J Med Signals Sens. 2025 Feb 28;15:5. doi: 10.4103/jmss.jmss_55_24. eCollection 2025.

ABSTRACT

BACKGROUND: Multiple sclerosis (MS) is one of the most common reasons of neurological disabilities in young adults. The disease occurs when the immune system attacks the central nervous system and destroys the myelin of nervous cells. This results in appearing several lesions in the magnetic resonance (MR) images of patients. Accurate determination of the amount and the place of lesions can help physicians to determine the severity and progress of the disease.

METHOD: Due to the importance of this issue, this challenge has been dedicated to the segmentation and localization of lesions in MR images of patients with MS. The goal was to segment and localize the lesions in the flair MR images of patients as close as possible to the ground truth masks.

RESULTS: Several teams sent us their results for the segmentation and localization of lesions in MR images. Most of the teams preferred to use deep learning methods. The methods varied from a simple U-net structure to more complicated networks.

CONCLUSION: The results show that deep learning methods can be useful for segmentation and localization of lesions in MR images. In this study, we briefly described the dataset and the methods of teams attending the competition.

PMID:40191684 | PMC:PMC11970832 | DOI:10.4103/jmss.jmss_55_24

Front Genet. 2025 Mar 21;16:1532651. doi: 10.3389/fgene.2025.1532651. eCollection 2025.

ABSTRACT

MOTIVATION: Predicting the response of cell lines to characteristic drugs based on multi-omics gene information has become the core problem of precision oncology. At present, drug response prediction using multi-omics gene data faces the following three main challenges: first, how to design a gene probe feature extraction model with biological interpretation and high performance; second, how to develop multi-omics weighting modules for reasonably fusing genetic data of different lengths and noise conditions; third, how to construct deep learning models that can handle small sample sizes while minimizing the risk of possible overfitting.

RESULTS: We propose an innovative drug response prediction model (NMDP). First, the NMDP model introduces an interpretable semi-supervised weighted SPCA module to solve the feature extraction problem in multi-omics gene data. Next, we construct a multi-omics data fusion framework based on sample similarity networks, bimodal tests, and variance information, which solves the data fusion problem and enables the NMDP model to focus on more relevant genomic data. Finally, we combine a one-dimensional convolution method and Kolmogorov-Arnold networks (KANs) to predict the drug response. We conduct five sets of real data experiments and compare NMDP against seven advanced drug response prediction methods. The results show that NMDP achieves the best performance, with sensitivity and specificity reaching 0.92 and 0.93, respectively-an improvement of 11%-57% compared to other models. Bio-enrichment experiments strongly support the biological interpretation of the NMDP model and its ability to identify potential targets for drug activity prediction.

PMID:40191608 | PMC:PMC11968432 | DOI:10.3389/fgene.2025.1532651

APL Bioeng. 2025 Apr 3;9(2):026104. doi: 10.1063/5.0242570. eCollection 2025 Jun.

ABSTRACT

Current risk assessment models for predicting ischemic stroke (IS) in patients with atrial fibrillation (AF) often fail to account for the effects of medications and the complex interactions between drugs, proteins, and diseases. We developed an interpretable deep learning model, the AF-Biological-IS-Path (ABioSPath), to predict one-year IS risk in AF patients by integrating drug-protein-disease pathways with real-world clinical data. Using a heterogeneous multilayer network, ABioSPath identifies mechanisms of drug actions and the propagation of comorbid diseases. By combining mechanistic pathways with patient-specific characteristics, the model provides individualized IS risk assessments and identifies potential molecular pathways involved. We utilized the electronic health record data from 7859 AF patients, collected between January 2008 and December 2009 across 43 hospitals in Hong Kong. ABioSPath outperformed baseline models in all evaluation metrics, achieving an AUROC of 0.7815 (95% CI: 0.7346-0.8283), a positive predictive value of 0.430, a negative predictive value of 0.870, a sensitivity of 0.500, a specificity of 0.885, an average precision of 0.409, and a Brier score of 0.195. Cohort-level analysis identified key proteins, such as CRP, REN, and PTGS2, within the most common pathways. Individual-level analysis further highlighted the importance of PIK3/Akt and cytokine and chemokine signaling pathways and identified IS risks associated with less-studied drugs like prochlorperazine maleate. ABioSPath offers a robust, data-driven approach for IS risk prediction, requiring only routinely collected clinical data without the need for costly biomarkers. Beyond IS, the model has potential applications in screening risks for other diseases, enhancing patient care, and providing insights for drug development.

PMID:40191603 | PMC:PMC11970939 | DOI:10.1063/5.0242570

R Soc Open Sci. 2024 Oct 23;11(10):240720. doi: 10.1098/rsos.240720. eCollection 2024 Oct.

ABSTRACT

Contemporary drug discovery paradigms rely heavily on binding assays about the bio-physicochemical processes. However, this dominant approach suffers from overlooked higher-order interactions arising from the intricacies of molecular mechanisms, such as those involving cis-regulatory elements. It introduces potential impairments and restrains the potential development of computational methods. To address this limitation, I developed a deep learning model that leverages an end-to-end approach, relying exclusively on therapeutic information about drugs. By transforming textual representations of drug and virus genetic information into high-dimensional latent representations, this method evades the challenges arising from insufficient information about binding specificities. Its strengths lie in its ability to implicitly consider complexities such as epistasis and chemical-genetic interactions, and to handle the pervasive challenge of data scarcity. Through various modeling skills and data augmentation techniques, the proposed model demonstrates outstanding performance in out-of-sample validations, even in scenarios with unknown complex interactions. Furthermore, the study highlights the importance of chemical diversity for model training. While the method showcases the feasibility of deep learning in data-scarce scenarios, it reveals a promising alternative for drug discovery in situations where knowledge of underlying mechanisms is limited.

PMID:40191531 | PMC:PMC11972434 | DOI:10.1098/rsos.240720

Imaging Sci Dent. 2025 Mar;55(1):1-10. doi: 10.5624/isd.20240139. Epub 2025 Jan 15.

ABSTRACT

PURPOSE: This study was performed to assess the performance and accuracy of artificial intelligence (AI) in the detection and diagnosis of maxillary sinus pathologies using computed tomography (CT)/cone-beam computed tomography (CBCT) imaging.

MATERIALS AND METHODS: A comprehensive literature search was conducted across 4 databases: Google Scholar, BioMed Central (BMC), ProQuest, and PubMed. Combinations of keywords such as "DCNN," "deep learning," "convolutional neural network," "machine learning," "predictive modeling," and "data mining" were used to identify relevant articles. The study included articles that were published within the last 5 years, written in English, available in full text, and focused on diagnostic accuracy.

RESULTS: Of an initial 530 records, 12 studies with a total of 3,349 patients (7,358 images) were included. All articles employed deep learning methods. The most commonly tested pathologies were maxillary rhinosinusitis and maxillary sinusitis, while the most frequently used AI models were convolutional neural network architectures, including ResNet and DenseNet, YOLO, and U-Net. DenseNet and ResNet architectures have demonstrated superior precision in detecting maxillary sinus pathologies due to their capacity to handle deeper networks without overfitting. The performance in detecting maxillary sinus pathology varied, with an accuracy ranging from 85% to 97%, a sensitivity of 87% to 100%, a specificity of 87.2% to 99.7%, and an area under the curve of 0.80 to 0.91.

CONCLUSION: AI with various architectures has been used to detect maxillary sinus abnormalities on CT/CBCT images, achieving near-perfect results. However, further improvements are needed to increase accuracy and consistency.

PMID:40191392 | PMC:PMC11966023 | DOI:10.5624/isd.20240139

Sci Rep. 2025 Apr 6;15(1):11776. doi: 10.1038/s41598-025-90533-y.

ABSTRACT

Accurate segmentation of biomedical time-series, such as intracardiac electrograms, is vital for understanding physiological states and supporting clinical interventions. Traditional rule-based and feature engineering approaches often struggle with complex clinical patterns and noise. Recent deep learning advancements offer solutions, showing various benefits and drawbacks in segmentation tasks. This study evaluates five segmentation algorithms, from traditional rule-based methods to advanced deep learning models, using a unique clinical dataset of intracardiac signals from 100 patients. We compared a rule-based method, a support vector machine (SVM), fully convolutional semantic neural network (UNet), region proposal network (Faster R-CNN), and recurrent neural network for electrocardiographic signals (DENS-ECG). Notably, Faster R-CNN has never been applied to 1D signals segmentation before. Each model underwent Bayesian optimization to minimize hyperparameter bias. Results indicated that deep learning models outperformed traditional methods, with UNet achieving the highest segmentation score of 88.9 % (root mean square errors for onset and offset of 8.43 ms and 7.49 ms), closely followed by DENS-ECG at 87.8 %. Faster R-CNN and SVM showed moderate performance, while the rule-based method had the lowest accuracy (77.7 %). UNet and DENS-ECG excelled in capturing detailed features and handling noise, highlighting their potential for clinical application. Despite greater computational demands, their superior performance and diagnostic potential support further exploration in biomedical time-series analysis.

PMID:40189617 | DOI:10.1038/s41598-025-90533-y

J Microbiol Methods. 2025 Apr 4:107125. doi: 10.1016/j.mimet.2025.107125. Online ahead of print.

ABSTRACT

Conventional clinical microbiological techniques are enhanced by the introduction of artificial intelligence (AI). Comprehensive data processing and analysis enabled the development of curated datasets that has been effectively used in training different AI algorithms. Recently, a number of machine learning (ML) and deep learning (DL) algorithms are developed and evaluated using diverse microbiological datasets. These datasets included spectral analysis (Raman and MALDI-TOF spectroscopy), microscopic images (Gram and acid fast stains), and genomic and protein sequences (whole genome sequencing (WGS) and protein data banks (PDBs)). The primary objective of these algorithms is to minimize the time, effort, and expenses linked to conventional analytical methods. Furthermore, AI algorithms are incorporated with quantitative structure-activity relationship (QSAR) models to predict novel antimicrobial agents that address the continuing surge of antimicrobial resistance. During the COVID-19 pandemic, AI algorithms played a crucial role in vaccine developments and the discovery of new antiviral agents, and introduced potential drug candidates via drug repurposing. However, despite their significant benefits, the implementation of AI encounters various challenges, including ethical considerations, the potential for bias, and errors related to data training. This review seeks to provide an overview of the most recent applications of artificial intelligence in clinical microbiology, with the intention of educating a wider audience of clinical practitioners regarding the current uses of machine learning algorithms and encouraging their implementation. Furthermore, it will discuss the challenges related to the incorporation of AI into clinical microbiology laboratories and examine future opportunities for AI within the realm of infectious disease epidemiology.

PMID:40188989 | DOI:10.1016/j.mimet.2025.107125

Med Image Anal. 2025 Apr 5;102:103567. doi: 10.1016/j.media.2025.103567. Online ahead of print.

ABSTRACT

Artifacts in histology images pose challenges for accurate diagnosis with deep learning models, often leading to misinterpretations. Existing artifact restoration methods primarily rely on Generative Adversarial Networks (GANs), which approach the problem as image-to-image translation. However, those approaches are prone to mode collapse and can unexpectedly alter morphological features or staining styles. To address the issue, we propose ArtiDiffuser, a counterfactual diffusion model tailored to restore only artifact-distorted regions while preserving the integrity of the rest of the image. Additionally, we show an innovative perspective by addressing the misdiagnosis stemming from artifacts via artifact synthesis as data augmentation, and thereby leverage ArtiDiffuser to unify the artifact synthesis and the restoration capabilities. This synergy significantly surpasses the performance of conventional methods which separately handle artifact restoration or synthesis. We propose a Swin-Transformer denoising network backbone to capture both local and global attention, further enhanced with a class-guided Mixture of Experts (MoE) to process features related to specific artifact categories. Moreover, it utilizes adaptable class-specific tokens for enhanced feature discrimination and a mask-weighted loss function to specifically target and correct artifact-affected regions, thus addressing issues of data imbalance. In downstream applications, ArtiDiffuser employs a consistency regularization strategy that assures the model's predictive accuracy is maintained across original and artifact-augmented images. We also contribute the first comprehensive histology dataset, comprising 723 annotated patches across various artifact categories, to facilitate further research. Evaluations on four distinct datasets for both restoration and synthesis demonstrate ArtiDiffuser's effectiveness compared to GAN-based approaches, used for either pre-processing or augmentation. The code is available at https://github.com/wagnchogn/ArtiDiffuser.

PMID:40188685 | DOI:10.1016/j.media.2025.103567

Environ Int. 2025 Mar 30;198:109427. doi: 10.1016/j.envint.2025.109427. Online ahead of print.

ABSTRACT

Wastewater-based epidemiology (WBE) represents a powerful technique for quantifying the attenuation characteristics and consumption of pharmaceuticals. In addition to WBE, no further methods have been developed to assess the wastewater stability related to antidepressants (ADs). In this study, the biodegradability, solubility, and adsorption or partition of 66 ADs were objectively scored according to the relevant guidelines of the Organisation for Economic Cooperation and Development. An assessment framework and the MSSL-RealFormer classification model of ADs wastewater stability were constructed based on physicochemical properties to predict the ADs wastewater stability and the quantitative structure-activity relationship. The constructed MSSL-RealFormer classification model exhibited a markedly higher prediction accuracy than traditional methods. Furthermore, 15 high-stable ADs in wastewater with low biodegradability, high solubility, and low adsorption or partition were identified. SHapley Additive exPlanation method demonstrated that group hydrophobicity, electrostatic and van der Waals forces exerted a significant influence on the ADs wastewater stability. And molecular stability was found to be significantly correlated with the ADs wastewater stability. A combination of density functional theory and MSSL-RealFormer classification model was employed to identify 17 high-stable transformation products of nine medium- and low-stable ADs in wastewater. The Ecological Structure Activity Relationships model demonstrated that bupropion, tapentadol and chlorpheniramine exhibited significant acute toxicity to the aquatic food chain. In this study, a novel deep learning model was constructed to rapidly screen the correlation between the ADs wastewater stability and their molecular structures. It is anticipated to prove a favorable tool for optimizing the wastewater stability screening of pharmaceuticals.

PMID:40188602 | DOI:10.1016/j.envint.2025.109427

Comput Methods Programs Biomed. 2025 Mar 27;265:108728. doi: 10.1016/j.cmpb.2025.108728. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: In the medical field of digital pathology, many tasks rely on visual assessments of tissue patterns or cells, presenting an opportunity to apply computer vision methods. However, acquiring a substantial number of annotations for developing deep learning algorithms remains a bottleneck. The annotation process is inherently biased due to various constraints, including labor shortages, high costs, time inefficiencies, and a strongly imbalanced distribution of labels. This study explores available solutions for reducing the costs of annotation bootstrapping in the challenging task of follicular lymphoma diagnosis.

METHODS: We compare three distinct approaches to annotation bootstrapping: extensive manual annotations, active learning, and weak supervision. We propose a hybrid architecture for centroblast and centrocyte detection from whole slide images, based on a custom cell encoder and contextual encoding derived from foundation models for digital pathology. We collected a dataset of 41 whole slide images scanned with a 20x objective lens and resolution 0.24μm/pixel, from which 12,704 cell annotations were gathered.

RESULTS: Applying our proposed active learning workflow led to an almost twofold increase in the number of samples within the minority class. The best bootstrapping method improved the overall performance of the detection algorithm by 18 percentage points, yielding a macro-averaged F1-score, precision, and recall of 63%.

CONCLUSIONS: The results of this study may find applications in other digital pathology problems, particularly for tasks involving a lack of homogeneous cell clusters within whole slide images.

PMID:40188578 | DOI:10.1016/j.cmpb.2025.108728

Sci Rep. 2025 Apr 7;15(1):11813. doi: 10.1038/s41598-025-96234-w.

ABSTRACT

Alzheimer's disease (AD) subjects usually show more profound morphological changes with time compared to cognitively normal (CN) individuals. These changes are the combination of two major biological processes: normal aging and AD pathology. Investigating normal aging and residual morphological changes separately can increase our understanding of the disease. This paper proposes two scores, the aging score (AS) and the AD-specific score (ADS), whose purpose is to measure these two components of brain atrophy independently. For this, in the first step, we estimate the atrophy due to the normal aging of CN subjects by computing the expected deformation required to match imaging templates generated at different ages. We used a state-of-the-art generative deep learning model for generating such imaging templates. In the second step, we apply deep learning-based diffeomorphic registration to align the given image of a subject with a reference imaging template. Parametrization of this deformation field is then decomposed voxel-wise into their parallel and perpendicular components with respect to the parametrization of the expected atrophy of CN individuals in one year computed in the first step. AS and ADS are the normalized scores of these two components, respectively. We evaluated these two scores on the OASIS-3 dataset with 1,014 T1-weighted MRI scans. Of these, 326 scans were from CN subjects, and 688 scans were from subjects diagnosed with AD at various stages of clinical severity, as defined by clinical dementia rating (CDR) scores. Our results reveal that AD is marked by both disease-specific brain changes and an accelerated aging process. Such changes affect brain regions differently. Moreover, the proposed scores were sensitive to detect changes in the early stages of the disease, which is promising for its potential future use in clinical studies. Our code is freely available at https://github.com/Fjr9516/DBM_with_DL .

PMID:40189702 | DOI:10.1038/s41598-025-96234-w

Sci Rep. 2025 Apr 6;15(1):11781. doi: 10.1038/s41598-025-96297-9.

ABSTRACT

Mandarin orange is a popular fruit in China and known worldwide for its unique flavor and nutritional benefits. As consumer demand for fruit quality increases, the fine assessment and grading of fruit sweetness-especially through non-destructive testing techniques-are becoming increasingly important in agriculture and commerce. In this paper, a new Attention for Orange (AO) attention mechanism and Multiscale Feature Optimization (MFO) feature extraction module are designed and combined with VGG13 convolutional neural network (CNN), innovatively proposed VGG-MFO-Orange CNN model for accurately classifying mandarin oranges with different sweetness. First, a sample of Linhai mandarin oranges was collected, and a sweetness triple classification dataset with 5022 images was formed, utilizing image acquisition and sugar detection. The proposed model was then trained against six influential classical CNN models: DenseNet121, MobileNet_v2, ResNet50, ShuffleNet, VGG13, and VGG13_bn. The experimental results showed that our model achieved an accuracy of 86.8% on the validation set, which was significantly better than the other six models. It also demonstrated excellent generalization ability and effectiveness in predicting the sweetness of Linhai mandarin oranges. Therefore, our model can provide an efficient means of fruit grading for agricultural production, contribute to agricultural modernization, and enhance the competitiveness of agricultural products in the market.

PMID:40189693 | DOI:10.1038/s41598-025-96297-9

Sci Rep. 2025 Apr 6;15(1):11765. doi: 10.1038/s41598-025-96071-x.

ABSTRACT

Hyperthermia (HT) in combination with radio- and/or chemotherapy has become an accepted cancer treatment for distinct solid tumour entities. In HT, tumour tissue is exogenously heated to temperatures between 39 and 43 °C for 60 min. Temperature monitoring can be performed non-invasively using dynamic magnetic resonance imaging (MRI). However, the slow nature of MRI leads to motion artefacts in the images due to the movements of patients during image acquisition. By discarding parts of the data, the speed of the acquisition can be increased - known as undersampling. However, due to the invalidation of the Nyquist criterion, the acquired images might be blurry and can also produce aliasing artefacts. The aim of this work was, therefore, to reconstruct highly undersampled MR thermometry acquisitions with better resolution and with fewer artefacts compared to conventional methods. The use of deep learning in the medical field has emerged in recent times, and various studies have shown that deep learning has the potential to solve inverse problems such as MR image reconstruction. However, most of the published work only focuses on the magnitude images, while the phase images are ignored, which are fundamental requirements for MR thermometry. This work, for the first time, presents deep learning-based solutions for reconstructing undersampled MR thermometry data. Two different deep learning models have been employed here, the Fourier Primal-Dual network and the Fourier Primal-Dual UNet, to reconstruct highly undersampled complex images of MR thermometry. MR images of 44 patients with different sarcoma types who received HT treatment in combination with radiotherapy and/or chemotherapy were used in this study. The method reduced the temperature difference between the undersampled MRIs and the fully sampled MRIs from 1.3 to 0.6 °C in full volume and 0.49 °C to 0.06 °C in the tumour region for a theoretical acceleration factor of 10.

PMID:40189690 | DOI:10.1038/s41598-025-96071-x

Sci Rep. 2025 Apr 6;15(1):11754. doi: 10.1038/s41598-025-95871-5.

ABSTRACT

To investigate the potential of employing artificial intelligence (AI) -driven breast ultrasound analysis models for the classification of glandular tissue components (GTC) in dense breast tissue. A total of 1,848 healthy women with mammograms classified as dense breast were enrolled in this prospective study. Residual Network (ResNet) 101 classification model and ResNet with fully Convolutional Networks (ResNet + FCN) segmentation model were trained. The better effective model was selected to appraise the classification performance of 3 breast radiologists and 3 non-breast radiologists. The evaluation metrics included sensitivity, specificity, and positive predictive value (PPV). The ResNet101 model demonstrated superior performance compared to the ResNet + FCN model. It significantly enhanced the classification sensitivity of all radiologists by 0.060, 0.021, 0.170, 0.009, 0.052, and 0.047, respectively. For P1 to P4 glandular, the PPVs of all radiologists increased by 0.154, 0.178, 0.027, and 0.109 with Ai-assisted. Notably, the non-breast radiologists experienced a particularly substantial rise in PPV (p < 0.01). This study trained ResNet 101 deep learning model is a reliable and accurate system for assisting different experienced radiologists differentiate dense breast glandular tissue components in ultrasound images.

PMID:40189689 | DOI:10.1038/s41598-025-95871-5

Sci Rep. 2025 Apr 6;15(1):11750. doi: 10.1038/s41598-025-95985-w.

ABSTRACT

Cassava is a tuberous edible plant native to the American tropics and is essential for its versatile applications including cassava flour, bread, tapioca, and laundry starch. Cassava leaf diseases reduce crop yields, elevate production costs, and disrupt market stability. This places significant burdens on farmers and economies while highlighting the need for effective management strategies. Traditional methods of manual disease diagnosis are costly, labor-intensive, and time-consuming. This research aims to address the challenge of accurate disease classification by overcoming the limitations of existing methods, which encounter difficulties with the complexity and variability of leaf disease symptoms. To the best of our knowledge, this is the first study to propose a novel dual-track feature aggregation architecture that integrates the Residual Inception Positional Encoding Attention (RIPEA) Network with EfficientNet for the classification of cassava leaf diseases. The proposed model employs a dual-track feature aggregation architecture which integrates the RIPEA Network with EfficientNet. The RIPEA track extracts significant features by leveraging residual connections for preserving gradients and uses multi-scale feature fusion for combining fine-grained details with broader patterns. It also incorporates Coordinate and Mixed Attention mechanisms which focus on cross-channel and long-range dependencies. The extracted features from both tracks are aggregated for classification. Furthermore, it incorporates an image augmentation method and a cosine decay learning rate schedule to improve model training. This improves the ability of the model to accurately differentiate between Cassava Bacterial Blight (CBB), Brown Streak Disease (CBSD), Green Mottle (CGM), Mosaic Disease (CMD), and healthy leaves, addressing both local textures and global structures. Additionally, to enhance the interpretability of the model, we apply Grad-CAM to provide visual explanations for the model's decision-making process, helping to understand which regions of the leaf images contribute to the classification results. The proposed network achieved a classification accuracy of 93.06%.

PMID:40189680 | DOI:10.1038/s41598-025-95985-w

Sci Rep. 2025 Apr 6;15(1):11757. doi: 10.1038/s41598-025-96385-w.

ABSTRACT

Coherent beam combination has emerged as a promising strategy for overcoming the power limitations of individual fibre lasers. This approach relies on maintaining precise phase difference between the constituent beamlets, which are typically established using phase retrieval algorithms. However, phase locking is often studied under the assumption that the power levels of the beamlets remain stable, an idealisation that does not hold always in practical applications. Over the operational lifetime of fibre lasers, power degradation inevitably occurs, introducing additional challenges to phase retrieval. To address this, we propose a deep learning algorithm for single-step simultaneous phase and amplitude identification, directly from a single camera observation of the intensity distribution of the combined beam. By leveraging its ability to detect and interpret subtle variations in intensity interference patterns, the deep learning approach can accurately disentangle phase and power contributions, even in the presence of significant power fluctuations. Using a spatial light modulator, we systematically investigate the impact of power-level fluctuations on phase retrieval within a simulated coherent beam combination system. Furthermore, we explore the scalability of this deep learning approach by evaluating its ability to achieve the required phase and amplitude precision as the number of beamlets increases.

PMID:40189661 | DOI:10.1038/s41598-025-96385-w

Sci Rep. 2025 Apr 6;15(1):11747. doi: 10.1038/s41598-025-96053-z.

ABSTRACT

The utility of CT-derived parameters for hepatic steatosis assessment has primarily focused on non-alcoholic fatty liver disease. This study aimed to evaluate their applicability in chronic hepatitis B (CHB) through a retrospective analysis of 243 CHB patients. Using deep-learning-based 3D organ segmentation on abdominal CT scans at 100 kVp, the mean volumetric CT attenuation of the liver and spleen was automatically measured on pre-contrast (liver (L)_pre and spleen (S)_pre) and post-contrast (L_post and S_post) portal venous phase images. To identify mild, moderate, and severe steatosis (S1, S2, and S3 based on the controlled attenuation parameter), L_pre showed areas under the receiver operating characteristic curve (AUROCs) of 0.695, 0.779, and 0.795, significantly higher than L-S_pre (0.633, 0.691, and 0.732; Ps = 0.02, 0.003, and 0.03). Post-contrast parameters demonstrated slightly lower AUROCs than their pre-contrast counterparts (Ps = 0.15-0.81). Concomitant hepatic fibrosis influenced diagnostic performance, with CT parameters performing better in patients without severe fibrosis than those with (F3-4 on transient elastography), though statistical significance was only observed for L-S_post in severe steatosis (P = 0.037). In conclusion, CT attenuation-based parameters extracted through automated 3D analysis show promise as a tool for assessing hepatic steatosis in patients with CHB.

PMID:40189652 | DOI:10.1038/s41598-025-96053-z

Sci Rep. 2025 Apr 6;15(1):11744. doi: 10.1038/s41598-025-95819-9.

ABSTRACT

Neural style transfer (NST) has opened new possibilities for digital art by enabling the blending of distinct artistic styles with content from various images. However, traditional NST methods often need help balancing style fidelity and content preservation, and many models need more computational efficiency, limiting their applicability for real-time applications. This study aims to enhance the efficiency and quality of NST by proposing a refined model that addresses key challenges in content retention, style fidelity, and computational performance. Specifically, the research explores techniques to improve the visual coherence of style transfer, ensuring consistency and accessibility for practical use. The proposed model integrates Adaptive Instance Normalization (AdaIN) and Gram matrix-based style representation within a convolutional neural network (CNN) architecture. The model is evaluated using quantitative metrics such as content loss, style loss, Structural Similarity Index (SSIM), and processing time, along with a qualitative assessment of content and style consistency across various image pairs. The proposed model significantly improves content and style balance, with content and style loss values reduced by 15% compared to baseline models. The optimal configuration yields an SSIM score of 0.88 for medium style intensity, maintaining structural integrity while achieving stylistic effects. Additionally, the model's processing time is reduced by 76%, making it suitable for near-real-time applications. Style fidelity scores remain high across various artistic styles, with minimal loss in content retention. The refined NST model balances style and content effectively, enhancing visual quality and computational efficiency. These advancements make NST more accessible for real-time artistic applications, providing a versatile digital art, design, and multimedia production tool.

PMID:40189651 | DOI:10.1038/s41598-025-95819-9

Sci Rep. 2025 Apr 6;15(1):11778. doi: 10.1038/s41598-025-96523-4.

ABSTRACT

Agriculture is an essential foundation that supports numerous economies, and the longevity of the coffee business is of paramount significance. Controlling and safeguarding coffee farms from harmful pests, including the Coffee Berry Borer, Mealybugs, Scales, and Leaf Miners, which may drastically affect crop productivity and quality. Standard methods for detecting pest diseases sometimes need specialized knowledge or thorough analysis, leading to a substantial commitment of time and effort. To address this challenge, researchers have explored the use of computer vision and deep learning techniques for the automated detection of plant pest diseases. This paper presents a novel strategy for the early detection of coffee crop killers using Hybrid Vision Graph Neural Networks (HV-GNN) in coffee plantations. The model was trained and validated using a curated dataset of 2850 labelled coffee plant images, which included diverse insect infestations. The HV-GNN design allows the model to recognize individual pests within images and capture the complex relationships between them, potentially leading to improved detection accuracy. HV-GNN proficiently detect pests by analyzing their visual characteristics and elucidating the interconnections among pests in images. Experimental findings indicate that HV-GNN attain a detection accuracy of 93.6625%, exceeding that of leading models. The increased accuracy underscores the feasibility of practical implementation, enabling proactive pest control to protect coffee farms and improve agricultural output.

PMID:40189644 | DOI:10.1038/s41598-025-96523-4

Sci Rep. 2025 Apr 6;15(1):11772. doi: 10.1038/s41598-025-91225-3.

ABSTRACT

Image observation method is a key method for shale reservoir evaluation. At the micro scale, scanning electron microscope images can be used to accurately understand the structural characteristics of shale. Most of the current research is to artificially identify the microstructure of shale. This approach has subjective limitations and makes it difficult to process images in batches on a large scale. We take the scanning electron microscope image as the research object, and the shale deep learning theory as the research method to realize the intelligent identification of microscopic substances in the shale scanning electron microscope image. The results show that the improved deep learning model performs better than other deep learning models. The maximum values of Precision, Recall, mAP50 and mAP50-95 reached 0.94442, 0.91695, 0.9579 and 0.71547, respectively. The functions of the optimized Yolov8 model were integrated with SEM technology. In engineering practice, it can assist researchers to quickly locate object substances and obtain high-quality SEM images, effectively improving the efficiency and accuracy of reservoir evaluation. In addition, this technology has great potential for development, and it is expected to play an important role in expanding to a variety of fields such as medicine and materials science by changing the test object.

PMID:40189619 | DOI:10.1038/s41598-025-91225-3