Eur Heart J Acute Cardiovasc Care. 2025 Apr 7:zuaf058. doi: 10.1093/ehjacc/zuaf058. Online ahead of print.

NO ABSTRACT

PMID:40192550 | DOI:10.1093/ehjacc/zuaf058

J Sports Sci. 2025 Apr 7:1-19. doi: 10.1080/02640414.2025.2488157. Online ahead of print.

ABSTRACT

Predicting high-run chases in cricket is a complex task influenced by various factors, including team rankings, match conditions, pitch behavior, and inning scores. This study evaluates the effectiveness of probabilistic machine learning models, namely Naïve Bayes (NB), Bayesian Network (BN), Bayesian Regularized Neural Network (BRNN), Hidden Naïve Bayes (HNB), Correlation Feature-Based Filter Weighting Naïve Bayes (CFWNB), and Class-Specific Attribute Weighted Naïve Bayes (CAWNB), in predicting high run chases in T20I cricket. Model performance was assessed using accuracy, precision, sensitivity, specificity, F1-score, AUC-ROC, and entropy, while Monte Carlo simulations ensured robustness across multiple iterations. Non-parametric statistical tests were employed due to the non-normal distribution of performance metrics, with the Friedman test revealing significant ranking variations among models. The results demonstrate that CAWNB consistently outperforms other models in terms of accuracy, precision, AUC, and F1-score, making it the most reliable choice for high-run chase prediction. Future research should explore hybrid Bayesian deep learning approaches, real-time data adaptation, and the application of these models to other cricket formats and sports analytics to further enhance predictive performance.

PMID:40192186 | DOI:10.1080/02640414.2025.2488157

Eur J Clin Invest. 2025 Apr;55 Suppl 1:e70002. doi: 10.1111/eci.70002.

ABSTRACT

BACKGROUND: Recent advancements in deep learning (DL), a subset of artificial intelligence, have shown the potential to automate and improve disease recognition, phenotyping and prediction of disease onset and outcomes by analysing various sources of medical data. The electrocardiogram (ECG) is a valuable tool for diagnosing and monitoring cardiovascular conditions.

METHODS: The implementation of DL in ECG analysis has been used to detect and predict rhythm abnormalities and conduction abnormalities, ischemic and structural heart diseases, with performance comparable to physicians. However, despite promising development of DL algorithms for automatic ECG analysis, the integration of DL-based ECG analysis and deployment of medical devices incorporating these algorithms into routine clinical practice remains limited.

RESULTS: This narrative review highlights the applications of DL in 12-lead ECG analysis. Furthermore, we review randomized controlled trials that assess the clinical effectiveness of these DL tools. Finally, it addresses different key barriers to widespread implementation in clinical practice, including regulatory hurdles, algorithm transparency and data privacy concerns.

CONCLUSIONS: By outlining both the progress and the obstacles in this field, this review aims to provide insights into how DL could shape the future of ECG analysis and enhance cardiovascular care in daily clinical practice.

PMID:40191935 | DOI:10.1111/eci.70002

Eur J Clin Invest. 2025 Apr;55 Suppl 1:e14370. doi: 10.1111/eci.14370.

ABSTRACT

BACKGROUND: The management of cardiotoxicity related to cancer therapies has emerged as a significant clinical challenge, prompting the rapid growth of cardio-oncology. As cancer treatments become more complex, there is an increasing need to enhance diagnostic and therapeutic strategies for managing their cardiovascular side effects.

OBJECTIVE: This review investigates the potential of artificial intelligence (AI) to revolutionize cardio-oncology by integrating diverse data sources to address the challenges of cardiotoxicity management.

METHODS: We explore applications of AI in cardio-oncology, focusing on its ability to leverage multiple data sources, including electronic health records, electrocardiograms, imaging modalities, wearable sensors, and circulating serum biomarkers.

RESULTS: AI has demonstrated significant potential in improving risk stratification and longitudinal monitoring of cardiotoxicity. By optimizing the use of electrocardiograms, non-invasive imaging, and circulating biomarkers, AI facilitates earlier detection, better prediction of outcomes, and more personalized therapeutic interventions. These advancements are poised to enhance patient outcomes and streamline clinical decision-making.

CONCLUSIONS: AI represents a transformative opportunity in cardio-oncology by advancing diagnostic and therapeutic capabilities. However, successful implementation requires addressing practical challenges such as data integration, model interpretability, and clinician training. Continued collaboration between clinicians and AI developers will be essential to fully integrate AI into routine clinical workflows.

PMID:40191923 | DOI:10.1111/eci.14370

ACS Nano. 2025 Apr 7. doi: 10.1021/acsnano.5c02004. Online ahead of print.

ABSTRACT

Swimming kinematics and macroscale mechanical testing have shown that the vertebral column of sharks acts as a biological spring, storing and releasing energy during locomotion. Using synchrotron X-ray nanotomography and deep-learning image segmentation, we studied the ultrastructure and deformation mechanism of mineralized shark vertebrae from Carcharhinus limbatus (Blacktip shark). The vertebral centrum con regions: the corpus calcareum, a hypermineralized double cone, and the intermediale, blocks of mineralized cartilage interspersed by unmineralized arches. At the micron scale, mineralized cartilage has previously been described as a 3D network of interconnected mineral plates that vary in thickness and spacing. The corpus calcareum consists of stacked, interconnected, curved mineralized planes permeated by a network of organic occlusions. The mineral network in the intermedialia resembles trabecular bone, including thicker struts in the direction opposite to the predominant biological strain. We characterized collagenous fiber elements winding around lacunar spaces in the intermedialia, and we hypothesize the swirling arrangement and elasticity of the fibers to be distributing stress. With little permanent deformation detected in mineralized structures, it is likely that the soft organic matrix is crucial for absorbing energy through deformation, irreversible damage, and viscoelastic behavior. In the corpus calcareum, cracks typically terminate toward thick struts along the mineral planes, resembling the microscale crack deflection and arrest mechanism found in other staggered biocomposites, such as nacre or bone. Using transmission electron microscopy (TEM), we observed preferentially oriented, needlelike bioapatite crystallites and d-band patterns of collagen type-II fibrils resulting from intrafibrillar mineralization.

PMID:40191917 | DOI:10.1021/acsnano.5c02004

Front Aging Neurosci. 2025 Mar 21;17:1532470. doi: 10.3389/fnagi.2025.1532470. eCollection 2025.

ABSTRACT

Conventional computer-aided diagnostic techniques for Alzheimer's disease (AD) predominantly rely on magnetic resonance imaging (MRI) in isolation. Genetic imaging methods, by establishing the link between genes and brain structures in disease progression, facilitate early prediction of AD development. While deep learning methods based on MRI have demonstrated promising results for early AD diagnosis, the limited dataset size has led most AD studies to lean on statistical approaches within the realm of imaging genetics. Existing deep-learning approaches typically utilize pre-defined regions of interest and risk variants from known susceptibility genes, employing relatively straightforward feature fusion methods that fail to fully capture the relationship between images and genes. To address these limitations, we proposed a multi-modal deep learning classification network based on MRI and single nucleotide polymorphism (SNP) data for AD diagnosis and mild cognitive impairment (MCI) progression prediction. Our model leveraged a convolutional neural network (CNN) to extract whole-brain structural features, a Transformer network to capture genetic features, and employed a cross-transformer-based network for comprehensive feature fusion. Furthermore, we incorporated an attention-map-based interpretability method to analyze and elucidate the structural and risk variants associated with AD and their interrelationships. The proposed model was trained and evaluated using 1,541 subjects from the ADNI database. Experimental results underscored the superior performance of our model in effectively integrating and leveraging information from both modalities, thus enhancing the accuracy of AD diagnosis and prediction.

PMID:40191788 | PMC:PMC11968703 | DOI:10.3389/fnagi.2025.1532470

J Med Signals Sens. 2025 Feb 28;15:6. doi: 10.4103/jmss.jmss_46_24. eCollection 2025.

ABSTRACT

BACKGROUND: Gastroesophageal reflux disease (GERD) is a prevalent digestive disorder that impacts millions of individuals globally. Multichannel intraluminal impedance-pH (MII-pH) monitoring represents a novel technique and currently stands as the gold standard for diagnosing GERD. Accurately characterizing reflux events from MII data are crucial for GERD diagnosis. Despite the initial introduction of clinical literature toward software advancements several years ago, the reliable extraction of reflux events from MII data continues to pose a significant challenge. Achieving success necessitates the seamless collaboration of two key components: a reflux definition criteria protocol established by gastrointestinal experts and a comprehensive analysis of MII data for reflux detection.

METHOD: In an endeavor to address this challenge, our team assembled a dataset comprising 201 MII episodes. We meticulously crafted precise reflux episode definition criteria, establishing the gold standard and labels for MII data.

RESULT: A variety of signal-analyzing methods should be explored. The first Isfahan Artificial Intelligence Competition in 2023 featured formal assessments of alternative methodologies across six distinct domains, including MII data evaluations.

DISCUSSION: This article outlines the datasets provided to participants and offers an overview of the competition results.

PMID:40191685 | PMC:PMC11970833 | DOI:10.4103/jmss.jmss_46_24

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