Front Plant Sci. 2025 Feb 3;16:1473153. doi: 10.3389/fpls.2025.1473153. eCollection 2025.

ABSTRACT

Sowing uniformity is an important evaluation indicator of mechanical sowing quality. In order to achieve accurate evaluation of sowing uniformity in hybrid rice mechanical sowing, this study takes the seeds in a seedling tray of hybrid rice blanket-seedling nursing as the research object and proposes a method for evaluating sowing uniformity by combining image processing methods and the ODConv_C2f-ECA-WIoU-YOLOv8n (OEW-YOLOv8n) network. Firstly, image processing methods are used to segment seed image and obtain seed grids. Next, an improved model named OEW-YOLOv8n based on YOLOv8n is proposed to identify the number of seeds in a unit seed grid. The improved strategies include the following: (1) Replacing the Conv module in the Bottleneck of C2f modules with the Omni-Dimensional Dynamic Convolution (ODConv) module, where C2f modules are located at the connection between the Backbone and Neck. This improvement can enhance the feature extraction ability of the Backbone network, as the new modules can fully utilize the information of all dimensions of the convolutional kernel. (2) An Efficient Channel Attention (ECA) module is added to the Neck for improving the network's capability to extract deep semantic feature information of the detection target. (3) In the Bbox module of the prediction head, the Complete Intersection over Union (CIoU) loss function is replaced by the Weighted Intersection over Union version 3 (WIoUv3) loss function to improve the convergence speed of the bounding box loss function and reduce the convergence value of the loss function. The results show that the mean average precision (mAP) of the OEW-YOLOv8n network reaches 98.6%. Compared to the original model, the mAP improved by 2.5%. Compared to the advanced object detection algorithms such as Faster-RCNN, SSD, YOLOv4, YOLOv5s YOLOv7-tiny, and YOLOv10s, the mAP of the new network increased by 5.2%, 7.8%, 4.9%, 2.8% 2.9%, and 3.3%, respectively. Finally, the actual evaluation experiment showed that the test error is from -2.43% to 2.92%, indicating that the improved network demonstrates excellent estimation accuracy. The research results can provide support for the mechanized sowing quality detection of hybrid rice and the intelligent research of rice seeder.

PMID:39963535 | PMC:PMC11830705 | DOI:10.3389/fpls.2025.1473153

Front Plant Sci. 2025 Feb 3;16:1462694. doi: 10.3389/fpls.2025.1462694. eCollection 2025.

ABSTRACT

The increasing availability of genetic and genomic resources has underscored the need for automated microscopic phenotyping in plant-pathogen interactions to identify genes involved in disease resistance. Building on accumulated experience and leveraging automated microscopy and software, we developed BluVision Micro, a modular, machine learning-aided system designed for high-throughput microscopic phenotyping. This system is adaptable to various image data types and extendable with modules for additional phenotypes and pathogens. BluVision Micro was applied to screen 196 genetically diverse barley genotypes for interactions with powdery mildew fungi, delivering accurate, sensitive, and reproducible results. This enabled the identification of novel genetic loci and marker-trait associations in the barley genome. The system also facilitated high-throughput studies of labor-intensive phenotypes, such as precise colony area measurement. Additionally, BluVision's open-source software supports the development of specific modules for various microscopic phenotypes, including high-throughput transfection assays for disease resistance-related genes.

PMID:39963527 | PMC:PMC11832026 | DOI:10.3389/fpls.2025.1462694

Front Artif Intell. 2025 Feb 3;7:1449329. doi: 10.3389/frai.2024.1449329. eCollection 2024.

ABSTRACT

The accurate classification of potato leaf diseases plays a pivotal role in ensuring the health and productivity of crops. This study presents a unified approach for addressing this challenge by leveraging the power of Explainable AI (XAI) and transfer learning within a deep Learning framework. In this research, we propose a transfer learning-based deep learning model that is tailored for potato leaf disease classification. Transfer learning enables the model to benefit from pre-trained neural network architectures and weights, enhancing its ability to learn meaningful representations from limited labeled data. Additionally, Explainable AI techniques are integrated into the model to provide interpretable insights into its decision-making process, contributing to its transparency and usability. We used a publicly available potato leaf disease dataset to train the model. The results obtained are 97% for validation accuracy and 98% for testing accuracy. This study applies gradient-weighted class activation mapping (Grad-CAM) to enhance model interpretability. This interpretability is vital for improving predictive performance, fostering trust, and ensuring seamless integration into agricultural practices.

PMID:39963448 | PMC:PMC11830750 | DOI:10.3389/frai.2024.1449329

Front Ophthalmol (Lausanne). 2025 Feb 3;4:1497848. doi: 10.3389/fopht.2024.1497848. eCollection 2024.

ABSTRACT

INTRODUCTION: Glaucoma, optic neuritis (ON), and non-arteritic anterior ischemic optic neuropathy (NAION) produce distinct patterns of retinal ganglion cell (RGC) damage. We propose a booster Variational Autoencoder (bVAE) to capture spatial variations in RGC loss and generate latent space (LS) montage maps that visualize different degrees and spatial patterns of optic nerve bundle injury. Furthermore, the bVAE model is capable of tracking the spatial pattern of RGC thinning over time and classifying the underlying cause.

METHODS: The bVAE model consists of an encoder, a display decoder, and a booster decoder. The encoder decomposes input ganglion cell layer (GCL) thickness maps into two display latent variables (dLVs) and eight booster latent variables (bLVs). The dLVs capture primary spatial patterns of RGC thinning, while the display decoder reconstructs the GCL map and creates the LS montage map. The bLVs add finer spatial details, improving reconstruction accuracy. XGBoost was used to analyze the dLVs and bLVs, estimating normal/abnormal GCL thinning and classifying diseases (glaucoma, ON, and NAION). A total of 10,701 OCT macular scans from 822 subjects were included in this study.

RESULTS: Incorporating bLVs improved reconstruction accuracy, with the image-based root-mean-square error (RMSE) between input and reconstructed GCL thickness maps decreasing from 5.55 ± 2.29 µm (two dLVs only) to 4.02 ± 1.61 µm (two dLVs and eight bLVs). However, the image-based structural similarity index (SSIM) remained similar (0.91 ± 0.04), indicating that just two dLVs effectively capture the main GCL spatial patterns. For classification, the XGBoost model achieved an AUC of 0.98 for identifying abnormal spatial patterns of GCL thinning over time using the dLVs. Disease classification yielded AUCs of 0.95 for glaucoma, 0.84 for ON, and 0.93 for NAION, with bLVs further increasing the AUCs to 0.96 for glaucoma, 0.93 for ON, and 0.99 for NAION.

CONCLUSION: This study presents a novel approach to visualizing and quantifying GCL thinning patterns in optic neuropathies using the bVAE model. The combination of dLVs and bLVs enhances the model's ability to capture key spatial features and predict disease progression. Future work will focus on integrating additional image modalities to further refine the model's diagnostic capabilities.

PMID:39963427 | PMC:PMC11830743 | DOI:10.3389/fopht.2024.1497848

J Multidiscip Healthc. 2025 Feb 12;18:787-799. doi: 10.2147/JMDH.S492163. eCollection 2025.

ABSTRACT

OBJECTIVE: To evaluate the effectiveness of deep learning technology based on generative adversarial networks (GANs) in reducing motion artifacts in cardiac magnetic resonance (CMR) cine sequences.

METHODS: The training and testing datasets consisted of 2000 and 200 pairs of clear and blurry images, respectively, acquired through simulated motion artifacts in CMR cine sequences. These datasets were used to establish and train a deep learning GAN model. To assess the efficacy of the deep learning network in mitigating motion artifacts, 100 images with simulated motion artifacts and 37 images with real-world motion artifacts encountered in clinical practice were selected. Image quality pre- and post-optimization was assessed using metrics including Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Leningrad Focus Measure, and a 5-point Likert scale.

RESULTS: After GAN optimization, notable improvements were observed in the PSNR, SSIM, and focus measure metrics for the 100 images with simulated artifacts. These metrics increased from initial values of 23.85±2.85, 0.71±0.08, and 4.56±0.67, respectively, to 27.91±1.74, 0.83±0.05, and 7.74±0.39 post-optimization. Additionally, the subjective assessment scores significantly improved from 2.44±1.08 to 4.44±0.66 (P<0.001). For the 37 images with real-world artifacts, the Tenengrad Focus Measure showed a significant enhancement, rising from 6.06±0.91 to 10.13±0.48 after artifact removal. Subjective ratings also increased from 3.03±0.73 to 3.73±0.87 (P<0.001).

CONCLUSION: GAN-based deep learning technology effectively reduces motion artifacts present in CMR cine images, demonstrating significant potential for clinical application in optimizing CMR motion artifact management.

PMID:39963324 | PMC:PMC11830935 | DOI:10.2147/JMDH.S492163

Front Bioinform. 2025 Feb 3;5:1520382. doi: 10.3389/fbinf.2025.1520382. eCollection 2025.

ABSTRACT

Proteins, composed of amino acids, are crucial for a wide range of biological functions. Proteins have various interaction sites, one of which is the protein-ligand binding site, essential for molecular interactions and biochemical reactions. These sites enable proteins to bind with other molecules, facilitating key biological functions. Accurate prediction of these binding sites is pivotal in computational drug discovery, helping to identify therapeutic targets and facilitate treatment development. Machine learning has made significant contributions to this field by improving the prediction of protein-ligand interactions. This paper reviews studies that use machine learning to predict protein-ligand binding sites from sequence data, focusing on recent advancements. The review examines various embedding methods and machine learning architectures, addressing current challenges and the ongoing debates in the field. Additionally, research gaps in the existing literature are highlighted, and potential future directions for advancing the field are discussed. This study provides a thorough overview of sequence-based approaches for predicting protein-ligand binding sites, offering insights into the current state of research and future possibilities.

PMID:39963299 | PMC:PMC11830693 | DOI:10.3389/fbinf.2025.1520382

Front Neurosci. 2025 Feb 3;19:1461654. doi: 10.3389/fnins.2025.1461654. eCollection 2025.

ABSTRACT

INTRODUCTION: Music has a profound impact on human emotions, capable of eliciting a wide range of emotional responses, a phenomenon that has been effectively harnessed in the field of music therapy. Given the close relationship between music and language, researchers have begun to explore how music influences brain activity and cognitive processes by integrating artificial intelligence with advancements in neuroscience.

METHODS: In this study, a total of 120 subjects were recruited, all of whom were students aged between 19 and 26 years. Each subject is required to listen to six 1-minute music segments expressing different emotions and speak at the 40-second mark. In terms of constructing the classification model, this study compares the classification performance of deep neural networks with other machine learning algorithms.

RESULTS: The differences in EEG signals between different emotions during speech are more pronounced compared to those in a quiet state. In the classification of EEG signals for speaking and quiet states, using deep neural network algorithms can achieve accuracies of 95.84% and 96.55%, respectively.

DISCUSSION: Under the stimulation of music with different emotions, there are certain differences in EEG between speaking and resting states. In the construction of EEG classification models, the classification performance of deep neural network algorithms is superior to other machine learning algorithms.

PMID:39963261 | PMC:PMC11830716 | DOI:10.3389/fnins.2025.1461654

J Biomed Opt. 2025 Feb;30(2):026001. doi: 10.1117/1.JBO.30.2.026001. Epub 2025 Feb 17.

ABSTRACT

SIGNIFICANCE: Current methods for complex conjugate removal (CCR) in frequency-domain optical coherence tomography (FD-OCT) often require additional hardware components, which increase system complexity and cost. A software-based solution would provide a more efficient and cost-effective alternative.

AIM: We aim to develop a deep learning approach to effectively remove complex conjugate artifacts (CCAs) from OCT scans without the need for extra hardware components.

APPROACH: We introduce a deep learning method that employs generative adversarial networks to eliminate CCAs from OCT scans. Our model leverages both conventional intensity images and phase images from the OCT scans to enhance the artifact removal process.

RESULTS: Our CCR-generative adversarial network models successfully converted conventional OCT scans with CCAs into artifact-free scans across various samples, including phantoms, human skin, and mouse eyes imaged in vivo with a phase-stable swept source-OCT prototype. The inclusion of phase images significantly improved the performance of the deep learning models in removing CCAs.

CONCLUSIONS: Our method provides a low-cost, data-driven, and software-based solution to enhance FD-OCT imaging capabilities by the removal of CCAs.

PMID:39963188 | PMC:PMC11831228 | DOI:10.1117/1.JBO.30.2.026001

Nanoscale. 2025 Feb 18. doi: 10.1039/d4nr05458j. Online ahead of print.

ABSTRACT

In addition to its excellent photoelectronic properties, the CsPbBr3 perovskite has been reported as a low thermal conductivity (k) material. However, few studies investigated the microscopic mechanisms underlying its low k. Studying its thermal transport behavior is crucial for understanding its thermal properties and thus improving its thermal stability. Here, we train a DFT-level deep-learning potential (DP) of CsPbBr3 and explore its ultra-low k using nonequilibrium molecular dynamics (NEMD). The k calculated using NEMD is 0.43 ± 0.01 W m-1 K-1, which is consistent with experimental results. Furthermore, the Cs vacancy contributes to the decrease in k due to the distortion of the Pb-Br cage, which enhances phonon scattering and reduces the phonon lifetime. Our research reveals the significant potential of machine learning force fields in thermal and phonon behavior research and the valuable insights gained from defect-regulated thermal conductivity.

PMID:39963065 | DOI:10.1039/d4nr05458j

J Pathol Transl Med. 2025 Feb 18. doi: 10.4132/jptm.2024.10.23. Online ahead of print.

ABSTRACT

BACKGROUND: High-grade serous ovarian carcinoma (HGSC) exhibits significant heterogeneity, posing challenges for effective clinical categorization. Understanding the histomorphological diversity within HGSC could lead to improved prognostic stratification and personalized treatment approaches.

METHODS: We applied the Histomic Atlases of Variation Of Cancers model to whole slide images from The Cancer Genome Atlas dataset for ovarian cancer. Histologically distinct tumor clones were grouped into common histomic clusters. Principal component analysis and K-means clustering classified HGSC samples into three groups: highly differentiated (HD), intermediately differentiated (ID), and lowly differentiated (LD).

RESULTS: HD tumors showed diverse patterns, lower densities, and stronger eosin staining. ID tumors had intermediate densities and balanced staining, while LD tumors were dense, patternless, and strongly hematoxylin-stained. RNA sequencing revealed distinct patterns in mitochondrial oxidative phosphorylation and energy metabolism, with upregulation in the HD, downregulation in the LD, and the ID positioned in between. Survival analysis showed significantly lower overall survival for the LD compared to the HD and ID, underscoring the critical role of mitochondrial dynamics and energy metabolism in HGSC progression.

CONCLUSIONS: Deep learning-based histologic analysis effectively stratifies HGSC into clinically relevant prognostic groups, highlighting the role of mitochondrial dynamics and energy metabolism in disease progression. This method offers a novel approach to HGSC categorization.

PMID:39962925 | DOI:10.4132/jptm.2024.10.23

Front Plant Sci. 2025 Feb 3;16:1559814. doi: 10.3389/fpls.2025.1559814. eCollection 2025.

NO ABSTRACT

PMID:39963532 | PMC:PMC11830810 | DOI:10.3389/fpls.2025.1559814

Comput Struct Biotechnol J. 2024 Sep 27;23:3575-3583. doi: 10.1016/j.csbj.2024.09.018. eCollection 2024 Dec.

ABSTRACT

Accessible and easy-to-use standardized bioinformatics workflows are necessary to advance microbiome research from observational studies to large-scale, data-driven approaches. Standardized multi-omics data enables comparative studies, data reuse, and applications of machine learning to model biological processes. To advance broad accessibility of standardized multi-omics bioinformatics workflows, the National Microbiome Data Collaborative (NMDC) has developed the Empowering the Development of Genomics Expertise (NMDC EDGE) resource, a user-friendly, open-source web application (https://nmdc-edge.org). Here, we describe the design and main functionality of the NMDC EDGE resource for processing metagenome, metatranscriptome, natural organic matter, and metaproteome data. The architecture relies on three main layers (web application, orchestration, and execution) to ensure flexibility and expansion to future workflows. The orchestration and execution layers leverage best practices in software containers and accommodate high-performance computing and cloud computing services. Further, we have adopted a robust user research process to collect feedback for continuous improvement of the resource. NMDC EDGE provides an accessible interface for researchers to process multi-omics microbiome data using production-quality workflows to facilitate improved data standardization and interoperability.

PMID:39963423 | PMC:PMC11832004 | DOI:10.1016/j.csbj.2024.09.018

Small Methods. 2025 Feb 17:e2402111. doi: 10.1002/smtd.202402111. Online ahead of print.

ABSTRACT

Spatially resolved transcriptomics (SRT) has emerged as a transformative technology for elucidating cellular organization and tissue architecture. However, a significant challenge remains in identifying pathology-relevant spatial functional landscapes within the tissue microenvironment, primarily due to the limited integration of cell-cell communication dynamics. To address this limitation, SpaDCN, a Spatially Dynamic graph Convolutional Network framework is proposed, which aligns cell-cell communications and gene expression within a spatial context to reveal the spatial functional regions with the coherent cellular organization. To effectively transfer the influence of cell-cell communications on expression variation, SpaDCN respectively generates the node layer and edge layer of spatial graph representation from expression data and the ligand-receptor complex contributions and then employs a dynamic graph convolution to switch the propagation of node graph and edge graph. It is demonstrated that SpaDCN outperforms existing methods in identifying spatial domains and denoising expression across various platforms and species. Notably, SpaDCN excels in identifying marker genes with significant prognostic potential in cancer tissues. In conclusion, SpaDCN offers a powerful and precise tool for spatial domain detection in spatial transcriptomics, with broad applicability across various tissue types and research disciplines.

PMID:39962819 | DOI:10.1002/smtd.202402111

Oncologist. 2025 Feb 6;30(2):oyae320. doi: 10.1093/oncolo/oyae320.

ABSTRACT

BACKGROUND: The impact of concurrent proton pump inhibitors (PPIs) use on the prognosis of patients with breast cancer undergoing cyclin-dependent kinase inhibitors (CDKIs) treatment is currently uncertain. Considerable divergence exists regarding the clinical studies. In this study, we aim to perform a comprehensive analysis to evaluate the influence of concomitant PPI use on the effectiveness and adverse effects of CDKIs in patients with breast cancer.

METHODS: This study encompassed all pertinent clinical studies published up to the present, following the PRISMA guidelines. The study used hazard ratio (HR) or odds ratio (OR) as a summary statistic and used fixed or random effects models for pooled estimation.

RESULTS: This study incorporated 10 research articles involving 2993 participants. Among patients with breast cancer undergoing treatment with CDKIs, the simultaneous administration of PPIs was associated with a notable reduction in overall survival (HR = 2.00; 95% CI, 1.35-2.96). Nevertheless, no substantial correlation was observed between the simultaneous utilization of PPIs and the progression-free survival (PFS) of patients (HR = 1.30; 95% CI, 0.98-1.74). PFS did not change significantly when considering different drugs, treatment lines, or regions alone. Furthermore, the simultaneous administration of PPIs was found to result in a notable decrease in the incidence of grades 3/4 risk factors (OR = 0.63, 95% CI, 0.46-0.85).

CONCLUSION: The concurrent administration of PPIs did not result in significant alterations in the risk of disease advancement among patients with breast cancer undergoing CDKIs treatment. The utilization of PPIs led to a decrease in the adverse effects linked to the administration of CDKIs.

PMID:39963828 | DOI:10.1093/oncolo/oyae320

Eur Heart J Cardiovasc Pharmacother. 2025 Feb 17:pvaf014. doi: 10.1093/ehjcvp/pvaf014. Online ahead of print.

ABSTRACT

AIMS: Managing patients with atherosclerotic cardiovascular disease (ASCVD) and heart failure (HF) is challenging. While sodium-glucose cotransporter 2 inhibitors (SGLT2i) and glucagon-like peptide-1 receptor agonists (GLP-1 RA) show cardiovascular benefits, the impact of combining these agents is unclear. This study evaluated whether adding GLP-1 RA to SGLT2i provides additional benefits in patients with both ASCVD and HF.

METHODS AND RESULTS: This retrospective observational study utilized the TriNetX database to analyze patients with ASCVD and HF who initiated GLP-1 RA with SGLT2i or SGLT2i alone from August 1, 2016, to September 30, 2024. A total of 2 797 317 patients were identified, with 96 051 patients meeting inclusion criteria. After propensity score matching (PSM), 5 272 patients in each group were analyzed. Primary outcomes included mortality or hospitalization within one year; secondary outcomes examined mortality, hospitalization, and heart failure exacerbation (HFE). Patients receiving GLP-1RA and SGLT2i therapies had significantly lower risk of mortality or hospitalization (HR 0.78; 95% CI 0.74-0.83), mortality (HR 0.72; 95% CI 0.62-0.84), hospitalization (HR 0.78; 95% CI 0.73-0.83), and HFE (HR 0.77; 95% CI 0.72-0.83) versus SGLT2i alone. Subgroup analyses showed consistent benefits in patients with HFpEF, HFrEF, patients with diabetes, obesity, chronic kidney disease, or those using semaglutide or dulaglutide, while liraglutide use showed a neutral effect. Drug-related side effects were monitored as safety outcomes, which showed no significant differences between groups.

CONCLUSIONS: In ASCVD and HF patients, adding GLP-1 RA to SGLT2i reduces one-year mortality and hospitalization, warranting further investigation in diverse settings.

PMID:39963713 | DOI:10.1093/ehjcvp/pvaf014

BMC Bioinformatics. 2025 Feb 17;26(1):54. doi: 10.1186/s12859-025-06053-z.

ABSTRACT

Adverse drug reactions (ADRs) are among the global public health events that seriously endanger human life and cause high economic burdens. Therefore, predicting the possibility of their occurrence and taking early and effective response measures is of great significance. Constructing a correlation matrix between drugs and their adverse reactions, followed by effective correlation data mining, is one of the current strategies to predict ADRs using accessible public data. Since the number of known ADRs in real-world data is far less than the number of their unknown counterparts, the drug-ADR association matrix is very sparse, which greatly affects the classification performance of machine learning methods. To effectively address the problem of sparsity, we proposed a novel weighted pseudo-labeling framework that mines potential unknown drug-ADR pairs by integrating multiple weighted matrix factorization (MF) models and treating them as pseudo-labeled drug-ADR pairs. Pseudo-labeled data is added to the training set, and the MF model is fine-tuned to improve the classification performance. To prevent overfitting to easily found pseudo-labels and improve the quality of pseudo-labels, a novel weighting approach for pseudo-labels was adopted. This paper reproduces the baselines under the same experimental conditions to evaluate the performance of the proposed method on sparse data from the Side Effect Resource (SIDER) database. Experimental results showed that our method outperformed other baselines in the Area Under Precision-Recall and F1-scores and still maintained the best performance in sparser scenarios. Furthermore, we conducted a case study, and the results showed that our proposed framework efficiently predicted ADRs in the real world.

PMID:39962381 | DOI:10.1186/s12859-025-06053-z

JAMA Netw Open. 2025 Feb 3;8(2):e2460033. doi: 10.1001/jamanetworkopen.2024.60033.

ABSTRACT

IMPORTANCE: Donation after circulatory death (DCD) heart procurement has increased, but concerns remain about the effect of simultaneous heart and lung procurement, particularly with thoracoabdominal normothermic regional perfusion (TA-NRP), on the use of DCD lungs. Previous analyses exclude critical donor factors and organ nonuse, and rapidly rising DCD use may bias comparisons to historical controls.

OBJECTIVE: To use validated risk-adjusted models to assess whether DCD heart procurement via TA-NRP and direct procurement is associated with lung use.

DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study involved adult DCD donors between January 1, 2019, and September 30, 2024, listed in the Scientific Registry of Transplant Recipients (SRTR). The SRTR deceased donor yield model was used to develop an observed to expected (O:E) yield ratio of lung use obtained through DCD among 4 cohorts: cardiac DCD donors vs noncardiac DCD donors and cardiac DCD donors undergoing TA-NRP vs direct procurement. Temporal trends in O:E ratios were analyzed with the Cochran-Armitage test.

MAIN OUTCOMES AND MEASURES: The O:E ratios of DCD lung use.

RESULTS: Among 24 431 DCD donors (15 878 [65.0%] male; median [IQR] age, 49.0 [37.0-58.0] years), 22 607 were noncardiac DCD (14 375 [63.6%] male; median [IQR] age, 51.0 [39.0-58.0] years) and 1824 were cardiac DCD (1503 [82.4%] male; median [IQR] age, 32.0 [26.0-38.0] years) donors; noncardiac DCD donors were more likely to be smokers (6873 [30.4%] vs 227 [12.4%]; P < .001). Among cardiac DCD donors, 325 underwent TA-NRP, while 712 underwent direct procurement. TA-NRP donors had shorter median (IQR) lung ischemic times (6.07 [4.38-9.56] hours vs 8.12 [6.16-12.00] hours; P < .001) and distances to recipient hospitals (222 [9-626] nautical miles vs 331 [159-521] nautical miles; P = .050) than direct procurement donors. Lung use was higher among cardiac DCD donations compared with noncardiac DCD donations (16.7% vs 4.4%, P < .001). Within the cardiac DCD cohort, lung use was similar between TA-NRP and direct procurement (19.1% vs 18.7%; P = .88) cohorts. Both noncardiac DCD and cardiac DCD donors had observed lung yields greater than expected (O:E, 1.29 [95% CI, 1.21-1.35] and 1.79 [95% CI, 1.62-1.96]; both P < .001), although cardiac DCD yield was significantly higher than noncardiac DCD yield (P < .001). Both TA-NRP and direct procurement lung yields were greater than expected (O:E, 2.00 [95% CI, 1.60-2.43] and 1.77 [95% CI, 1.52-1.99]; both P < .001) but were not significantly different from each other (P = .83). The O:E ratios did not change significantly over time across all cohorts. Among recipients, the TA-NRP cohort experienced significantly better 90-day mortality (0 of 62 vs 9 of 128 patients [7.0%]; P = .03) and overall survival (4 of 62 patients [6.5%] vs 21 of 128 patients [16.4%]; P = .04) rates compared with the direct procurement cohort.

CONCLUSIONS AND RELEVANCE: In this cohort study of DCD donors, concomitant heart procurement provided better-than-expected rates of lung use as assessed with validated O:E use ratios regardless of procurement technique. The findings also suggest a survival benefit with improved 90-day and overall survival rates for the TA-NRP cohort compared with the direct procurement cohort. Policies should be developed to maximize the benefits of these donations.

PMID:39960670 | PMC:PMC11833517 | DOI:10.1001/jamanetworkopen.2024.60033

Sci Rep. 2025 Feb 17;15(1):5693. doi: 10.1038/s41598-025-85802-9.

ABSTRACT

Recently, deep learning-based medical image classification models have made substantial advancements. However, many existing models prioritize performance at the cost of efficiency, limiting their practicality in clinical use. Traditional Convolutional Neural Network (CNN)-based methods, Transformer-based methods, and hybrid approaches combining these two struggle to balance performance and model complexity. To achieve efficient predictions with a low parameter count, we propose DenseAttentionNetwork (DANet), a lightweight model for Alzheimer's disease detection in 3D MRI images. DANet leverages dense connections and a linear attention mechanism to enhance feature extraction and capture long-range dependencies. Its architecture integrates convolutional layers for localized feature extraction with linear attention for global context, enabling efficient multi-scale feature reuse across the network. By replacing traditional self-attention with a parameter-efficient linear attention mechanism, DANet overcomes some limitations of standard self-attention. Extensive experiments across multi-institutional datasets demonstrate that DANet achieves the best performance in area under the receiver operating characteristic curve (AUC), which underscores the model's robustness and effectiveness in capturing relevant features for Alzheimer's disease detection while also attaining a strong accuracy structure with fewer parameters. Visualizations based on activation maps further verify the model's ability to highlight AD-relevant regions in 3D MRI images, providing clinically interpretable insights into disease progression.

PMID:39962113 | DOI:10.1038/s41598-025-85802-9

Sci Rep. 2025 Feb 17;15(1):5815. doi: 10.1038/s41598-025-85703-x.

ABSTRACT

Alzheimer's Disease (AD) is a progressive condition of a neurological brain disorder recognized by symptoms such as dementia, memory loss, alterations in behaviour, and impaired reasoning abilities. Recently, many researchers have been working to develop an effective AD recognition system using deep learning (DL) based convolutional neural network (CNN) model aiming to deploy the automatic medical image diagnosis system. The existing system is still facing difficulties in achieving satisfactory performance in terms of accuracy and efficiency because of the lack of feature ineffectiveness. This study proposes a lightweight Stacked Convolutional Neural Network with a Channel Attention Network (SCCAN) for MRI based on AD classification to overcome the challenges. In the procedure, we sequentially integrate 5 CNN modules, which form a stack CNN aiming to generate a hierarchical understanding of features through multi-level extraction, effectively reducing noise and enhancing the weight's efficacy. This feature is then fed into a channel attention module to select the practical features based on the channel dimension, facilitating the selection of influential features. . Consequently, the model exhibits reduced parameters, making it suitable for training on smaller datasets. Addressing the class imbalance in the Kaggle MRI dataset, a balanced distribution of samples among classes is emphasized. Extensive experiments of the proposed model with the ADNI1 Complete 1Yr 1.5T, Kaggle, and OASIS-1 datasets showed 99.58%, 99.22%, and 99.70% accuracy, respectively. The proposed model's high performance surpassed state-of-the-art (SOTA) models and proved its excellence as a significant advancement in AD classification using MRI images.

PMID:39962097 | DOI:10.1038/s41598-025-85703-x

Insights Imaging. 2025 Feb 17;16(1):44. doi: 10.1186/s13244-025-01911-z.

ABSTRACT

OBJECTIVE: To assess the accuracy of deep learning reconstruction (DLR) technique on synthetic MRI (SyMRI) including T2 measurements and diagnostic performance of DLR synthetic MRI (SyMRIDL) in patients with knee osteoarthritis (KOA) using conventional MRI as standard reference.

MATERIALS AND METHODS: This prospective study recruited 36 volunteers and 70 patients with suspected KOA from May to October 2023. DLR and non-DLR synthetic T2 measurements (T2-SyMRIDL, T2-SyMRI) for phantom and in vivo knee cartilage were compared with multi-echo fast-spin-echo (MESE) sequence acquired standard T2 values (T2MESE). The inter-reader agreement on qualitative evaluation of SyMRIDL and the positive percent agreement (PPA) and negative percentage agreement (NPA) were analyzed using routine images as standard diagnosis.

RESULTS: DLR significantly narrowed the quantitative differences between T2-SyMRIDL and T2MESE for 0.8 ms with 95% LOA [-5.5, 7.1]. The subjective assessment between DLR synthetic MR images and conventional MRI was comparable (all p > 0.05); Inter-reader agreement for SyMRIDL and conventional MRI was substantial to almost perfect with values between 0.62 and 0.88. SyMRIDL MOAKS had substantial inter-reader agreement and high PPA/NPA values (95%/99%) using conventional MRI as standard reference. Moreover, T2-SyMRIDL measurements instead of non-DLR ones significantly differentiated normal-appearing from injury-visible cartilages.

CONCLUSION: DLR synthetic knee MRI provided both weighted images for clinical diagnosis and accurate T2 measurements for more confidently identifying early cartilage degeneration from normal-appearing cartilages.

CRITICAL RELEVANCE STATEMENT: One-acquisition synthetic MRI based on deep learning reconstruction provided an accurate quantitative T2 map and morphologic images in relatively short scan time for more confidently identifying early cartilage degeneration from normal-appearing cartilages compared to the conventional morphologic knee sequences.

KEY POINTS: Deep learning reconstruction (DLR) synthetic knee cartilage T2 values showed no difference from conventional ones. DLR synthetic T1-, proton density-, STIR-weighted images had high positive percent agreement and negative percentage agreement using MRI OA Knee Score features. DLR synthetic T2 measurements could identify early cartilage degeneration from normal-appearing ones.

PMID:39961957 | DOI:10.1186/s13244-025-01911-z