Eur J Nucl Med Mol Imaging. 2025 Feb 18. doi: 10.1007/s00259-025-07132-2. Online ahead of print.

ABSTRACT

PURPOSE: Quantitative analysis of PET images in brain PET/CT relies on MRI-derived regions of interest (ROIs). However, the pairs of PET/CT and MR images are not always available, and their alignment is challenging if their acquisition times differ considerably. To address these problems, this study proposes a deep learning framework for translating CT of PET/CT to synthetic MR images (MRSYN) and performing automated quantitative regional analysis using MRSYN-derived segmentation.

METHODS: In this retrospective study, 139 subjects who underwent brain [18F]FBB PET/CT and T1-weighted MRI were included. A U-Net-like model was trained to translate CT images to MRSYN; subsequently, a separate model was trained to segment MRSYN into 95 regions. Regional and composite standardised uptake value ratio (SUVr) was calculated in [18F]FBB PET images using the acquired ROIs. For evaluation of MRSYN, quantitative measurements including structural similarity index measure (SSIM) were employed, while for MRSYN-based segmentation evaluation, Dice similarity coefficient (DSC) was calculated. Wilcoxon signed-rank test was performed for SUVrs computed using MRSYN and ground-truth MR (MRGT).

RESULTS: Compared to MRGT, the mean SSIM of MRSYN was 0.974 ± 0.005. The MRSYN-based segmentation achieved a mean DSC of 0.733 across 95 regions. No statistical significance (P > 0.05) was found for SUVr between the ROIs from MRSYN and those from MRGT, excluding the precuneus.

CONCLUSION: We demonstrated a deep learning framework for automated regional brain analysis in PET/CT with MRSYN. Our proposed framework can benefit patients who have difficulties in performing an MRI scan.

PMID:39964542 | DOI:10.1007/s00259-025-07132-2

Radiology. 2025 Feb;314(2):e241351. doi: 10.1148/radiol.241351.

ABSTRACT

Background Deep learning (DL) methods enable faster shoulder MRI than conventional methods, but arthroscopy-validated evidence of good diagnostic performance is scarce. Purpose To validate the clinical efficacy of 7-minute threefold parallel imaging (PIx3)-accelerated DL super-resolution shoulder MRI against arthroscopic findings. Materials and Methods Adults with painful shoulder conditions who underwent PIx3-accelerated DL super-resolution 3-T shoulder MRI and arthroscopy between March and November 2023 were included in this retrospective study. Seven radiologists independently evaluated the MRI scan quality parameters and the presence of artifacts (Likert scale rating ranging from 1 [very bad/severe] to 5 [very good/absent]) as well as the presence of rotator cuff tears, superior and anteroinferior labral tears, biceps tendon tears, cartilage defects, Hill-Sachs lesions, Bankart fractures, and subacromial-subdeltoid bursitis. Interreader agreement based on κ values was evaluated, and diagnostic performance testing was conducted. Results A total of 121 adults (mean age, 55 years ± 14 [SD]; 75 male) who underwent MRI and arthroscopy within a median of 39 days (range, 1-90 days) were evaluated. The overall image quality was good (median rating, 4 [IQR, 4-4]), with high reader agreement (κ ≥ 0.86). Motion artifacts and image noise were minimal (rating of 4 [IQR, 4-4] for each), and reconstruction artifacts were absent (rating of 5 [IQR, 5-5]). Arthroscopy-validated abnormalities were detected with good or better interreader agreement (κ ≥ 0.68). The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve were 89%, 90%, 89%, and 0.89, respectively, for supraspinatus-infraspinatus tendon tears; 82%, 63%, 68%, and 0.68 for subscapularis tendon tears; 93%, 73%, 86%, and 0.83 for superior labral tears; 100%, 100%, 100%, and 1.00 for anteroinferior labral tears; 68%, 90%, 82%, and 0.80 for biceps tendon tears; 42%, 93%, 81%, and 0.64 for cartilage defects; 93%, 99%, 98%, and 0.94 for Hill-Sachs deformities; 100%, 99%, 99%, and 1.00 for osseous Bankart lesions; and 97%, 63%, 92%, and 0.80 for subacromial-subdeltoid bursitis. Conclusion Seven-minute PIx3-accelerated DL super-resolution 3-T shoulder MRI has good diagnostic performance for diagnosing tendinous, labral, and osteocartilaginous abnormalities. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Tuite in this issue.

PMID:39964264 | DOI:10.1148/radiol.241351

Radiology. 2025 Feb;314(2):e240473. doi: 10.1148/radiol.240473.

ABSTRACT

Background Individuals eligible for lung cancer screening with low-dose CT face a higher cardiovascular mortality risk. Purpose To investigate the association between changes in epicardial adipose tissue (EAT) at the 2-year interval and mortality in individuals undergoing serial low-dose CT lung cancer screening. Materials and Methods This secondary analysis of the National Lung Screening Trial obtained EAT volume and density from serial low-dose CT scans using a validated automated deep learning algorithm. EAT volume and density changes over 2 years were categorized into typical (decrease of 7% to increase of 11% and decrease of 3% to increase of 2%, respectively) and atypical (increase or decrease beyond typical) changes, which were associated with all-cause, cardiovascular, and lung cancer mortality. Uni- and multivariable Cox proportional hazard regression models-adjusted for baseline EAT values, age, sex, race, ethnicity, smoking, pack-years, heart disease or myocardial infarction, stroke, hypertension, diabetes, education status, body mass index, and coronary artery calcium-were performed. Results Among 20 661 participants (mean age, 61.4 years ± 5.0 [SD]; 12 237 male [59.2%]), 3483 (16.9%) died over a median follow-up of 10.4 years (IQR, 9.9-10.8 years) (cardiovascular related: 816 [23.4%]; lung cancer related: 705 [20.2%]). Mean EAT volume increased (2.5 cm3/m2 ± 11.0) and density decreased (decrease of 0.5 HU ± 3.0) over 2 years. Atypical changes in EAT volume were independent predictors of all-cause mortality (atypical increase: hazard ratio [HR], 1.15 [95% CI: 1.06, 1.25] [P < .001]; atypical decrease: HR, 1.34 [95% CI: 1.23, 1.46] [P < .001]). An atypical decrease in EAT volume was associated with cardiovascular mortality (HR, 1.27 [95% CI: 1.06, 1.51]; P = .009). EAT density increase was associated with all-cause, cardiovascular, and lung cancer mortality (HR, 1.29 [95% CI: 1.18, 1.40] [P < .001]; HR, 1.29 [95% CI: 1.08, 1.54] [P = .005]; HR, 1.30 [95% CI: 1.07, 1.57] [P = .007], respectively). Conclusion EAT volume increase and decrease and EAT density increase beyond typical on subsequent chest CT scans were associated with all-cause mortality in participants screened for lung cancer. EAT volume decrease and EAT density increase were associated with elevated risk of cardiovascular mortality after adjustment for baseline EAT values. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Fuss in this issue.

PMID:39964263 | DOI:10.1148/radiol.240473

ACS Sens. 2025 Feb 18. doi: 10.1021/acssensors.4c03096. Online ahead of print.

ABSTRACT

To enhance the sensitivity, integration, and practicality of the Raman detection system, a deep learning-based dual-functional subregional microfluidic integrated hydrogel surface-enhanced Raman scattering (SERS) platform is proposed in this paper. First, silver nanoparticles (Ag NPs) with a homogeneous morphology were synthesized using a one-step reduction method. Second, these Ag NPs were embedded in N-isopropylacrylamide/poly(vinyl alcohol) (Ag NPs-NIPAM/PVA) hydrogels. Finally, a dual-functional SERS platform featuring four channels, each equipped with a switch and a detection region, was developed in conjunction with microfluidics. This platform effectively allows the flow of the test material to be directed to a specific detection region by sequential activation of the hydrogel switches with an external heating element. It then utilizes the corresponding heating element in the detection region to adjust the gaps between Ag NPs, enabling the measurement of the Raman enhancement performance in the designated SERS detection area. The dual-functional microfluidic-integrated hydrogel SERS platform enables subregional sampling and simultaneous detection of multiple molecules. The platform demonstrated excellent detection performance for Rhodamine 6G (R6G), achieving a detection limit as low as 10-10 mol/L and an enhancement factor of 107, with relative standard deviations of the main characteristic peaks below 10%. Additionally, the platform is capable of simultaneous subarea detection of four real molecules─thiram, pyrene, anthracene, and dibutyl phthalate─combined with fully connected neural network technology, which offers improved predictability, practicality, and applicability for their classification and identification.

PMID:39964084 | DOI:10.1021/acssensors.4c03096

Drug Dev Ind Pharm. 2025 Feb 18:1-18. doi: 10.1080/03639045.2025.2468811. Online ahead of print.

ABSTRACT

OBJECTIVE: This review aims to explore innovative therapeutic strategies, with a particular focus on recent advancements in drug delivery systems using bioinspired nanomaterials such as solid lipid nanoparticles (SLNs) and nanostructured lipid carriers (NLCs) for the Idiopathic pulmonary fibrosis (IPF).

SIGNIFICANCE OF THE REVIEW: Current treatments for IPF, including the FDA-approved anti-fibrotic agents pirfenidone and nintedanib, primarily aim to slow disease progression rather than reverse fibrosis. Bioinspired nanomaterials like SLNs and NLCs have shown promise in enhancing the efficacy of anti-fibrotic agents by improving drug solubility, stability, and targeted delivery. These systems not only minimize systemic side effects but also maximize therapeutic impact in lung tissues, offering a new hope for improved patient management and outcomes in this debilitating disease.

KEY FINDINGS: SLNs facilitate sustained drug release and have demonstrated potential in delivering phosphodiesterase type 5 inhibitors effectively to lung cells. NLCs, on the other hand, exhibit superior biocompatibility and controlled release properties, making them suitable for pulmonary applications. Studies indicate that both SLNs and NLCs can enhance the bioavailability of drugs like ciprofloxacin and montelukast, thereby improving treatment outcomes in pulmonary conditions.

CONCLUSIONS: The integration of nanotechnology into anti-fibrotic therapy represents a significant advancement in addressing the challenges posed by IPF. By leveraging the unique properties of SLNs and NLCs, there is potential to overcome the limitations of current treatments and provide new therapeutic options that offer better management and improved outcomes for patients suffering from this debilitating disease.

PMID:39963904 | DOI:10.1080/03639045.2025.2468811

Proc Natl Acad Sci U S A. 2025 Feb 25;122(8):e2420961122. doi: 10.1073/pnas.2420961122. Epub 2025 Feb 18.

ABSTRACT

Protein Serine Kinase H1 (PSKH1) was recently identified as a crucial factor in kidney development and is overexpressed in prostate, lung, and kidney cancers. However, little is known about PSKH1 regulatory mechanisms, leading to its classification as a "dark" kinase. Here, we used biochemistry and mass spectrometry to define PSKH1's consensus substrate motif, protein interactors, and how interactors, including Ca2+ sensor proteins, promote or suppress activity. Intriguingly, despite the absence of a canonical Calmodulin binding motif, Ca2+-Calmodulin activated PSKH1 while, in contrast, the ER-resident Ca2+ sensor of the Cab45, Reticulocalbin, Erc55, Calumenin (CREC) family, Reticulocalbin-3, suppressed PSKH1 catalytic activity. In addition to antagonistic regulation of the PSKH1 kinase domain by Ca2+ sensing proteins, we identified UNC119B as a protein interactor that activates PSKH1 via direct engagement of the kinase domain. Our findings identify complementary allosteric mechanisms by which regulatory proteins tune PSKH1's catalytic activity and raise the possibility that different Ca2+ sensors may act more broadly to tune kinase activities by detecting and decoding extremes of intracellular Ca2+ concentrations.

PMID:39964718 | DOI:10.1073/pnas.2420961122

Eur J Nutr. 2025 Feb 18;64(2):97. doi: 10.1007/s00394-025-03600-5.

ABSTRACT

PURPOSE: Recent studies indicate that shift work may affect workers' eating habits and overall well-being. This study aimed to assess differences in eating patterns, sleep quality, and mental health between Italian shift and non-shift workers, with a focus on individual chronotype and the type of shift work (day vs. night shift).

METHODS: The cross-sectional study involved 322 subjects (166 shift and 156 non-shift workers). Eating habits were evaluated using a 7-day diary and the Medi-Lite questionnaire. Sleep quality was assessed with the Pittsburgh Sleep Quality Index (PSQI), and mental health with the Depression Anxiety Stress Scales (DASS). Individual chronotype was defined using the Morningness-Eveningness Questionnaire.

RESULTS: No significant differences in daily energy, macronutrient, and micronutrient intake between the two groups, nor in the temporal pattern of eating. However, shift workers had significantly (p < 0.05) lower adherence to the Mediterranean diet (MD) (7.6 ± 2.3 vs 8.1 ± 2.2) compared to non-shift workers. Shift workers also reported significantly poorer sleep quality (mean PSQI score 7.6 ± 3.7 vs. 5.8 ± 3.0) and higher levels of anxiety and stress symptoms. Among shift workers, those with an evening chronotype had significantly lower MD adherence than those with a morning chronotypes. Additionally, night shift workers experienced more sleep disturbances compared to day ones.

CONCLUSION: Shift workers reported lower MD adherence, poorer sleep quality, and a higher prevalence of anxiety and stress symptoms compared to a similar group of non-shift workers. Evening chronotypes and night shift work were associated with worse eating habits and sleep quality.

PMID:39964501 | DOI:10.1007/s00394-025-03600-5

Genomics Proteomics Bioinformatics. 2025 Feb 18:qzaf009. doi: 10.1093/gpbjnl/qzaf009. Online ahead of print.

ABSTRACT

In recent years, computational methods for quantifying cell type proportions from transcription data have gained significant attention, particularly those reference-based methods which have demonstrated high accuracy. However, there is currently a lack of comprehensive evaluation and guidance for available reference-based deconvolution methods in cell proportion deconvolution analysis. In this study, we introduce Deconvolution Evaluator (Deconer), a comprehensive toolkit for the evaluation of reference-based deconvolution methods. Deconer provides various simulated and real gene expression datasets, including both bulk and single-cell sequencing data, and offers multiple visualization interfaces. By utilizing Deconer, we conducted systematic comparisons of 16 reference-based deconvolution methods from different perspectives, including method robustness, accuracy in deconvolving rare components, signature gene selection, and building external reference. We also performed an in-depth analysis of the application scenarios and challenges in cell proportion deconvolution methods. Finally, we provided constructive suggestions for users in selecting and developing cell proportion deconvolution algorithms. This work presents novel insights to researchers, assisting them in choosing appropriate toolkits, applying solutions in clinical contexts, and advancing the development of deconvolution tools tailored to gene expression data. The tutorials, manual, source code, and demo data of Deconer are publicly available at https://honchkrow.github.io/Deconer/.

PMID:39963994 | DOI:10.1093/gpbjnl/qzaf009

Mol Biol Evol. 2025 Feb 18:msaf045. doi: 10.1093/molbev/msaf045. Online ahead of print.

ABSTRACT

In the wake of pandemics like COVID-19, which have zoonotic origins, the role of wildlife as reservoirs for emerging infectious diseases has garnered heightened attention. Migratory birds, traversing continents, represent a potent but under-researched vector for the spread of infectious diseases, including novel coronaviruses. This study delves into the genetic diversity and transmission dynamics of coronaviruses in migratory birds, presenting pivotal findings. From April 2019 to April 2023, we screened 5,263 migratory bird samples collected from Shanghai, China, identifying 372 coronavirus-positive samples belonging to five avian-related coronavirus subgenera and subsequently obtaining 120 complete genome sequences. To facilitate further research with a global perspective, the study curated all available 19,000 avian-associated CoVs and expanded the original 12 species to 16, including three novel coronavirus species identified in our study and one re-classified species from the public domain. The study illuminates the intricate genetic evolution and transmission dynamics of birds-related coronaviruses on a global scale. A notable aspect of our research is the identification of complex recombination patterns within the spike protein across different virus species and subgenera, highlighting migratory birds as a reservoir of coronavirus. Notably, the coronaviruses found in migratory birds, predominantly from the orders Anseriformes, Charadriiformes, and Pelecaniformes, with domestic ducks from Anseriformes playing a key role in bridging the transmission of coronaviruses between migratory and non-migratory birds. These findings reveal the genetic and recombination characteristics of coronaviruses in migratory birds, emphasizing the critical role of ecologically pivotal bird species in coronavirus transmission and genetic diversity shaping.

PMID:39963938 | DOI:10.1093/molbev/msaf045

Pathologie (Heidelb). 2025 Feb 18. doi: 10.1007/s00292-025-01418-w. Online ahead of print.

ABSTRACT

BACKGROUND: Besides reactions of the IgE-mediated immediate type, medicamentous therapies can cause a variety of different mucocutaneous adverse events. Exanthematous manifestations require a fast and certain diagnosis due to their extent, sometimes rapid progression, and mucous membrane or organ involvement.

OBJECTIVES: The spectrum of non-IgE-mediated exanthematic drug reactions is covered.

MATERIAL AND METHODS: The most relevant reactions are portrayed clinically and histopathologically.

RESULTS: Displayed are classical maculo-papular drug eruption, lichenoid drug reaction, acute generalized exanthematic pustulosis (AGEP), severe potentially life-threatening drug reactions such as Stevens-Johnson syndrome (SJS), and toxic epidermal necrolysis (TEN) as well as generalized bullous fixed drug eruption (GBFDE), drug reaction with eosinophilia and systemic symptoms (DRESS), and some others.

CONCLUSIONS: Cutaneous drug-related side effects cover a broad spectrum. Important for the correct treatment is a reliable diagnosis. In the case of severe, life-threatening drug reactions, however, permanent discontinuation of the drug is essential.

PMID:39964515 | DOI:10.1007/s00292-025-01418-w

Front Public Health. 2025 Feb 3;13:1520467. doi: 10.3389/fpubh.2025.1520467. eCollection 2025.

ABSTRACT

Rare diseases, affecting millions globally, pose a significant healthcare burden despite impacting a small population. While approximately 70% of all rare diseases are genetic and often begin in childhood, diagnosis remains slow and only 5% have approved treatments. The UN emphasizes improved access to primary care (diagnostic and potentially therapeutic) for these patients and their families. Next-generation sequencing (NGS) offers hope for earlier and more accurate diagnoses, potentially leading to preventative measures and targeted therapies. In here, we explore the therapeutic landscape for rare diseases, analyzing drugs in development and those already approved by the European Medicines Agency (EMA). We differentiate between orphan drugs with market exclusivity and repurposed existing drugs, both crucial for patients. By analyzing market size, segmentation, and publicly available data, this comprehensive study aims to pave the way for improved understanding of the treatment landscape and a wider knowledge accessibility for rare disease patients.

PMID:39963479 | PMC:PMC11830808 | DOI:10.3389/fpubh.2025.1520467

Front Public Health. 2025 Feb 3;13:1520467. doi: 10.3389/fpubh.2025.1520467. eCollection 2025.

ABSTRACT

Rare diseases, affecting millions globally, pose a significant healthcare burden despite impacting a small population. While approximately 70% of all rare diseases are genetic and often begin in childhood, diagnosis remains slow and only 5% have approved treatments. The UN emphasizes improved access to primary care (diagnostic and potentially therapeutic) for these patients and their families. Next-generation sequencing (NGS) offers hope for earlier and more accurate diagnoses, potentially leading to preventative measures and targeted therapies. In here, we explore the therapeutic landscape for rare diseases, analyzing drugs in development and those already approved by the European Medicines Agency (EMA). We differentiate between orphan drugs with market exclusivity and repurposed existing drugs, both crucial for patients. By analyzing market size, segmentation, and publicly available data, this comprehensive study aims to pave the way for improved understanding of the treatment landscape and a wider knowledge accessibility for rare disease patients.

PMID:39963479 | PMC:PMC11830808 | DOI:10.3389/fpubh.2025.1520467

BMC Pulm Med. 2025 Feb 17;25(1):81. doi: 10.1186/s12890-024-03455-2.

ABSTRACT

BACKGROUND: This study aimed to assess how Elexacaftor/Tezacaftor/Ivacaftor (ETI) influences lung function, Body Mass Index (BMI), Sweat Test (ST) and mental health of Cystic Fibrosis (CF) patients, emphasizing on depression and anxiety.

METHODS: We conducted an observational, prospective, multicentre study including 108 patients over 18 years old who initiated ETI therapy between December 2019 and December 2023. Patients underwent regular evaluations, including clinical, functional, and microbiological assessments, alongside completion of quality of life, anxiety, and depression questionnaires. We evaluated whether there was a difference in anxiety and depression levels over time.

RESULTS: After 12 months of treatment, significant improvements were noted in BMI, lung function (FEV1%), ST and various aspects of quality of life (CFQ-R). However, anxiety and depression levels did not differ significantly during the follow-up. When we stratified our sample by key groups, we observed that younger patients (under 28 years) and those with homozygous Phe508del mutations experienced significant higher anxiety with no differences on depression. Furthermore, anxiety and depression demonstrated a moderate correlation, strengthening over time.

CONCLUSIONS: Treatment with ETI establishes significant improvements in lung function, BMI, ST and quality of life in patients with CF. However, despite these positive outcomes, there were no significant changes observed in levels of anxiety and depression, except for individuals with homozygous mutation type and those younger than 28 years old, who exhibited significant higher levels of anxiety.

PMID:39962495 | DOI:10.1186/s12890-024-03455-2

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