Sci Rep. 2025 Jan 17;15(1):2346. doi: 10.1038/s41598-025-86976-y.

ABSTRACT

Brodalumab, a humanized monoclonal antibody that targets the interleukin-17 receptor A, is primarily used to manage moderate-to-severe plaque psoriasis. Although it has demonstrated favorable efficacy and safety in clinical trials, the strict inclusion and exclusion criteria may not fully reflect its safety profile in real-world settings. As its use becomes more widespread in clinical practice, understanding its safety in real-world applications is crucial.This study employed disproportionality analysis to assess the safety of brodalumab by examining all adverse event reports that identified brodalumab as the primary suspected drug in the FDA Adverse Event Reporting System database since 2017. Techniques such as the Reporting Odds Ratio, Proportional Reporting Ratio, Multi-item Gamma Poisson Shrinker, and Bayesian Confidence Propagation Neural Network were utilized to analyze the adverse events associated with brodalumab. Additionally, the Weibull distribution was used to model the temporal risk of adverse events.The study identified several adverse reactions already listed on the drug's label that showed positive signals, including arthralgia, headache, myalgia, suicidal ideation, oropharyngeal pain, injection site mass, and infections. Additionally, we found potential adverse reactions not noted on the drug's label that exhibited positive signals, including depression, increased blood pressure, peripheral swelling, gait disturbance, inability to walk, stress, myocardial infarction, sepsis, uveitis, nephrolithiasis, and interstitial lung disease. Moreover, this analysis highlighted the critical need for vigilant monitoring of adverse events, especially during the first month following the initiation of treatment.This study provides initial insights into the real-world safety of brodalumab, confirming known adverse reactions and uncovering additional potential risks. The results deliver vital information that can assist clinicians in making informed decisions when prescribing brodalumab for psoriasis treatment.

PMID:39824966 | DOI:10.1038/s41598-025-86976-y

J Hepatol. 2025 Jan 15:S0168-8278(25)00002-9. doi: 10.1016/j.jhep.2024.12.045. Online ahead of print.

ABSTRACT

BACKGROUND & AIMS: Lanifibranor is a pan-PPAR agonist that improves glucose/lipid metabolism and reverses steatohepatitis and fibrosis in adults with MASH. We tested its effect on insulin resistance at the level of different target tissues in relationship to change in intrahepatic triglyceride (IHTG) content.

METHODS: This phase 2, single center, study randomized (1:1) 38 patients with T2D and MASLD to receive lanifibranor 800 mg or placebo for 24 weeks. The primary endpoint was the change in IHTG (1H-MRS). The main prespecified secondary endpoint was the change in hepatic, muscle and adipose tissue insulin sensitivity using the gold-standard euglycemic hyperinsulinemic clamp technique measuring glucose turnover. Other secondary endpoints included changes in cardiometabolic parameters (i.e., HbA1c, lipid profile, adiponectin).

RESULTS: Lanifibranor compared to placebo significantly lowered IHTG (full analysis set [FAS] -44% vs. -12%, respectively; least squares mean difference -31%, 95% CI -51 to -12%; in completers -50% vs. -16%; both p<0.01). More patients reached ≥30% IHTG reduction with lanifibranor compared to placebo (FAS 65% vs. 22%; completers 79% vs. 29%; both p<0.01) and steatosis resolution (FAS 25% vs. 0%; p<0.05). Lanifibranor significantly improved hepatic and peripheral insulin resistance (i.e., fasting endogenous [primarily hepatic] glucose production, hepatic IR, and insulin-stimulated muscle glucose disposal or Rd). Secondary metabolic endpoints also improved (fasting glucose, insulin, HOMA-IR, HbA1c; HDL-C), and adiponectin increased 2.4-fold (all p<0.001). Lanifibranor caused modest weight gain (+2.7%). Adverse events were mild (gastrointestinal side effects, hemoglobin decrease) and drug-related TEAE leading to study discontinuation were balanced between groups.

CONCLUSIONS: Lanifibranor significantly improves hepatic, muscle and adipose tissue insulin resistance. Lanifibranor treatment was safe and effective in reducing hepatic steatosis and cardiometabolic risk factors associated with metabolic dysfunction.

IMPACT AND IMPLICATIONS: No prior studies have evaluated the effect of lanifibranor on insulin sensitivity at the level of muscle, liver and adipose tissue and its relationship to changes in intrahepatic triglyceride (IHTG) content in insulin resistant subjects with MASLD and T2D. We observed a significant decrease in IHTG after 24 weeks of treatment (by ∼50%, p < 0.001 versus placebo) that was associated with a major improvement in hepatic and peripheral (Rd) insulin sensitivity, restoration of adipose tissue function with more than two-fold increase in plasma adiponectin concentration and improvement in cardiometabolic risk factors. This is the first in-depth study on how a pan-PPAR approach reverses steatosis and metabolic dysfunction in patients with T2D and MASLD. It has important clinical implications because it offers proof-of-concept that by targeting the key underlying metabolic defects in MASLD (i.e., insulin resistance, lipotoxicity and hyperglycemia) one can restore cardiometabolic health and offers a compelling rationale for treating with lanifibranor individuals with MASLD, either alone or in combination with weight loss and other treatment strategies.

GOV IDENTIFIER: NCT03459079.

PMID:39824443 | DOI:10.1016/j.jhep.2024.12.045

NAR Cancer. 2025 Jan 15;7(1):zcae047. doi: 10.1093/narcan/zcae047. eCollection 2025 Mar.

ABSTRACT

Cancer is a complex disease with heterogeneous mutational and gene expression patterns. Subgroups of patients who share a phenotype might share a specific genetic architecture including protein-protein interactions (PPIs). We developed the Atlas of Protein-Protein Interactions in Cancer (APPIC), an interactive webtool that provides PPI subnetworks of 10 cancer types and their subtypes shared by cohorts of patients. To achieve this, we analyzed publicly available RNA sequencing data from patients and identified PPIs specific to 26 distinct cancer subtypes. APPIC compiles biological and clinical information from various databases, including the Human Protein Atlas, Hugo Gene Nomenclature Committee, g:Profiler, cBioPortal and Clue.io. The user-friendly interface allows for both 2D and 3D PPI network visualizations, enhancing the usability and interpretability of complex data. For advanced users seeking greater customization, APPIC conveniently provides all output files for further analysis and visualization on other platforms or tools. By offering comprehensive insights into PPIs and their role in cancer, APPIC aims to support the discovery of tumor subtype-specific novel targeted therapeutics and drug repurposing. APPIC is freely available at https://appic.brown.edu.

PMID:39822275 | PMC:PMC11734624 | DOI:10.1093/narcan/zcae047

Naunyn Schmiedebergs Arch Pharmacol. 2025 Jan 16. doi: 10.1007/s00210-024-03753-w. Online ahead of print.

ABSTRACT

The selective estrogen receptor modulator (SERM) raloxifene hydrochloride (RLH) is used extensively in the management and prevention of breast cancer and osteoporosis. Recent clinical studies show the repurposing of RLH in various diseases based on its structure and some clinical trials studies. Optimizing the clinical effectiveness of this important drug requires a thorough review of the formulation techniques, patent environment, and analytical procedures. The purpose of this study is to give a thorough understanding of dug repurposing with the most recent formulation strategies, patents, and analytical methods related to RLH. Highlighting recent developments, pointing out current issues, and suggesting future lines of inquiry and development are the objectives. A thorough literature analysis was carried out with an emphasis on repurposing of RLH for various diseases and analytical techniques employed in the measurement and quality control of RLH. These techniques included spectroscopic, chromatographic, and electrochemical approaches. Key advancements and trends were found by analyzing patent databases. The evaluation also looked into formulation techniques intended to improve the medicine's therapeutic efficacy and bioavailability, notably cutting-edge drug delivery methods. For the study of RLH, the review identifies several sophisticated analytical techniques that provide increased accuracy and robustness. Significant innovation has been revealed by the patent landscape, particularly in formulations targeted at enhancing solubility and bioavailability. Notable formulation techniques that overcome the drawbacks of conventional techniques include transdermal patches, nanoparticulate systems, and various drug delivery techniques.

PMID:39820645 | DOI:10.1007/s00210-024-03753-w

Curr Pharm Biotechnol. 2025 Jan 15. doi: 10.2174/0113892010335576241202061139. Online ahead of print.

ABSTRACT

BACKGROUND: Dilated Cardiomyopathy (DCM) is a debilitating cardiovascular disorder that challenges current therapeutic strategies. The exploration of novel drug repositioning opportunities through gene expression analysis offers a promising avenue for discovering effective treatments.

OBJECTIVE: This study aims to identify potential drug repositioning opportunities and lead compounds for DCM treatment by optimizing gene expression characteristics using published data.

METHODS: Our approach involved analyzing DCM expression profiles from the Gene Expression Omnibus database and identifying differentially expressed genes with GEO2R. A protein interaction network was constructed using the STRING database and visualized with Cytoscape. Enrichment analyses were conducted on these genes through the Omicshare platform, followed by the identification of candidate compounds via the Connectivity Map (CMAP) and validation through molecular docking. The Coremine Medical database was utilized to predict potential herbal medicines.

RESULTS: We identified 29 differentially expressed genes, highlighting MYH6, NPPA, and NPPB as central to DCM pathology. Enrichment analyses indicated significant impacts on biological processes, such as organ morphogenesis and inflammatory responses. The AGE-RAGE signaling pathway was notably affected. From over 6,100 compounds analyzed, tenoxicam emerged as a promising candidate, with Radix Salviae Miltiorrhizae (Danshen) being suggested as a potential herbal treatment.

CONCLUSION: This study underscores the utility of bioinformatics in uncovering new therapeutic candidates for DCM, offering a foundational step towards novel drug development.

PMID:39819398 | DOI:10.2174/0113892010335576241202061139

JCO Glob Oncol. 2025 Jan;11:e2400239. doi: 10.1200/GO.24.00239. Epub 2025 Jan 16.

ABSTRACT

PURPOSE: The availability of drugs and national public policies for patients with rare cancers, including sarcomas, varies in different parts of the world.

METHODS: In this manuscript, we have conducted a comprehensive analysis to evaluate rare cancer policies in Latin American countries' national policy documents. Additionally, we have reviewed the approvals for sarcoma drugs in selected Latin American countries and compared them with US Food and Drug Administration (FDA) and European Medicines Agency (EMA) approvals.

RESULTS: The documents reviewed showed a lack of explicit focus on rare cancers, with no mention in 70% of the countries analyzed. Drug approval data reveal that in the last 15 years, the FDA and EMA have approved 19 and 13 drugs for sarcoma, whereas their Latin American counterparts, namely ANVISA, ANMAT, and COFEPRIS, approved six, eight, and seven drugs, respectively.

CONCLUSION: Our data suggest that improving rare cancer and sarcoma care in Latin America requires enhanced collaboration for better rare cancer policies.

PMID:39819122 | DOI:10.1200/GO.24.00239

Genet Med Open. 2024 Mar 20;2:101840. doi: 10.1016/j.gimo.2024.101840. eCollection 2024.

ABSTRACT

The number of human disease genes has dramatically increased over the past decade, largely fueled by ongoing advances in sequencing technologies. In parallel, the number of available clinical genetic tests has also increased, including the utilization of exome sequencing for undiagnosed diseases. Although most clinical sequencing tests have been centered on enrichment-based multigene panels and exome sequencing, the continued improvements in performance and throughput of genome sequencing suggest that this technology is emerging as a potential platform for routine clinical genetic testing. A notable advantage is a single workflow with the opportunity to reflexively interrogate content as clinically indicated; however, challenges with implementing routine clinical genome sequencing still remain. This review is centered on evaluating the applications of genome sequencing as a single platform for clinical constitutional genetic testing, including its potential utility for diagnostic testing, carrier screening, cytogenomic molecular karyotyping, prenatal testing, mitochondrial genome interrogation, and pharmacogenomic and polygenic risk score testing.

PMID:39822265 | PMC:PMC11736070 | DOI:10.1016/j.gimo.2024.101840

Clin Transl Sci. 2025 Jan;18(1):e70131. doi: 10.1111/cts.70131.

ABSTRACT

In neurovascular settings, including treatment and prevention of ischemic stroke and prevention of thromboembolic complications after percutaneous neurointerventional procedures, dual antiplatelet therapy with a P2Y12 inhibitor and aspirin is the standard of care. Clopidogrel remains the most commonly prescribed P2Y12 inhibitor for neurovascular indications. However, patients carrying CYP2C19 no-function alleles have diminished capacity for inhibition of platelet reactivity due to reduced formation of clopidogrel's active metabolite. In patients with cardiovascular disease undergoing a percutaneous coronary intervention, CYP2C19 no-function allele carriers treated with clopidogrel experience a higher risk of major adverse cardiovascular outcomes, and multiple large prospective outcomes studies have shown an improvement in clinical outcomes when antiplatelet therapy selection was guided by CYP2C19 genotype. Similarly, accumulating evidence has associated CYP2C19 no-function alleles with poor clinical outcomes in clopidogrel-treated patients in neurovascular settings. However, the utility of implementing a genotype-guided antiplatelet therapy selection strategy in the setting of neurovascular disease and the clinical outcomes evidence in neurointerventional procedures remains unclear. In this review, we will (1) summarize existing evidence and guideline recommendations related to CYP2C19 genotype-guided antiplatelet therapy in the setting of neurovascular disease, (2) evaluate and synthesize the existing evidence on the relationship of clinical outcomes to CYP2C19 genotype and clopidogrel treatment in patients undergoing a percutaneous neurointerventional procedure, and (3) identify knowledge gaps and discuss future research directions.

PMID:39822142 | DOI:10.1111/cts.70131

PLoS One. 2025 Jan 17;20(1):e0313051. doi: 10.1371/journal.pone.0313051. eCollection 2025.

ABSTRACT

OBJECTIVE: Managing blood glucose levels is challenging for elite athletes with type 1 diabetes (T1D) as competition can cause unpredictable fluctuations. While fear of hypoglycemia during physical activity is well documented, research on hyperglycemia-related anxiety (HRA) is limited. HRA refers to the heightened fear that hyperglycemia-related symptoms will impair functioning. This study investigates current strategies employed to mitigate HRA during competition and the development of alternative approaches.

RESEARCH DESIGN AND METHODS: Elite athletes with TID, aged >14 who self-reported HRA during competition were recruited. Elite athletes were defined as individuals exercising >10 hours per week whose athletic performance has achieved the highest competition level. 60 to 90-minute virtual semi-structured interviews were analyzed using an Interpretative Phenomenological Analysis.

RESULTS: Ten elite athletes with T1D (average age 25 ± 3 years; T1D duration 12 ± 8 years; number of competitions per year 27 ± 19; training time per week 12 ± 6 hours) reported the strategies they currently use to mitigate HRA. These strategies include managing insulin and nutrition intake, embracing social support networks, using technology, practicing relaxation techniques, establishing routines, performing pre-competition aerobic exercise, and maintaining adequate sleep hygiene. Several additional approaches that could be implemented were identified including establishing targeted support networks, developing peer-reviewed resources on HRA, ensuring support teams have sufficient tools, and improving existing technology.

CONCLUSIONS: Elite athletes with T1D use physiological and psychological strategies to mitigate HRA during competition. This finding highlights the need for increased support and education for these athletes, and advancements in technology. A multidisciplinary approach involving healthcare professionals, athletic staff, and peer mentors could help integrate personalized anxiety management and diabetes care strategies into training regimens, enhancing both mental resilience and performance outcomes for athletes with T1D.

PMID:39823464 | DOI:10.1371/journal.pone.0313051

Cardiovasc Intervent Radiol. 2025 Jan 16. doi: 10.1007/s00270-024-03918-3. Online ahead of print.

ABSTRACT

Pediatric pain management presents unique challenges due to the intrinsic characteristics of children such as their developmental stages, communication barriers, and varying pain perceptions. Life-limiting conditions affecting children are a growing medical concern, requiring a comprehensive, multidisciplinary approach to improve quality of life or ensure a dignified end of life. Interventional radiology (IR) plays a critical role in this strategy, similar to its role in adult care. Not only life-limiting conditions pose a challenge in pediatric chronic pain management, but also other benign chronic diseases (e.g., cystic fibrosis, muscular dystrophy, neurodegenerative disorders, metabolic disorders). This review focuses on specific IR strategies for pediatric pain management, including ablation, embolization/chemoembolization, and nerve blocks. It emphasizes the importance of tailored approaches for pediatric patients, considering genetic disorders and oncological diseases, which may require a diverse range of IR treatments. The aim is to provide a summary of these interventional techniques and highlight the unique considerations necessary for effective pediatric pain management.

PMID:39821652 | DOI:10.1007/s00270-024-03918-3

Bioethics. 2025 Jan 17. doi: 10.1111/bioe.13385. Online ahead of print.

ABSTRACT

Writers have debated whether germline genome-editing is person-affecting or identity-affecting. The difference is thought to be ethically relevant to whether we should choose genome-editing or choose preimplantation genetic diagnosis and embryo selection, when seeking to prevent or produce bad conditions (e.g., cystic fibrosis, or deafness) in the individuals who will grow from the embryo edited or selected. We consider the very recent views of three prominent bioethicists and philosophers who have grappled with this issue. We claim that both sides are right, but that the sense in which genome-editing is person-affecting is less important, morally, when the aim is to have healthy children. Since this is the predominant objective of engaging in embryo selection and genome-editing, and since there are certain risks, at least for now, with genome-editing, it remains better, morally, to engage in embryo selection than genome-editing.

PMID:39821416 | DOI:10.1111/bioe.13385

Comput Med Imaging Graph. 2025 Jan 8;120:102492. doi: 10.1016/j.compmedimag.2025.102492. Online ahead of print.

ABSTRACT

In clinical optical molecular imaging, the need for real-time high frame rates and low excitation doses to ensure patient safety inherently increases susceptibility to detection noise. Faced with the challenge of image degradation caused by severe noise, image denoising is essential for mitigating the trade-off between acquisition cost and image quality. However, prevailing deep learning methods exhibit uncontrollable and suboptimal performance with limited interpretability, primarily due to neglecting underlying physical model and frequency information. In this work, we introduce an end-to-end model-driven Deep Equilibrium Unfolding Mamba (DEQ-UMamba) that integrates proximal gradient descent technique and learnt spatial-frequency characteristics to decouple complex noise structures into statistical distributions, enabling effective noise estimation and suppression in fluorescent images. Moreover, to address the computational limitations of unfolding networks, DEQ-UMamba trains an implicit mapping by directly differentiating the equilibrium point of the convergent solution, thereby ensuring stability and avoiding non-convergent behavior. With each network module aligned to a corresponding operation in the iterative optimization process, the proposed method achieves clear structural interpretability and strong performance. Comprehensive experiments conducted on both clinical and in vivo datasets demonstrate that DEQ-UMamba outperforms current state-of-the-art alternatives while utilizing fewer parameters, facilitating the advancement of cost-effective and high-quality clinical molecular imaging.

PMID:39823663 | DOI:10.1016/j.compmedimag.2025.102492

J Med Internet Res. 2025 Jan 17;27:e65434. doi: 10.2196/65434.

ABSTRACT

BACKGROUND: Studying the impact of COVID-19 on mental health is both compelling and imperative for the health care system's preparedness development. Discovering how pandemic conditions and governmental strategies and measures have impacted mental health is a challenging task. Mental health issues, such as depression and suicidal tendency, are traditionally explored through psychological battery tests and clinical procedures. To address the stigma associated with mental illness, social media is used to examine language patterns in posts related to suicide. This strategy enhances the comprehension and interpretation of suicidal ideation. Despite easy expression via social media, suicidal thoughts remain sensitive and complex to comprehend and detect. Suicidal ideation captures the new suicidal statements used during the COVID-19 pandemic that represents a different context of expressions.

OBJECTIVE: In this study, our aim was to detect suicidal ideation by mining textual content extracted from social media by leveraging state-of-the-art natural language processing (NLP) techniques.

METHODS: The work was divided into 2 major phases, one to classify suicidal ideation posts and the other to extract factors that cause suicidal ideation. We proposed a hybrid deep learning-based neural network approach (Bidirectional Encoder Representations from Transformers [BERT]+convolutional neural network [CNN]+long short-term memory [LSTM]) to classify suicidal and nonsuicidal posts. Two state-of-the-art deep learning approaches (CNN and LSTM) were combined based on features (terms) selected from term frequency-inverse document frequency (TF-IDF), Word2vec, and BERT. Explainable artificial intelligence (XAI) was used to extract key factors that contribute to suicidal ideation in order to provide a reliable and sustainable solution.

RESULTS: Of 348,110 records, 3154 (0.9%) were selected, resulting in 1338 (42.4%) suicidal and 1816 (57.6%) nonsuicidal instances. The CNN+LSTM+BERT model achieved superior performance, with a precision of 94%, a recall of 95%, an F1-score of 94%, and an accuracy of 93.65%.

CONCLUSIONS: Considering the dynamic nature of suicidal behavior posts, we proposed a fused architecture that captures both localized and generalized contextual information that is important for understanding the language patterns and predict the evolution of suicidal ideation over time. According to Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) XAI algorithms, there was a drift in the features during and before COVID-19. Due to the COVID-19 pandemic, new features have been added, which leads to suicidal tendencies. In the future, strategies need to be developed to combat this deadly disease.

PMID:39823631 | DOI:10.2196/65434

J Neurosurg. 2025 Jan 17:1-9. doi: 10.3171/2024.8.JNS24415. Online ahead of print.

ABSTRACT

OBJECTIVE: The extent of resection (EOR) and postoperative residual tumor (RT) volume are prognostic factors in glioblastoma. Calculations of EOR and RT rely on accurate tumor segmentations. Raidionics is an open-access software that enables automatic segmentation of preoperative and early postoperative glioblastoma using pretrained deep learning models. The aim of this study was to compare the prognostic value of manually versus automatically assessed volumetric measurements in glioblastoma patients.

METHODS: Adult patients who underwent resection of histopathologically confirmed glioblastoma were included from 12 different hospitals in Europe and North America. Patient characteristics and survival data were collected as part of local tumor registries or were retrieved from patient medical records. The prognostic value of manually and automatically assessed EOR and RT volume was compared using Cox regression models.

RESULTS: Both manually and automatically assessed RT volumes were a negative prognostic factor for overall survival (manual vs automatic: HR 1.051, 95% CI 1.034-1.067 [p < 0.001] vs HR 1.019, 95% CI 1.007-1.030 [p = 0.001]). Both manual and automatic EOR models showed that patients with gross-total resection have significantly longer overall survival compared with those with subtotal resection (manual vs automatic: HR 1.580, 95% CI 1.291-1.932 [p < 0.001] vs HR 1.395, 95% CI 1.160-1.679 [p < 0.001]), but no significant prognostic difference of gross-total compared with near-total (90%-99%) resection was found. According to the Akaike information criterion and the Bayesian information criterion, all multivariable Cox regression models showed similar goodness-of-fit.

CONCLUSIONS: Automatically and manually measured EOR and RT volumes have comparable prognostic properties. Automatic segmentation with Raidionics can be used in future studies in patients with glioblastoma.

PMID:39823581 | DOI:10.3171/2024.8.JNS24415

J Chem Inf Model. 2025 Jan 17. doi: 10.1021/acs.jcim.4c01591. Online ahead of print.

ABSTRACT

In recent decades, covalent inhibitors have emerged as a promising strategy for therapeutic development, leveraging their unique mechanism of forming covalent bonds with target proteins. This approach offers advantages such as prolonged drug efficacy, precise targeting, and the potential to overcome resistance. However, the inherent reactivity of covalent compounds presents significant challenges, leading to off-target effects and toxicities. Accurately predicting and modulating this reactivity have become a critical focus in the field. In this work, we compiled a data set of 419 cysteine-targeted covalent compounds and their reactivity through an extensive literature review. Employing machine learning, deep learning, and quantum mechanical calculations, we evaluated the intrinsic reactivity of the covalent compounds. Our FP-Stack models demonstrated robust Pearson and Spearman correlations of approximately 0.80 and 0.75 on the test set, respectively. This empowers rapid and accurate reactivity predictions, significantly reducing computational costs and streamlining structural handling and experimental procedures. Experimental validation on acrylamide compounds underscored the predictive efficacy of our model. This study presents an efficient computational tool for the reactivity prediction of covalent compounds and is expected to offer valuable insights for guiding covalent drug discovery and development.

PMID:39823568 | DOI:10.1021/acs.jcim.4c01591

Invest Radiol. 2025 Jan 20. doi: 10.1097/RLI.0000000000001148. Online ahead of print.

ABSTRACT

OBJECTIVES: Pancreatic diffusion-weighted imaging (DWI) has numerous clinical applications, but conventional single-shot methods suffer from off resonance-induced artifacts like distortion and blurring while cardiovascular motion-induced phase inconsistency leads to quantitative errors and signal loss, limiting its utility. Multishot DWI (msDWI) offers reduced image distortion and blurring relative to single-shot methods but increases sensitivity to motion artifacts. Motion-compensated diffusion-encoding gradients (MCGs) reduce motion artifacts and could improve motion robustness of msDWI but come with the cost of extended echo time, further reducing signal. Thus, a method that combines msDWI with MCGs while minimizing the echo time penalty and maximizing signal would improve pancreatic DWI. In this work, we combine MCGs generated via convex-optimized diffusion encoding (CODE), which reduces the echo time penalty of motion compensation, with deep learning (DL)-based denoising to address residual signal loss. We hypothesize this method will qualitatively and quantitatively improve msDWI of the pancreas.

MATERIALS AND METHODS: This prospective institutional review board-approved study included 22 patients who underwent abdominal MR examinations from August 22, 2022 and May 17, 2023 on 3.0 T scanners. Following informed consent, 2-shot spin-echo echo-planar DWI (b = 0, 800 s/mm2) without (M0) and with (M1) CODE-generated first-order gradient moment nulling was added to their clinical examinations. DL-based denoising was applied to the M1 images (M1 + DL) off-line. ADC maps were reconstructed for all 3 methods. Blinded pair-wise comparisons of b = 800 s/mm2 images were done by 3 subspecialist radiologists. Five metrics were compared: pancreatic boundary delineation, motion artifacts, signal homogeneity, perceived noise, and diagnostic preference. Regions of interest of the pancreatic head, body, and tail were drawn, and mean ADC values were computed. Repeated analysis of variance and post hoc pairwise t test with Bonferroni correction were used for comparing mean ADC values. Bland-Altman analysis compared mean ADC values. Reader preferences were tabulated and compared using Wilcoxon signed rank test with Bonferroni correction and Fleiss κ.

RESULTS: M1 was significantly preferred over M0 for perceived motion artifacts and signal homogeneity (P < 0.001). M0 was significantly preferred over M1 for perceived noise (P < 0.001), but DL-based denoising (M1 + DL) reversed this trend and was significantly favored over M0 (P < 0.001). ADC measurements from M0 varied between different regions of the pancreas (P = 0.001), whereas motion correction with M1 and M1 + DL resulted in homogeneous ADC values (P = 0.24), with values similar to those reported for ssDWI with motion correction. ADC values from M0 were significantly higher than M1 in the head (bias 16.6%; P < 0.0001), body (bias 11.0%; P < 0.0001), and tail (bias 8.6%; P = 0.001). A small but significant bias (2.6%) existed between ADC values from M1 and M1 + DL.

CONCLUSIONS: CODE-generated motion compensating gradients improves multishot pancreatic DWI as interpreted by expert readers and eliminated ADC variation throughout the pancreas. DL-based denoising mitigated signal losses from motion compensation while maintaining ADC consistency. Integrating both techniques could improve the accuracy and reliability of multishot pancreatic DWI.

PMID:39823511 | DOI:10.1097/RLI.0000000000001148

PLoS One. 2025 Jan 17;20(1):e0314535. doi: 10.1371/journal.pone.0314535. eCollection 2025.

ABSTRACT

Bacterial Leaf Blight (BLB) usually attacks rice in the flowering stage and can cause yield losses of up to 50% in severely infected fields. The resulting yield losses severely impact farmers, necessitating compensation from the regulatory authorities. This study introduces a new pipeline specifically designed for detecting BLB in rice fields using unmanned aerial vehicle (UAV) imagery. Employing the U-Net architecture with a ResNet-101 backbone, we explore three band combinations-multispectral, multispectral+NDVI, and multispectral+NDRE-to achieve superior segmentation accuracy. Due to the lack of suitable UAV-based datasets for rice disease, we generate our own dataset through disease inoculation techniques in experimental paddy fields. The dataset is increased using data augmentation and patch extraction methods to improve training robustness. Our findings demonstrate that the U-Net model incorporating ResNet-101 backbone trained with multispectral+NDVI data significantly outperforms other band combinations, achieving high accuracy metrics, including mean Intersection over Union (mIoU) of up to 97.20%, mean accuracy of up to 99.42%, mean F1-score of up to 98.56%, mean Precision of 97.97%, and mean Recall of 99.16%. Additionally, this approach efficiently segments healthy rice from other classes, minimizing misclassification and improving disease severity assessment. Therefore, the experiment concludes that the accurate mapping of the disease extent and severity level in the field is reliable to accurately allocating the compensation. The developed methodology has the potential for broader application in diagnosing other rice diseases, such as Blast, Bacterial Panicle Blight, and Sheath Blight, and could significantly enhance agricultural management through accurate damage mapping and yield loss estimation.

PMID:39823436 | DOI:10.1371/journal.pone.0314535

PLoS One. 2025 Jan 17;20(1):e0316919. doi: 10.1371/journal.pone.0316919. eCollection 2025.

ABSTRACT

PURPOSE: In this study, we investigated the performance of deep learning (DL) models to differentiate between normal and glaucomatous visual fields (VFs) and classify glaucoma from early to the advanced stage to observe if the DL model can stage glaucoma as Mills criteria using only the pattern deviation (PD) plots. The DL model results were compared with a machine learning (ML) classifier trained on conventional VF parameters.

METHODS: A total of 265 PD plots and 265 numerical datasets of Humphrey 24-2 VF images were collected from 119 normal and 146 glaucomatous eyes to train the DL models to classify the images into four groups: normal, early glaucoma, moderate glaucoma, and advanced glaucoma. The two popular pre-trained DL models: ResNet18 and VGG16, were used to train the PD images using five-fold cross-validation (CV) and observed the performance using balanced, pre-augmented data (n = 476 images), imbalanced original data (n = 265) and feature extraction. The trained images were further investigated using the Grad-CAM visualization technique. Moreover, four ML models were trained from the global indices: mean deviation (MD), pattern standard deviation (PSD) and visual field index (VFI), using five-fold CV to compare the classification performance with the DL model's result.

RESULTS: The DL model, ResNet18 trained from balanced, pre-augmented PD images, achieved high accuracy in classifying the groups with an overall F1-score: 96.8%, precision: 97.0%, recall: 96.9%, and specificity: 99.0%. The highest F1 score was 87.8% for ResNet18 with the original dataset and 88.7% for VGG16 with feature extraction. The DL models successfully localized the affected VF loss in PD plots. Among the ML models, the random forest (RF) classifier performed best with an F1 score of 96%.

CONCLUSION: The DL model trained from PD plots was promising in differentiating normal and glaucomatous groups and performed similarly to conventional global indices. Hence, the evidence-based DL model trained from PD images demonstrated that the DL model could stage glaucoma using only PD plots like Mills criteria. This automated DL model will assist clinicians in precision glaucoma detection and progression management during extensive glaucoma screening.

PMID:39823435 | DOI:10.1371/journal.pone.0316919

PLoS One. 2025 Jan 17;20(1):e0313930. doi: 10.1371/journal.pone.0313930. eCollection 2025.

ABSTRACT

In the current cybersecurity landscape, Distributed Denial of Service (DDoS) attacks have become a prevalent form of cybercrime. These attacks are relatively easy to execute but can cause significant disruption and damage to targeted systems and networks. Generally, attackers perform it to make reprisal but sometimes this issue can be authentic also. In this paper basically conversed about some deep learning models that will hand over a descent accuracy in prediction of DDoS attacks. This study evaluates various models, including Vanilla LSTM, Stacked LSTM, Deep Neural Networks (DNN), and other machine learning models such as Random Forest, AdaBoost, and Gaussian Naive Bayes to determine the DDoS attack along with comparing these approaches as well as perceiving which one is about to give elegant outcomes in prediction. The rationale for selecting Long Short-Term Memory (LSTM) networks for evaluation in our study is based on their proven effectiveness in modeling sequential and time-series data, which are inherent characteristics of network traffic and cybersecurity data. Here, a benchmark dataset named CICDDoS2019 is used that contains 88 features from which a handful (22) convenient features are extracted further deep learning models are applied. The result that is acquired here is significantly better than available techniques those are attainable in this context by using Machine Learning models, data mining techniques and some IOT based approaches. It's not possible to completely avoid your server from these threats but by applying discussed techniques in the present juncture, these attacks can be prevented to an extent and it will also help to server to fulfil the genuine requests instead of sticking in the accomplishing the requests created by the unauthentic user.

PMID:39823417 | DOI:10.1371/journal.pone.0313930

J Chem Inf Model. 2025 Jan 17. doi: 10.1021/acs.jcim.4c01014. Online ahead of print.

ABSTRACT

Molecular Docking is a critical task in structure-based virtual screening. Recent advancements have showcased the efficacy of diffusion-based generative models for blind docking tasks. However, these models do not inherently estimate protein-ligand binding strength thus cannot be directly applied to virtual screening tasks. Protein-ligand scoring functions serve as fast and approximate computational methods to evaluate the binding strength between the protein and ligand. In this work, we introduce normalized mixture density network (NMDN) score, a deep learning (DL)-based scoring function learning the probability density distribution of distances between protein residues and ligand atoms. The NMDN score addresses limitations observed in existing DL scoring functions and performs robustly in both pose selection and virtual screening tasks. Additionally, we incorporate an interaction module to predict the experimental binding affinity score to fully utilize the learned protein and ligand representations. Finally, we present an end-to-end blind docking and virtual screening protocol named DiffDock-NMDN. For each protein-ligand pair, we employ DiffDock to sample multiple poses, followed by utilizing the NMDN score to select the optimal binding pose, and estimating the binding affinity using scoring functions. Our protocol achieves an average enrichment factor of 4.96 on the LIT-PCBA data set, proving effective in real-world drug discovery scenarios where binder information is limited. This work not only presents a robust DL-based scoring function with superior pose selection and virtual screening capabilities but also offers a blind docking protocol and benchmarks to guide future scoring function development.

PMID:39823352 | DOI:10.1021/acs.jcim.4c01014