Sci Rep. 2025 Apr 29;15(1):15075. doi: 10.1038/s41598-025-99137-y.

ABSTRACT

Lung cancer, as one of the most lethal malignancies worldwide, primarily relies on radiation therapy, with about 60%-70% of patients requiring this treatment. In radiation therapy planning, precise segmentation of the Gross Tumor Volume (GTV) in CT images is crucial. However, the low contrast between the tumor and surrounding tissues, small size of the tumor area, and high heterogeneity of its internal structure pose significant technical challenges for accurate segmentation. To address these limitations, we propose RAU-Net (ROI-Attention U-Net), a two-stage framework, which combines target detection for Region of Interest (ROI) localization with a refined U-Net architecture incorporating attention mechanisms. Experiments on Lung Cancer GTV Dataset1 demonstrated that RAU-Net achieved a Dice coefficient of (77.13 ± 0.55)% and a sensitivity of (80.38 ± 0.63)% on the validation set, representing improvements of 4.1% and 6.25%, respectively, compared to the next best model, and significantly outperforming traditional U-Net and other advanced models. Similarly, On Lung Cancer GTV Dataset2, RAU-Net demonstrated remarkable performance, achieving the highest Dice coefficient of (73.95 ± 0.66)% and the second-highest Sensitivity of (66.40 ± 0.92)%, showcasing its superiority over other models overall. Ablation studies further confirmed the crucial role of the ROI extraction phase, attention mechanism, SE-Res module, and Combined Loss Function (CLoss) in enhancing segmentation performance. This framework provides a clinically viable solution for GTV delineation while offering methodological insights for medical image analysis.

PMID:40301479 | DOI:10.1038/s41598-025-99137-y

Sci Rep. 2025 Apr 29;15(1):15064. doi: 10.1038/s41598-025-97715-8.

ABSTRACT

In smart manufacturing, logistics, and other inside settings where the Global Positioning System (GPS) doesn't work, indoor positioning systems (IPS) are essential. Due to environmental complexity, signal noise, and possible data manipulation, traditional IPS techniques struggle with accuracy, resilience, and security. Online and offline phases are distinguished in the suggested indoor location system that employs deep learning and fingerprinting. During the offline phase, mobile devices gather signal strength measurements and contextual data traverse inside settings via Wi-Fi, Bluetooth, and magnetometers. Fingerprint classification using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering follows the application of signal processing techniques for noise reduction and data augmentation. The online phase involves extracting information to improve the model's accuracy. These features can be signal-based, spatial-temporal, motion-based, or environmental. The Deep Spatial-Temporal Attention Network (Deep-STAN) is an innovative hybrid model for location classification that combines Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Long-Short Term Memory (LSTMs), and attention processes. The model hyperparameters are fine-tuned using hybrid optimization to guarantee optimal performance. The work's main contribution is the incorporation of ECC, an effective encryption and decryption method for signal data, which is based on Galois fields. This cryptographic method is well-suited for real-world applications since it guarantees low-latency operations while simultaneously improving data integrity and confidentiality. In addition, S-box enhances the IPS's resilience and security by including QR codes for distinct location marking and blockchain technology for safe and immutable storing of positioning data. Moreover, the performance of the suggested model includes an accuracy of 0.9937, precision of 0.987, sensitivity of 0.9898, and specificity of 0.9878, while when 80% of data were used it had an accuracy of 0.9804, precision of 0.9722, sensitivity of 0.9859, and specificity of 0.9756. These outcomes prove that the proposed system is stable and flexible enough to be used in indoor positioning applications.

PMID:40301441 | DOI:10.1038/s41598-025-97715-8

Sci Rep. 2025 Apr 29;15(1):15000. doi: 10.1038/s41598-025-98398-x.

ABSTRACT

The COVID-19 outbreak has highlighted the importance of mathematical epidemic models like the Susceptible-Infected-Recovered (SIR) model, for understanding disease spread dynamics. However, enhancing their predictive accuracy complicates parameter estimation. To address this, we proposed a novel model that integrates traditional mathematical modeling with deep learning which has shown improved predicted power across diverse fields. The proposed model includes a simple artificial neural network (ANN) for regional disease incidences, and a graph convolutional neural network (GCN) to capture spread to adjacent regions. GCNs are a recent deep learning algorithm designed to learn spatial relationship from graph-structured data. We applied the model to COVID-19 incidences in Spain to evaluate its performance. It achieved a 0.9679 correlation with the test data, outperforming previous models with fewer parameters. By leveraging the efficient training methods of deep learning, the model simplifies parameter estimation while maintaining alignment with the mathematical framework to ensure interpretability. The proposed model may allow the more robust and insightful analyses by leveraging the generalization power of deep learning and theoretical foundations of the mathematical models.

PMID:40301427 | DOI:10.1038/s41598-025-98398-x

J Imaging Inform Med. 2025 Apr 29. doi: 10.1007/s10278-025-01515-5. Online ahead of print.

ABSTRACT

Breast ultrasound is a useful and rapid diagnostic tool for the early detection of breast cancer. Artificial intelligence-supported computer-aided decision systems, which assist expert radiologists and clinicians, provide reliable and rapid results. Deep learning methods and techniques are widely used in the field of health for early diagnosis, abnormality detection, and disease diagnosis. Therefore, in this study, a deep ensemble learning model based on Dirichlet distribution using pre-trained transfer learning models for breast cancer classification from ultrasound images is proposed. In the study, experiments were conducted using the Breast Ultrasound Images Dataset (BUSI). The dataset, which had an imbalanced class structure, was balanced using data augmentation techniques. DenseNet201, InceptionV3, VGG16, and ResNet152 models were used for transfer learning with fivefold cross-validation. Statistical analyses, including the ANOVA test and Tukey HSD test, were applied to evaluate the model's performance and ensure the reliability of the results. Additionally, Grad-CAM (Gradient-weighted Class Activation Mapping) was used for explainable AI (XAI), providing visual explanations of the deep learning model's decision-making process. The spaced repetition method, commonly used to improve the success of learners in educational sciences, was adapted to artificial intelligence in this study. The results of training with transfer learning models were used as input for further training, and spaced repetition was applied using previously learned information. The use of the spaced repetition method led to increased model success and reduced learning times. The weights obtained from the trained models were input into an ensemble learning system based on Dirichlet distribution with different variations. The proposed model achieved 99.60% validation accuracy on the dataset, demonstrating its effectiveness in breast cancer classification.

PMID:40301291 | DOI:10.1007/s10278-025-01515-5

Biomed Pharmacother. 2025 Apr 28;187:118104. doi: 10.1016/j.biopha.2025.118104. Online ahead of print.

ABSTRACT

Dengue virus (DENV) threatens global health; specific antiviral drugs are required to combat it. Such anti-DENV therapeutics can be rapidly developed by repositioning the drugs approved for other indications. This study investigated six medications of different classes drawn from a library of molecules. In silico analyses were performed to determine potential binding affinity for the DENV non-structural protein NS3 protease and NS5 RNA-dependent RNA polymerase (RdRp). Of the six candidates, galidesivir and tadalafil showed the highest binding affinities for the DENV NS3 protease and NS5 RdRp, with tadalafil demonstrating the highest binding affinity. Galidesivir and tadalafil substantially suppressed viral replication in DENV replicon cells without inducing cytotoxicity and showed half-maximal inhibitory concentrations of 10 μM and 2.56 μM, respectively. Both galidesivir and tadalafil effectively suppress DENV infection in human hepatoma and baby hamster kidney cells, and tadalafil demonstrates protease-inhibitory activity. In an AG129 mouse model of DENV infection, both galidesivir and tadalafil reduced viral loads in the serum, with tadalafil producing a notable reduction by day four. Both drugs markedly suppressed DENV replication in the hepatic tissue. Histopathologically, both galidesivir- and tadalafil-treated mice showed alleviation of DENV-induced lesions in the spleen and liver, indicating the potential therapeutic effects of these drugs. These findings highlight the potential of repositioning galidesivir and tadalafil as effective anti-DENV therapies with low cytotoxicity, meeting the urgent global need for new therapeutic agents against this pathogen.

PMID:40300391 | DOI:10.1016/j.biopha.2025.118104

Nat Metab. 2025 Apr 29. doi: 10.1038/s42255-025-01294-x. Online ahead of print.

ABSTRACT

Agonists and antagonists of the glucose-dependent insulinotropic polypeptide receptor (GIPR) enhance body weight loss induced by glucagon-like peptide-1 receptor (GLP-1R) agonism. However, while GIPR agonism decreases body weight and food intake in a GLP-1R-independent manner via GABAergic GIPR+ neurons, it remains unclear whether GIPR antagonism affects energy metabolism via a similar mechanism. Here we show that the body weight and food intake effects of GIPR antagonism are eliminated in mice with global loss of either Gipr or Glp-1r but are preserved in mice with loss of Gipr in either GABAergic neurons of the central nervous system or peripherin-expressing neurons of the peripheral nervous system. Single-nucleus RNA-sequencing shows opposing effects of GIPR agonism and antagonism in the dorsal vagal complex, with antagonism, but not agonism, closely resembling GLP-1R signalling. Additionally, GIPR antagonism and GLP-1R agonism both regulate genes implicated in synaptic plasticity. Collectively, we show that GIPR agonism and antagonism decrease body weight via different mechanisms, with GIPR antagonism, unlike agonism, depending on functional GLP-1R signalling.

PMID:40301583 | DOI:10.1038/s42255-025-01294-x

Orphanet J Rare Dis. 2025 Apr 29;20(1):205. doi: 10.1186/s13023-025-03714-3.

ABSTRACT

BACKGROUND: The high variety of mutations found in the Cystic Fibrosis Transmembrane Regulator (CFTR) gene is responsible for the clinical heterogeneity observed in people with Cystic Fibrosis (CF) and the atypical manifestations in CFTR-related disorders (CFTR-RD). The intronic c.489+3A>G (c.621+3A>G) variant has been reported to have questionable pathogenicity, although its alleged severity was probably due to its co-segregation in cis with another undetected mutation, as previously reported from countries in the Mediterranean region. In the island of Cyprus, several rare CFTR variants have been previously identified, among them the c.489+3A>G in co-segregation with the pathogenic p.Cys1400Ter (cDNA name = c.4200_4201del or legacy name = 4332delTG) mutation. We aimed to investigate the prevalence of these variants in Cyprus and describe their clinical impact in patients and carriers.

RESULTS: The intronic variant c.489+3A>G has been so far identified to co-segregate with the pathogenic p.Cys1400Ter mutation in the same allele in six unrelated Cypriot families and in total of 20 subjects. Three of them were diagnosed with CF, presenting with persistent respiratory symptoms, pancreatic insufficiency and a second CF-causing mutation. Two were diagnosed with CFTR-RD, presenting with bronchiectasis, intermediate sweat test and a second mutation known to cause CFTR-RD. Also, four carriers had a high suspicion of CFTR-RD, with bronchiectasis or emphysema and intermediate sweat test, although due to the lack of another CFTR mutation and a second functional test, definite diagnosis has not been made. Haplotype analysis provided evidence of a common haplotype in all individuals with co-segregation of the c.489+3A>G variant with p.Cys1400Ter mutation.

CONCLUSION: The intronic c.489+3A>G variant co-segregates extensively with p.Cys1400Ter in Cyprus as an ancestral combination due to a possible founder effect. Before providing genetic counselling to subjects identified through population screening to harbour the c.489+3A>G variant, extensive analysis of CFTR including gene rearrangements should be performed to identify possible other mutations in cis, especially in Mediterranean countries where this complex allele is probably common. Further research is warranted to fully delineate the clinical implications of the in cis co-segregation of p.Cys1400Ter with c.489+3A>G, even in the absence of pathogenic variants in the other CFTR allele.

PMID:40301948 | DOI:10.1186/s13023-025-03714-3

Nat Med. 2025 Apr 29. doi: 10.1038/s41591-025-03678-8. Online ahead of print.

ABSTRACT

Bacteriophage (phage) therapy, which uses lytic viruses as antimicrobials, is a potential strategy to address the antimicrobial resistance crisis. Cystic fibrosis, a disease complicated by recurrent Pseudomonas aeruginosa pulmonary infections, is an example of the clinical impact of antimicrobial resistance. Here, using a personalized phage therapy strategy that selects phages for a predicted evolutionary trade-off, nine adults with cystic fibrosis (eight women and one man) of median age 32 (range 22-46) years were treated with phages on a compassionate basis because their clinical course was complicated by multidrug-resistant or pan-drug-resistant Pseudomonas that was refractory to prior courses of standard antibiotics. The individuals received a nebulized cocktail or single-phage therapy without adverse events. Five to 18 days after phage therapy, sputum Pseudomonas decreased by a median of 104 CFU ml-1, or a mean difference of 102 CFU ml-1 (P = 0.006, two-way analysis of variance with Dunnett's multiple-comparisons test), without altering sputum microbiome, and an analysis of sputum Pseudomonas showed evidence of trade-offs that decreased antibiotic resistance or bacterial virulence. In addition, an improvement of 6% (median) and 8% (mean) predicted FEV1 was observed 21-35 days after phage therapy (P = 0.004, Wilcoxon signed-rank t-test), which may reflect the combined effects of decreased bacterial sputum density and phage-driven trade-offs. These results show that a personalized, nebulized phage therapy trade-off strategy may affect clinical and microbiologic endpoints, which must be evaluated in larger clinical trials.

PMID:40301561 | DOI:10.1038/s41591-025-03678-8

Nat Commun. 2025 Apr 29;16(1):4021. doi: 10.1038/s41467-025-59136-z.

ABSTRACT

We present an efficient method for synthesizing cationic poly(ethylene imine) derivatives using the multicomponent split-Ugi reaction to create a library of functional ionizable lipopolymers. Here we show 155 polymers, formulated into polyplexes, to establish structure-activity relationships essential for endosomal escape and transfection. A lead structure is identified, and lipopolymer-lipid hybrid nanoparticles are developed to deliver mRNA to lung endothelium and immune cells, including T cells, with low in vivo toxicity. These nanoparticles show significant improvements in mRNA delivery to the lung compared to in vivo-JetPEI® and demonstrate effective delivery of therapeutic mRNA(s) of various sizes. IL-12 mRNA-loaded nanoparticles delay Lewis Lung cancer progression, while human CFTR mRNA restores CFTR protein function in CFTR knockout mice. Additionally, we demonstrate in vivo CRISPR-Cas9 mRNA delivery, achieving gene editing in lung tissue and successful PD-1 knockout in T cells in mice. These results highlight the platform's potential for systemic gene therapy delivery.

PMID:40301362 | DOI:10.1038/s41467-025-59136-z

Pharmacoeconomics. 2025 Apr 29. doi: 10.1007/s40273-025-01497-w. Online ahead of print.

ABSTRACT

BACKGROUND: Cystic fibrosis (CF) is a rare genetic condition requiring extensive medical care, which has a significant impact on people with CF. Advances in treatment have extended life expectancy, yet there remains a significant economic burden to manage CF. Cost-effectiveness analysis (CEA) is crucial for evaluating the economic value of treatments and screening for CF. This scoping review seeks to highlight the best practices and gaps in the current evidence base, contributing to robust and comparable CEAs in CF research.

METHODS: A scoping review was conducted using PubMed and Embase. Studies were included if they featured a CEA focused on CF treatment. Data extraction covered study characteristics, model inputs, and modeling assumptions. A qualitative synthesis was conducted to assess the inclusion of considerations for both healthcare and societal impacts.

RESULTS: In total, 11 studies were included. Of these, six focused on evaluations of supportive therapies for CF and five focused on evaluation of cystic fibrosis transmembrane conductance regulator (CFTR) modulators. Heterogeneity in comparators and drug costing methods complicated cross-study comparisons. A qualitative review revealed differences in the types of costs and outcomes considered. Studies captured long-term disease progression, health-related quality-of-life effects, and direct medical costs.

CONCLUSIONS: This review highlights the complexity of CEAs for CF treatment and underscores the need for standardized methodologies and comprehensive evaluations, including broader economic impacts, to support more robust analyses and better-informed decision-making in CF treatment.

PMID:40301297 | DOI:10.1007/s40273-025-01497-w

J Heart Lung Transplant. 2025 Apr 20:S1053-2498(25)01917-5. doi: 10.1016/j.healun.2025.04.010. Online ahead of print.

ABSTRACT

BACKGROUND: CD26/DPP-IV inhibitors (gliptins) target pro-inflammatory pathways that contribute to the development of chronic lung allograft dysfunction (CLAD). We analyzed longitudinal clinical data from 6 North American lung transplant centers to elucidate the effect of gliptin exposure on CLAD development after lung transplantation.

METHODS: This cohort included 6 North American lung transplant centers, four sites from the Clinical Trials in Organ Transplantation-20 study and 2 additional sites. First lung transplant recipients between December 2015 and August 2018 were eligible with follow up through June 2021. Gliptin exposures prior to CLAD onset in addition to CLAD risk factors were included in the models. The primary endpoint was a composite of probable CLAD, CLAD related deaths, and CLAD related re-transplant. Cox regression models were used to assess the association between gliptin use and the CLAD composite endpoint.

RESULTS: 779 patients met inclusion criteria, with 126 (16.2%) having any gliptin exposure. 233 (29.9%) patients experienced probable CLAD composite outcome. Across all centers, gliptin exposure at any point was not associated with probable CLAD or definite CLAD across the study period. In a post-hoc analysis of centers with median gliptin exposures > 6 months, exposure within the first 90 days post-transplant was associated with a decreased risk of definite CLAD composite across the study period (HR 0.25; 95% CI, 0.07, 0.83; p<0.05).

CONCLUSIONS: The association of gliptins and CLAD is complex, but early gliptin use may help protect against CLAD if started within 90 days post-transplant and used for a prolonged period.

PMID:40300676 | DOI:10.1016/j.healun.2025.04.010

Am J Nephrol. 2025 Apr 29:1-17. doi: 10.1159/000545614. Online ahead of print.

ABSTRACT

INTRODUCTION: Autosomal dominant polycystic kidney disease (ADPKD) is a genetic disorder that is characterized by the development of fluid-filled kidney cysts, which often lead to kidney failure. The vasopressin receptor 2 antagonist, tolvaptan, is the only approved treatment that slows the progression of ADPKD. There is an unmet need for treatment options for patients with ADPKD because tolvaptan has limited efficacy and non-negligible side effects. In vitro and in vivo data suggest that inhibition of the cystic fibrosis transmembrane conductance regulator (CFTR) may be a suitable approach to treating ADPKD. Here, we assessed the capacity of GLPG2737, a CFTR inhibitor, to inhibit cyst growth in preclinical models of ADPKD.

METHODS: We investigated the ability of GLPG2737 to modulate CFTR activity in mouse kidney inner medullary collecting duct (mIMCD-3) epithelial cells by measuring chloride flux, and to prevent cyst growth in mIMCD-3 cells, cells from human ADPKD kidney donors, and metanephric organ cultures (MOCs). We assessed cyst volume, kidney weight or volume, and blood urea nitrogen (BUN) in two mouse ADPKD models (Pkd1 kidney-specific knockout mouse model; Pkd1RC/RC mouse model) that received GLPG2737, tolvaptan, or their combination. Statistical tests used for data analysis were based on the normality and variance of the data.

RESULTS: GLPG2737 inhibited chloride flux in mIMCD-3 cells with an IC50 of 2.41 µM. In a 3D assay, GLPG2737 inhibited cyst growth in both wild-type (IC50 = 2.36 µM) and Pkd1 knockout (IC50 = 2.5 µM) mIMCD-3 cells. Preincubation of human ADPKD kidney cells with 10 µM of GLPG2737, 10 µM of tolvaptan, or their combination prevented forskolin-induced cyst growth by 40%, 29%, and 70%, respectively. Furthermore, 10 µM of GLPG2737 inhibited cyst growth in MOCs, decreasing the cyst area by 67% and the number of cysts per area by 46% after 6 days of culture. In both in vivo models, GLPG2737, tolvaptan, or their combination improved the projected cyst volume. In the Pkd1RC/RC model, GLPG2737 also improved the total kidney volume normalized to tibia length (LnTKV) and BUN, while tolvaptan improved the LnTKV and fibrosis but did not lower BUN at sacrifice. The combination reduced all parameters measured in the Pkd1RC/RC model, including cyclic adenosine monophosphate (cAMP) content in the kidneys.

CONCLUSIONS: Our findings in preclinical models provide evidence of the therapeutic potential of CFTR inhibition, and its possible combination with tolvaptan. The present work shows that targeting CFTR is a valid strategy to slow ADPKD progression.

PMID:40300563 | DOI:10.1159/000545614

Knee Surg Relat Res. 2025 Apr 29;37(1):17. doi: 10.1186/s43019-025-00268-3.

NO ABSTRACT

PMID:40302005 | DOI:10.1186/s43019-025-00268-3

J Cheminform. 2025 Apr 29;17(1):65. doi: 10.1186/s13321-025-01010-7.

ABSTRACT

The electron density is an important object in quantum chemistry that is crucial for many downstream tasks in drug design. Recent deep learning approaches predict the electron density around a molecule from atom types and atom positions. Most of these methods use the plane wave (PW) numerical method as a source of ground-truth training data. However, the drug design field mostly uses the Linear Combination of Atomic Orbitals (LCAO) for computation of quantum properties. In this study, we focus on prediction of the electron density for drug-like substances and training neural networks with LCAO-based datasets. Our experiments show that proper handling of large amplitudes of core orbitals is crucial for training on LCAO-based data. We propose to store the electron density with the standard grids instead of the uniform grid. This allowed us to reduce the number of probing points per molecule by 43 times and reduce storage space requirements by 8 times. Finally, we propose a novel architecture based on the DeepDFT model that we name LAGNet. It is specifically designed and tuned for drug-like substances and ∇ 2 DFT dataset.

PMID:40301997 | DOI:10.1186/s13321-025-01010-7

J Transl Med. 2025 Apr 29;23(1):482. doi: 10.1186/s12967-025-06480-9.

ABSTRACT

BACKGROUND: Ttyrosine kinase inhibitors (TKIs) represent the standard first-line treatment for patients with epidermal growth factor receptor (EGFR)-mutant lung adenocarcinoma. However, not all patients with EGFR mutations respond to TKIs. This study aims to develop a deep learning radiological-pathological-clinical (DLRPC) model that integrates computed tomography (CT) images, hematoxylin and eosin (H&E)-stained aspiration biopsy samples, and clinical data to predict the response in EGFR-mutant lung adenocarcinoma patients undergoing TKIs treatment.

METHODS: We retrospectively analyzed data from 214 lung adenocarcinoma patients who received TKIs treatment from two medical centers between September 2013 and June 2023. The DLRPC model leverages paired CT, pathological images and clinical data, incorporating a clinical-based attention mask to further explore the cross-modality associations. To evaluate its diagnostic performance, we compared the DLRPC model against single-modality models and a decision level fusion model based on Dempster-Shafer theory. Model performances metrics, including area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were used for evaluation. The Delong test assessed statistically significantly differences in AUC among models.

RESULTS: The DLRPC model demonstrated strong performance, achieving an AUC value of 0.8424. It outperformed the single-modality models (AUC = 0.6894, 0.7753, 0.8052 for CT model, pathology model and clinical model, respectively. P < 0.05). Additionally, the DLRPC model surpassed the decision level fusion model (AUC = 0.8132, P < 0.05).

CONCLUSION: The DLRPC model effectively predicts the response of EGFR-mutant lung adenocarcinoma patients to TKIs, providing a promising tool for personalized treatment decisions in lung cancer management.

PMID:40301933 | DOI:10.1186/s12967-025-06480-9

BMC Musculoskelet Disord. 2025 Apr 29;26(1):419. doi: 10.1186/s12891-025-08602-2.

ABSTRACT

BACKGROUND: In this study, a computed tomography (CT)-vision transformer (ViT) framework for diagnosing lumbar disc herniation (LDH) was proposed for the first time by taking advantage of the multidirectional advantages of CT and a ViT.

METHODS: The proposed ViT model was trained and validated on a dataset consisting of 983 patients, including 2100 CT images. We compared the performance of the ViT model with that of several convolutional neural networks (CNNs), including ResNet18, ResNet50, LeNet, AlexNet, and VGG16, across two primary tasks: vertebra localization and disc abnormality classification.

RESULTS: The integration of a ViT with CT imaging allowed the constructed model to capture the complex spatial relationships and global dependencies within scans, outperforming CNN models and achieving accuracies of 97.13% and 93.63% in terms of vertebra localization and disc abnormality classification, respectively. The performance of the model was further validated via gradient-weighted class activation mapping (Grad-CAM), providing interpretable insights into the regions of the CT scans that contributed to the model predictions.

CONCLUSION: This study demonstrated the potential of a ViT for diagnosing LDH using CT imaging. The results highlight the promising clinical applications of this approach, particularly for enhancing the diagnostic efficiency and transparency of medical AI systems.

PMID:40301802 | DOI:10.1186/s12891-025-08602-2

BMC Oral Health. 2025 Apr 30;25(1):665. doi: 10.1186/s12903-025-06017-y.

ABSTRACT

The classification of intraoral teeth structures is a critical component in modern dental analysis and forensic dentistry. Traditional methods, relying on 2D imaging, often suffer from limitations in accuracy and comprehensiveness due to the complex three-dimensional (3D) nature of dental anatomy. Although 3D imaging introduces the third dimension, offering a more comprehensive view, it also introduces additional challenges due to the irregular nature of the data. Our proposed approach addresses these issues with a novel method that extracts critical representative features from 3D tooth models and transforms them into a 2D image format suitable for detailed analysis. The 2D images are subsequently processed using a recurrent neural network (RNN) architecture, which effectively detects complex patterns essential for accurate classification, while its capability to manage sequential data is further augmented by fully connected layers specifically designed for this purpose. This innovative approach improves accuracy and diagnostic efficiency by reducing manual analysis and speeding up processing time, overcoming the challenges of 3D data irregularity and leveraging its detailed representation, thereby setting a new standard in dental identification.

PMID:40301795 | DOI:10.1186/s12903-025-06017-y

BMC Bioinformatics. 2025 Apr 29;26(1):116. doi: 10.1186/s12859-025-06123-2.

ABSTRACT

Protein-protein interactions (PPIs) refer to the phenomenon of protein binding through various types of bonds to execute biological functions. These interactions are critical for understanding biological mechanisms and drug research. Among these, the protein binding interface is a critical region involved in protein-protein interactions, particularly the hotspot residues on it that play a key role in protein interactions. Current deep learning methods trained on large-scale data can characterize proteins to a certain extent, but they often struggle to adequately capture information about protein binding interfaces. To address this limitation, we propose the PPI-Graphomer module, which integrates pretrained features from large-scale language models and inverse folding models. This approach enhances the characterization of protein binding interfaces by defining edge relationships and interface masks on the basis of molecular interaction information. Our model outperforms existing methods across multiple benchmark datasets and demonstrates strong generalization capabilities.

PMID:40301762 | DOI:10.1186/s12859-025-06123-2

BMC Med Imaging. 2025 Apr 29;25(1):139. doi: 10.1186/s12880-025-01623-2.

ABSTRACT

BACKGROUND: To assess the effect of the combination of deep learning reconstruction (DLR) and time-resolved maximum intensity projection (tMIP) or time-resolved average (tAve) post-processing method on image quality of CTA derived from low-dose cerebral CTP.

METHODS: Thirty patients underwent regular dose CTP (Group A) and other thirty with low-dose (Group B) were retrospectively enrolled. Group A were reconstructed with hybrid iterative reconstruction (R-HIR). In Group B, four image datasets of CTA were gained: L-HIR, L-DLR, L-DLRtMIP and L-DLRtAve. The CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and subjective images quality were calculated and compared. The Intraclass Correlation (ICC) between CTA and MRA of two subgroups were calculated.

RESULTS: The low-dose group achieved reduction of radiation dose by 33% in single peak arterial phase and 18% in total compared to the regular dose group (single phase: 0.12 mSv vs 0.18 mSv; total: 1.91mSv vs 2.33mSv). The L-DLRtMIP demonstrated higher CT values in vessels compared to R-HIR (all P < 0.05). The CNR of vessels in L-HIR were statistically inferior to R-HIR (all P < 0.001). There was no significant different in image noise and CNR of vessels between L-DLR and R-HIR (all P > 0.05, except P = 0.05 for CNR of ICAs, 77.19 ± 21.64 vs 73.54 ± 37.03). However, the L-DLRtMIP and L-DLRtAve presented lower image noise, higher CNR (all P < 0.05) and subjective scores (all P < 0.001) in vessels than R-HIR. The diagnostic accuracy in Group B was excellent (ICC = 0.944).

CONCLUSION: Combining DLR with tMIP or tAve allows for reduction in radiation dose by about 33% in single peak arterial phase and 18% in total in CTP scanning, while further improving image quality of CTA derived from CTP data when compared to HIR.

PMID:40301751 | DOI:10.1186/s12880-025-01623-2

Sci Rep. 2025 Apr 29;15(1):15002. doi: 10.1038/s41598-025-99576-7.

ABSTRACT

Brain tumor detection is essential for early diagnosis and successful treatment, both of which can significantly enhance patient outcomes. To evaluate brain MRI scans and categorize them into four types-pituitary, meningioma, glioma, and normal-this study investigates a potent artificial intelligence (AI) technique. Even though AI has been utilized in the past to detect brain tumors, current techniques still have issues with accuracy and dependability. Our study presents a novel AI technique that combines two distinct deep learning models to enhance this. When combined, these models improve accuracy and yield more trustworthy outcomes than when used separately. Key performance metrics including accuracy, precision, and dependability are used to assess the system once it has been trained using MRI scan pictures. Our results show that this combined AI approach works better than individual models, particularly in identifying different types of brain tumors. Specifically, the InceptionV3 + Xception combination hit an accuracy level of 98.50% in training and 98.30% in validation. Such results further argue the potential application for advanced AI techniques in medical imaging while speaking even more strongly to the fact that multiple AI models used concurrently are able to enhance brain tumor detection.

PMID:40301625 | DOI:10.1038/s41598-025-99576-7