, significantly reducing the typical requirement for fine-grained annotations. Full article

This study presents a novel AI method for extracting polygon and point features from historical geologic maps, representing a pivotal step for assessing the mineral resources needed for energy transition. Our innovative method involves using map units in the legends as prompts for one-shot segmentation and detection in geological feature extraction. The model, integrated with a human-in-the-loop system, enables geologists to refine results efficiently, combining the power of AI with expert oversight. Tested on geologic maps annotated by USGS and DARPA for the AI4CMA DARPA Challenge, our approach achieved a median F1 score of 0.91 for polygon feature segmentation and 0.73 for point feature detection when such features had abundant annotated data, outperforming current benchmarks. By efficiently and accurately digitizing historical geologic map, our method promises to provide crucial insights for responsible policymaking and effective resource management in the global energy transition. Full article

Most existing optic disc (OD) and cup (OC) segmentation models are biased to the dominant size and easy class (normal class), resulting in suboptimal performances on glaucoma-confirmed samples. Thus, these models are not optimal choices for assisting in tracking glaucoma progression and prognosis. Moreover, fully supervised models employing annotated glaucoma samples can achieve superior performances, although restricted by the high cost of collecting and annotating the glaucoma samples. Therefore, in this paper, we are dedicated to developing a glaucoma-specialized model by exploiting low-cost annotated normal fundus images, simultaneously adapting various common scenarios in clinical practice. We employ a contrastive learning and domain adaptation-based model by exploiting shared knowledge from normal samples. To capture glaucoma-related features, we utilize a Gram matrix to encode style information and the domain adaptation strategy to encode domain information, followed by narrowing the style and domain gaps between normal and glaucoma samples by contrastive and adversarial learning, respectively. To validate the efficacy of our proposed model, we conducted experiments utilizing two public datasets to mimic various common scenarios. The results demonstrate the superior performance of our proposed model across multi-scenarios, showcasing its proficiency in both the segmentation- and glaucoma-related metrics. In summary, our study illustrates a concerted effort to target confirmed glaucoma samples, mitigating the inherent bias issue in most existing models. Moreover, we propose an annotation-efficient strategy that exploits low-cost, normal-labeled fundus samples, mitigating the economic- and labor-related burdens by employing a fully supervised strategy. Simultaneously, our approach demonstrates its adaptability across various scenarios, highlighting its potential utility in both assisting in the monitoring of glaucoma progression and assessing glaucoma prognosis. Full article

Gaze zone detection involves estimating where drivers look in terms of broad categories (e.g., left mirror, speedometer, rear mirror). We here specifically focus on the automatic annotation of gaze zones in the context of road safety research, where the system can be tuned to specific drivers and driving conditions, so that an easy to use but accurate system may be obtained. We show with an existing dataset of eye region crops (nine gaze zones) and two newly collected datasets (12 and 10 gaze zones) that image classification with YOLOv8, which has a simple command line interface, achieves near-perfect accuracy without any pre-processing of the images, as long as a model is trained on the driver and conditions for which annotation is required (such as whether the drivers wear glasses or sunglasses). We also present two apps to collect the training images and to train and apply the YOLOv8 models. Future research will need to explore how well the method extends to real driving conditions, which may be more variable and more difficult to annotate for ground truth labels. Full article

The common carp (Cyprinus carpio) is a crucial freshwater species cultivated worldwide for food consumption. Female carp have better growth performance than males, which fascinates scholars to uncover the mechanism of gonadal differentiation and produce mono-sex populations. However, the mechanism of ovarian development at single-cell resolution is limited. Here, we conducted single-nucleus RNA sequencing in adolescent common carp ovaries. Our study obtained transcriptional profiles of 13,155 nuclei and revealed 13 distinct cell clusters in the ovaries, including three subtypes of germ cells and four subtypes of granulosa cells. We subsequently performed pseudotime trajectory analysis to delineate potential mechanisms underlying the development of germ cells and granulosa cells. We identified 1250 dynamic expression genes in germ cells and 1815 in granulosa cells (q-value < 0.01), including zp3, eif4a2 and aspm in germ cells and fshr and esr1 in granulosa cells. The functional annotation showed that dynamic expression genes in germ cells were involved in sperm–egg recognition and some terms related to meiosis, such as sister chromatid segregation and homologous recombination. Genes expressed dynamically in granulosa cells were related to the TGF-β signaling pathway, response to gonadotropin, and development of primary female sexual characteristics. In addition, the dynamic genes expressed in granulosa cells might relate to the complex communication between different cell types. In summary, our study provided a transcriptome profile of common carp ovaries at single-nucleus resolution, and we further revealed the potential cell type-specific mechanisms underlying oogenesis and the differentiation of granulosa cells, which will facilitate breeding all-female common carp populations. Full article

The Nao-zhou stock large yellow croaker (Larimichthys crocea) is a unique economic seawater fish species in China and exhibits significant dimorphism in both male and female phenotypes. Cultivating all-female seedlings can significantly improve breeding efficiency. To accelerate the cultivation process of all female seedlings of this species, it is necessary to deeply understand the regulatory mechanisms of sexual differentiation and gonadal development. This study used Illumina high-throughput sequencing to sequence the transcriptome of the testes and ovaries of Nao-zhou stock large yellow croaker to identify genes and molecular functions related to sex determination. A total of 10,536 differentially expressed genes were identified between males and females, including 5682 upregulated and 4854 downregulated genes. Functional annotation screened out 70 important candidate genes related to sex, including 34 genes highly expressed in the testis (including dmrt1, foxm1, and amh) and 36 genes highly expressed in the ovary (including gdf9, hsd3b1, and sox19b). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis found that differentially expressed genes were significantly enriched in nine signaling pathways related to sex determination and gonadal development, including steroid hormone biosynthesis, MAPK signaling pathway, and the TGF-beta signaling pathway. By screening sex-related differentially expressed genes and mapping protein–protein interaction networks, hub genes such as dmrt1, amh, and cyp19a1a were found to be highly connected. The expression levels of 15 sex-related genes, including amh, dmrt1, dmrt2a, foxl1, and zp3b, were determined by qRT–PCR and RNA sequencing. This study screened for differentially expressed genes related to sex determination and differentiation of Nao-zhou stock large yellow croaker and revealed the signaling pathways involved in gonad development of male and female individuals. The results provide important data for future research on sex determination and differentiation mechanisms, thereby providing a scientific basis for the cultivation of all-female seedlings. Full article

Conventional methods for tumor diagnosis suffer from two inherent limitations: they are time-consuming and subjective. Computer-aided diagnosis (CAD) is an important approach for addressing these limitations. Pathology whole-slide images (WSIs) are high-resolution tissue images that have made significant contributions to cancer diagnosis and prognosis assessment. Due to the complexity of WSIs and the availability of only slide-level labels, multiple instance learning (MIL) has become the primary framework for WSI classification. However, most MIL methods fail to capture the interdependence among image patches within a WSI, which is crucial for accurate classification prediction. Moreover, due to the weak supervision of slide-level labels, overfitting may occur during the training process. To address these issues, this paper proposes a dual-attention-based multiple instance learning framework (DAMIL). DAMIL leverages the spatial relationships and channel information between WSI patches for classification prediction, without detailed pixel-level tumor annotations. The output of the model preserves the semantic variations in the latent space, enhances semantic disturbance invariance, and provides reliable class identification for the final slide-level representation. We validate the effectiveness of DAMIL on the most commonly used public dataset, Camelyon16. The results demonstrate that DAMIL outperforms the state-of-the-art methods in terms of classification accuracy (ACC), area under the curve (AUC), and F1-Score. Our model also allows for the examination of its interpretability by visualizing the dual-attention weights. To the best of our knowledge, this is the first attempt to use a dual-attention mechanism, considering both spatial and channel information, for whole-slide image classification. Full article

Supernumerary teats (SNTs) or nipples often emerge around the mammary line. This study performed a genome-wide selective sweep analysis (GWS) at the copy number variant (CNV) level using two selected signal calculation methods (V_ST and F_ST) to identify candidate genes associated with SNTs in goats. A total of 12,310 CNVs were identified from 37 animals and 123 CNVs, with the top 1% V_ST values including 84 candidate genes (CDGs). Of these CDGs, minichromosome maintenance complex component 3, ectodysplasin A receptor associated via death domain, and cullin 5 demonstrated functions closely related to mammary gland development. In addition, 123 CNVs with the top 1% F_ST values were annotated to 97 CDGs. 5-Hydroxytryptamine receptor 2A, CCAAT/enhancer-binding protein alpha, and the polymeric immunoglobulin receptor affect colostrum secretion through multiple signaling pathways. Two genes, namely, RNA-binding motif protein 46 and β-1,3-galactosyltransferase 5, showed a close relation to mammary gland development. Six CNVs were identified and annotated to five genes by intersecting the top 1% of candidate CNVs with both parameters. These genes include LOC102185621, LOC102190481, and UDP-glucose pyrophosphorylase 2, which potentially affect the occurrence of BC through multiple biological processes, such as cell detoxification, glycogen synthesis, and phospholipid metabolism. In conclusion, we discovered numerous genes related to mammary development and breast cancer (BC) through a GWS, which suggests the mechanism of SNTs in goats and a certain association between mammary cancer and SNTs. Full article