-
Scientific Reports Jun 2024To obtain a reliable and accurate automatic speech recognition (ASR) machine learning model, it is necessary to have sufficient audio data transcribed, for training....
To obtain a reliable and accurate automatic speech recognition (ASR) machine learning model, it is necessary to have sufficient audio data transcribed, for training. Many languages in the world, especially the agglutinative languages of the Turkic family, suffer from a lack of this type of data. Many studies have been conducted in order to obtain better models for low-resource languages, using different approaches. The most popular approaches include multilingual training and transfer learning. In this study, we combined five agglutinative languages from the Turkic family-Kazakh, Bashkir, Kyrgyz, Sakha, and Tatar,-in order to provide multilingual training using connectionist temporal classification and an attention mechanism including a language model, because these languages have cognate words, sentence formation rules, and alphabet (Cyrillic). Data from the open-source database Common voice was used for the study, to make the experiments reproducible. The results of the experiments showed that multilingual training could improve ASR performances for all languages included in the experiment, except Bashkir language. A dramatic result was achieved for the Kyrgyz language: word error rate decreased to nearly one-fifth and character error rate decreased to one-fourth, which proves that this approach can be helpful for critically low-resource languages.
Topics: Humans; Multilingualism; Language; Machine Learning; Speech Recognition Software
PubMed: 38879705
DOI: 10.1038/s41598-024-64848-1 -
Scientific Reports Jun 2024Recently, ConvNeXt and blueprint separable convolution (BSConv) constructed from standard ConvNet modules have demonstrated competitive performance in advanced computer...
Recently, ConvNeXt and blueprint separable convolution (BSConv) constructed from standard ConvNet modules have demonstrated competitive performance in advanced computer vision tasks. This paper proposes an efficient model (BCRN) based on BSConv and the ConvNeXt residual structure for single image super-resolution, which achieves superior performance with very low parametric numbers. Specifically, the residual block (BCB) of the BCRN utilizes the ConvNeXt residual structure and BSConv to significantly reduce the number of parameters. Within the residual block, enhanced spatial attention and contrast-aware channel attention modules are simultaneously introduced to prioritize valuable features within the network. Multiple residual blocks are then stacked to form the backbone network, with Dense connections utilized between them to enhance feature utilization. Our model boasts extremely low parameters compared to other state-of-the-art lightweight models, while experimental results on benchmark datasets demonstrate its excellent performance. The code will be available at https://github.com/kptx666/BCRN .
PubMed: 38879679
DOI: 10.1038/s41598-024-64724-y -
Scientific Reports Jun 2024In this research, an upgraded and environmentally friendly process involving WO/Co-ZIF nanocomposite was used for the removal of Cefixime from the aqueous solutions....
In this research, an upgraded and environmentally friendly process involving WO/Co-ZIF nanocomposite was used for the removal of Cefixime from the aqueous solutions. Intelligent decision-making was employed using various models including Support Vector Regression (SVR), Genetic Algorithm (GA), Artificial Neural Network (ANN), Simulation Optimization Language for Visualized Excel Results (SOLVER), and Response Surface Methodology (RSM). SVR, ANN, and RSM models were used for modeling and predicting results, while GA and SOLVER models were employed to achieve the optimal conditions for Cefixime degradation. The primary goal of applying different models was to achieve the best conditions with high accuracy in Cefixime degradation. Based on R analysis, the quadratic factorial model in RSM was selected as the best model, and the regression coefficients obtained from it were used to evaluate the performance of artificial intelligence models. According to the quadratic factorial model, interactions between pH and time, pH and catalyst amount, as well as reaction time and catalyst amount were identified as the most significant factors in predicting results. In a comparison between the different models based on Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R Score) indices, the SVR model was selected as the best model for the prediction of the results, with a higher R Score (0.98), and lower MAE (1.54) and RMSE (3.91) compared to the ANN model. Both ANN and SVR models identified pH as the most important parameter in the prediction of the results. According to the Genetic Algorithm, interactions between the initial concentration of Cefixime with reaction time, as well as between the initial concentration of Cefixime and catalyst amount, had the greatest impact on selecting the optimal values. Using the Genetic Algorithm and SOLVER models, the optimum values for the initial concentration of Cefixime, pH, time, and catalyst amount were determined to be (6.14 mg L, 3.13, 117.65 min, and 0.19 g L) and (5 mg L, 3, 120 min, and 0.19 g L), respectively. Given the presented results, this research can contribute significantly to advancements in intelligent decision-making and optimization of the pollutant removal processes from the environment.
Topics: Nanocomposites; Machine Learning; Oxides; Tungsten; Cefixime; Neural Networks, Computer; Cobalt; Algorithms; Water Pollutants, Chemical; Anti-Bacterial Agents; Water Purification
PubMed: 38879660
DOI: 10.1038/s41598-024-64790-2 -
NPJ Digital Medicine Jun 2024The U.S. Food and Drug Administration’s (FDA) recent authorization of DermaSensor, an AI-enabled device for skin cancer detection in primary care, marks a pivotal...
The U.S. Food and Drug Administration’s (FDA) recent authorization of DermaSensor, an AI-enabled device for skin cancer detection in primary care, marks a pivotal moment in digital health innovation. Clinically, the authorization of the first AI-enabled device for use by non-specialists for detecting skin cancer reinforces the feasibility of digital health technologies to bridge gaps in access and expertise in medical practice. The authorization also establishes a new regulatory precedent for FDA authorization of medical devices incorporating AI and machine learning (ML) technologies within dermatology. Together, this article uses the DermaSensor authorization to examine the clinical evidence and regulatory implications of emerging AI-enabled technologies in dermatology.
PubMed: 38879640
DOI: 10.1038/s41746-024-01161-1 -
Nature Communications Jun 2024The growing scale and dimensionality of multiplexed imaging require reproducible and comprehensive yet user-friendly computational pipelines. TRACERx-PHLEX performs deep...
The growing scale and dimensionality of multiplexed imaging require reproducible and comprehensive yet user-friendly computational pipelines. TRACERx-PHLEX performs deep learning-based cell segmentation (deep-imcyto), automated cell-type annotation (TYPEx) and interpretable spatial analysis (Spatial-PHLEX) as three independent but interoperable modules. PHLEX generates single-cell identities, cell densities within tissue compartments, marker positivity calls and spatial metrics such as cellular barrier scores, along with summary graphs and spatial visualisations. PHLEX was developed using imaging mass cytometry (IMC) in the TRACERx study, validated using published Co-detection by indexing (CODEX), IMC and orthogonal data and benchmarked against state-of-the-art approaches. We evaluated its use on different tissue types, tissue fixation conditions, image sizes and antibody panels. As PHLEX is an automated and containerised Nextflow pipeline, manual assessment, programming skills or pathology expertise are not essential. PHLEX offers an end-to-end solution in a growing field of highly multiplexed data and provides clinically relevant insights.
Topics: Humans; Deep Learning; Image Processing, Computer-Assisted; Animals; Software; Spatial Analysis; Single-Cell Analysis; Phenotype; Mice; Image Cytometry
PubMed: 38879602
DOI: 10.1038/s41467-024-48870-5 -
NPJ Breast Cancer Jun 2024Given high costs of Oncotype DX (ODX) testing, widely used in recurrence risk assessment for early-stage breast cancer, studies have predicted ODX using quantitative...
Given high costs of Oncotype DX (ODX) testing, widely used in recurrence risk assessment for early-stage breast cancer, studies have predicted ODX using quantitative clinicopathologic variables. However, such models have incorporated only small cohorts. Using a cohort of patients from the National Cancer Database (NCDB, n = 53,346), we trained machine learning models to predict low-risk (0-25) or high-risk (26-100) ODX using quantitative estrogen receptor (ER)/progesterone receptor (PR)/Ki-67 status, quantitative ER/PR status alone, and no quantitative features. Models were externally validated on a diverse cohort of 970 patients (median follow-up 55 months) for accuracy in ODX prediction and recurrence. Comparing the area under the receiver operating characteristic curve (AUROC) in a held-out set from NCDB, models incorporating quantitative ER/PR (AUROC 0.78, 95% CI 0.77-0.80) and ER/PR/Ki-67 (AUROC 0.81, 95% CI 0.80-0.83) outperformed the non-quantitative model (AUROC 0.70, 95% CI 0.68-0.72). These results were preserved in the validation cohort, where the ER/PR/Ki-67 model (AUROC 0.87, 95% CI 0.81-0.93, p = 0.009) and the ER/PR model (AUROC 0.86, 95% CI 0.80-0.92, p = 0.031) significantly outperformed the non-quantitative model (AUROC 0.80, 95% CI 0.73-0.87). Using a high-sensitivity rule-out threshold, the non-quantitative, quantitative ER/PR and ER/PR/Ki-67 models identified 35%, 30% and 43% of patients as low-risk in the validation cohort. Of these low-risk patients, fewer than 3% had a recurrence at 5 years. These models may help identify patients who can forgo genomic testing and initiate endocrine therapy alone. An online calculator is provided for further study.
PubMed: 38879577
DOI: 10.1038/s41523-024-00651-5 -
Scientific Reports Jun 2024This study introduces a novel Hybrid Ensemble Machine-Learning (HEML) algorithm to merge long-term satellite-based reanalysis precipitation products (SRPPs), enabling...
This study introduces a novel Hybrid Ensemble Machine-Learning (HEML) algorithm to merge long-term satellite-based reanalysis precipitation products (SRPPs), enabling the estimation of super drought events in the Lake Victoria Basin (LVB) during the period of 1984 to 2019. This study considers three widely used Machine learning (ML) models, including RF (Random Forest), GBM (Gradient Boosting Machine), and KNN (k-nearest Neighbors), for the emerging HEML approach. The three SRPPs, including CHIRPS (Climate Hazards Group Infra-Red Precipitation with Station), ERA5-Land, and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network-Climate Data Record), were used to merge for developing new precipitation estimates from HEML model. Additionally, classification and regression models were employed as base learners in developing this algorithm. The newly developed HEML datasets were compared with other ML and SRPP products for super-drought monitoring. The Standardized precipitation evapotranspiration index (SPEI) was used to estimate super drought characteristics, including Drought frequency (DF), Drought Duration (DD), and Drought Intensity (DI) from machine learning and SRPPs products in LVB and compared with RG observation. The results revealed that the HEML algorithm shows excellent performance (CC = 0.93) compared to the single ML merging method and SRPPs against observation. Furthermore, the HEML merging product adeptly captures the spatiotemporal patterns of super drought characteristics during both training (1984-2009) and testing (2010-2019) periods. This research offers crucial insights for near-real-time drought monitoring, water resource management, and informed policy decisions.
PubMed: 38879570
DOI: 10.1038/s41598-024-61520-6 -
Scientific Data Jun 2024Pulmonary hypertension (PH) is a syndrome complex that accompanies a number of diseases of different etiologies, associated with basic mechanisms of structural and...
Pulmonary hypertension (PH) is a syndrome complex that accompanies a number of diseases of different etiologies, associated with basic mechanisms of structural and functional changes of the pulmonary circulation vessels and revealed pressure increasing in the pulmonary artery. The structural changes in the pulmonary circulation vessels are the main limiting factor determining the prognosis of patients with PH. Thickening and irreversible deposition of collagen in the pulmonary artery branches walls leads to rapid disease progression and a therapy effectiveness decreasing. In this regard, histological examination of the pulmonary circulation vessels is critical both in preclinical studies and clinical practice. However, measurements of quantitative parameters such as the average vessel outer diameter, the vessel walls area, and the hypertrophy index claimed significant time investment and the requirement for specialist training to analyze micrographs. A dataset of pulmonary circulation vessels for pathology assessment using semantic segmentation techniques based on deep-learning is presented in this work. 609 original microphotographs of vessels, numerical data from experts' measurements, and microphotographs with outlines of these measurements for each of the vessels are presented. Furthermore, here we cite an example of a deep learning pipeline using the U-Net semantic segmentation model to extract vascular regions. The presented database will be useful for the development of new software solutions for the analysis of histological micrograph.
Topics: Deep Learning; Hypertension, Pulmonary; Pulmonary Artery; Humans; Microscopy; Pulmonary Circulation
PubMed: 38879569
DOI: 10.1038/s41597-024-03473-z -
Scientific Reports Jun 2024Smooth pursuit eye movements are considered a well-established and quantifiable biomarker of sensorimotor function in psychosis research. Identifying psychotic syndromes...
Smooth pursuit eye movements are considered a well-established and quantifiable biomarker of sensorimotor function in psychosis research. Identifying psychotic syndromes on an individual level based on neurobiological markers is limited by heterogeneity and requires comprehensive external validation to avoid overestimation of prediction models. Here, we studied quantifiable sensorimotor measures derived from smooth pursuit eye movements in a large sample of psychosis probands (N = 674) and healthy controls (N = 305) using multivariate pattern analysis. Balanced accuracies of 64% for the prediction of psychosis status are in line with recent results from other large heterogenous psychiatric samples. They are confirmed by external validation in independent large samples including probands with (1) psychosis (N = 727) versus healthy controls (N = 292), (2) psychotic (N = 49) and non-psychotic bipolar disorder (N = 36), and (3) non-psychotic affective disorders (N = 119) and psychosis (N = 51) yielding accuracies of 65%, 66% and 58%, respectively, albeit slightly different psychosis syndromes. Our findings make a significant contribution to the identification of biologically defined profiles of heterogeneous psychosis syndromes on an individual level underlining the impact of sensorimotor dysfunction in psychosis.
Topics: Humans; Male; Female; Pursuit, Smooth; Psychotic Disorders; Adult; Biomarkers; Young Adult; Bipolar Disorder; Middle Aged; Case-Control Studies; Adolescent
PubMed: 38879556
DOI: 10.1038/s41598-024-64487-6 -
Plant Methods Jun 2024Image-based crop growth modeling can substantially contribute to precision agriculture by revealing spatial crop development over time, which allows an early and...
BACKGROUND
Image-based crop growth modeling can substantially contribute to precision agriculture by revealing spatial crop development over time, which allows an early and location-specific estimation of relevant future plant traits, such as leaf area or biomass. A prerequisite for realistic and sharp crop image generation is the integration of multiple growth-influencing conditions in a model, such as an image of an initial growth stage, the associated growth time, and further information about the field treatment. While image-based models provide more flexibility for crop growth modeling than process-based models, there is still a significant research gap in the comprehensive integration of various growth-influencing conditions. Further exploration and investigation are needed to address this gap.
METHODS
We present a two-stage framework consisting first of an image generation model and second of a growth estimation model, independently trained. The image generation model is a conditional Wasserstein generative adversarial network (CWGAN). In the generator of this model, conditional batch normalization (CBN) is used to integrate conditions of different types along with the input image. This allows the model to generate time-varying artificial images dependent on multiple influencing factors. These images are used by the second part of the framework for plant phenotyping by deriving plant-specific traits and comparing them with those of non-artificial (real) reference images. In addition, image quality is evaluated using multi-scale structural similarity (MS-SSIM), learned perceptual image patch similarity (LPIPS), and Fréchet inception distance (FID). During inference, the framework allows image generation for any combination of conditions used in training; we call this generation data-driven crop growth simulation.
RESULTS
Experiments are performed on three datasets of different complexity. These datasets include the laboratory plant Arabidopsis thaliana (Arabidopsis) and crops grown under real field conditions, namely cauliflower (GrowliFlower) and crop mixtures consisting of faba bean and spring wheat (MixedCrop). In all cases, the framework allows realistic, sharp image generations with a slight loss of quality from short-term to long-term predictions. For MixedCrop grown under varying treatments (different cultivars, sowing densities), the results show that adding these treatment information increases the generation quality and phenotyping accuracy measured by the estimated biomass. Simulations of varying growth-influencing conditions performed with the trained framework provide valuable insights into how such factors relate to crop appearances, which is particularly useful in complex, less explored crop mixture systems. Further results show that adding process-based simulated biomass as a condition increases the accuracy of the derived phenotypic traits from the predicted images. This demonstrates the potential of our framework to serve as an interface between a data-driven and a process-based crop growth model.
CONCLUSION
The realistic generation and simulation of future plant appearances is adequately feasible by multi-conditional CWGAN. The presented framework complements process-based models and overcomes their limitations, such as the reliance on assumptions and the low exact field-localization specificity, by realistic visualizations of the spatial crop development that directly lead to a high explainability of the model predictions.
PubMed: 38879522
DOI: 10.1186/s13007-024-01205-3