J Inflamm Res. 2025 Jan 16;18:637-652. doi: 10.2147/JIR.S503118. eCollection 2025.

ABSTRACT

PURPOSE: Immunometabolism is pivotal in rheumatoid arthritis (RA) pathogenesis, yet the intricacies of its pathological regulatory mechanisms remain poorly understood. This study explores the complex immunometabolic landscape of RA to identify potential therapeutic targets.

PATIENTS AND METHODS: We integrated genome-wide association study (GWAS) data involving 1,400 plasma metabolites, 731 immune cell traits, and RA outcomes from over 58,000 participants. Mendelian randomization (MR) and mediation analyses were applied to evaluate causal relationships among plasma metabolites, immune cells, and RA. We further analyzed single-cell and bulk transcriptomes to investigate differential gene expression, immune cell interactions, and relevant biological processes. Machine learning models identified hub genes, which were validated via quantitative real-time PCR (qRT-PCR). Then, potential small-molecule drugs were screened using the Connectivity Map (CMAP) and molecular docking. Finally, a phenome-wide association study (PheWAS) was conducted to evaluate potential side effects of drugs targeting the hub genes.

RESULTS: Causalities were found between six plasma metabolites, five immune cells and RA in genetically determined levels. Notably, DC mediated 18% of the protective effect of PE on RA. Autophagy-related scores were elevated in both RA and DC subsets in PE-associated biological processes. Through observation in the functional differences in cellular interactions between the identified clusters, DCs with high autophagy scores may process such as necroptosis and the activation of the Jak-STAT signaling pathway in contributing the pathogenesis of RA. Explainable machine learning, PPI network analysis, and qPCR jointly identified four hub genes (PFN1, SRP14, S100A11, and SAP18). CMAP, molecular docking, and PheWAS analysis further highlighted vismodegib as a promising therapeutic candidate.

CONCLUSION: This study clarifies the key immunometabolic mechanisms in RA, pinpointing promising paths for better prevention, diagnosis, and treatment.

PMID:39835297 | PMC:PMC11745140 | DOI:10.2147/JIR.S503118

Int J Nanomedicine. 2025 Jan 16;20:605-624. doi: 10.2147/IJN.S500487. eCollection 2025.

ABSTRACT

INTRODUCTION: Androgenetic alopecia (AGA) is a multifactorial and age-related dermatological disease that affects both males and females, usually at older ages. Traditional hair repair drugs exemplified by minoxidil have limitations such as skin irritation and hypertrichosis. Thus, attention has been shifted to the use of repurposing drugs. Metformin is an anti-diabetic drug, that can promote hair follicle regeneration via upregulation of the hair-inductive capability. Hence, the current study aims to fabricate a safe and effective nanoemulsion to improve metformin efficacy in targeting AGA.

METHODS: Rosemary oil was selected as the oily phase due to its ability to increase blood flow and hair growth. Rosemary-based nanoemulsions were statistically optimized by Box-Behnken experimental design, loaded with metformin, and incorporated into a hydrogel to form a nanoemulgel. Metformin-loaded nanoemulsions were assessed for their diametric size, uniformity, zeta potential, and metformin characteristics within the formulated nanosystem. The nanoemulgel was then evaluated in terms of its pH, percentage drug content, and in-vitro release performance. In-vivo study assessed the nanoemulgel's ability to augment hair growth in rats.

RESULTS: The experimental design displayed that using 50%w/w, 20%w/w, and 10%w/w of Cremophor®, Labrafil®, and deionized water, respectively, resulted in nanoemulsion formulation with the smallest globule size (125.01 ± 0.534 nm), unimodal size distribution (PDI=0.103), negative surface charge (-19.9 ± 2.01 mV) with a spherical morphological structure. Rosemary-based nanoemulgel displayed acceptable physicochemical characterizations namely; a neutral pH value of 6.7±0.15, high drug content (92.9± 2.3%), and controlled metformin in-vitro release. Besides, the formulated nanoemulgel significantly increased the number of hair follicles in the animal model compared with other controls and tested groups.

CONCLUSION: The designed nanoemulgel is a promising approach for treating androgenic alopecia.

PMID:39835177 | PMC:PMC11745075 | DOI:10.2147/IJN.S500487

Front Pharmacol. 2025 Jan 6;15:1503490. doi: 10.3389/fphar.2024.1503490. eCollection 2024.

ABSTRACT

Hepatocellular carcinoma (HCC) is a major medical challenge due to its high incidence and poor prognosis. 5-Fluorouracil (5-FU), although extensively studied in the treatment of HCC and other solid tumors, has limited application as a first-line therapy for HCC due to its resistance and significant inter-patient variability. To address these issues, researchers have explored drug repurposing. One of our key findings in this endeavour was the potent anti-HCC effect of the natural product Salidroside (Sal) when co-administered with 5-FU. Sal was found to inhibit mitosis and promote cellular senescence in HCC cells via a mechanism distinct from 5-FU, specifically by inducing excessive mitophagy that led to cellular mitochondrial dysfunction. Importantly, YIPF5 was confirmed as a potential molecular target of Sal. This natural product modulated YIPF5-induced mitophagy and influenced both mitosis and senescence in HCC cells. The combination of Sal and 5-FU demonstrated significant therapeutic effects in a mouse HCC model. In conclusion, our study was not only in line with the innovative strategy of drug repurposing, but also important for drug design and natural product screening targeting the relevant pathways.

PMID:39834805 | PMC:PMC11743563 | DOI:10.3389/fphar.2024.1503490

Front Nutr. 2025 Jan 6;11:1503389. doi: 10.3389/fnut.2024.1503389. eCollection 2024.

ABSTRACT

INTRODUCTION: Contemporary data and knowledge management and exploration are challenging due to regular releases, updates, and different types and formats. In the food and nutrition domain, solutions for integrating such data and knowledge with respect to the FAIR (Findability, Accessibility, Interoperability, and Reusability) principles are still lacking.

METHODS: To address this issue, we have developed a data and knowledge management system called NutriBase, which supports the compilation of a food composition database and its integration with evidence-based knowledge. This research is a novel contribution because it allows for the interconnection and complementation of food composition data with knowledge and takes what has been done in the past a step further by enabling the integration of knowledge. NutriBase focuses on two important challenges; data (semantic) harmonization by using the existing ontologies, and reducing missing data by semi-automatic data imputation made from conflating with existing databases.

RESULTS AND DISCUSSION: The developed web-based tool is highly modifiable and can be further customized to meet national or international requirements. It can help create and maintain the quality management system needed to assure data quality. Newly generated data and knowledge can continuously be added, as interoperability with other systems is enabled. The tool is intended for use by domain experts, food compilers, and researchers who can add and edit food-relevant data and knowledge. However, the tool is also accessible to food manufacturers, who can regularly update information about their products and thus give consumers access to current data. Moreover, the traceability of the data and knowledge provenance allows the compilation of a trustworthy management system. The system is designed to allow easy integration of data from different sources, which enables data borrowing and reduction of missing data. In this paper, the feasibility of NutriBase is demonstrated on Slovenian food-related data and knowledge, which is further linked with international resources. Outputs such as matched food components and food classifications have been integrated into semantic resources that are currently under development in various international projects.

PMID:39834464 | PMC:PMC11743969 | DOI:10.3389/fnut.2024.1503389

Front Endocrinol (Lausanne). 2025 Jan 6;15:1537014. doi: 10.3389/fendo.2024.1537014. eCollection 2024.

ABSTRACT

[This corrects the article DOI: 10.3389/fendo.2023.1184024.].

PMID:39835259 | PMC:PMC11744269 | DOI:10.3389/fendo.2024.1537014

Cureus. 2024 Dec 20;16(12):e76089. doi: 10.7759/cureus.76089. eCollection 2024 Dec.

ABSTRACT

Shock is a state of inadequate perfusion that affects vital organs. Cardiogenic shock (CS) predisposes patients to various arrhythmias. The adverse effect depends on intervention and pharmacogenomics. This narrative review sheds light on treatment strategies for arrhythmias caused by milrinone and dobutamine when managing CS. Dobutamine, through beta-1 agonism, and milrinone, by phosphodiesterase-3 inhibition, increase cardiac contractility by enhancing the availability of calcium to the myocardium. Dobutamine is also a beta-2 agonist, and milrinone is a phosphodiesterase-3 inhibitor; both result in peripheral vasodilation, leading to their use preferentially in patients with CS with normotensive blood pressure. To narrow down relevant literature, various electronic databases, including PubMed, Google Scholar, and Cochrane Library, were searched. The review revealed limited evidence favoring either milrinone or dobutamine as the preferred inotropic agent for managing CS, but it did reveal that though hospital stays using dobutamine were shorter, mortality from its induced arrhythmias led to an increase in all-cause mortality rates. Both proarrhythmic agents triggered ventricular and supraventricular tachyarrhythmias, some requiring cardioversion while others are non-sustained and managed medically or symptomatically. Though neither agent has a specific reversal agent, the effect of dobutamine was seen to be successfully aborted using intravenous ultrashort half-life beta-blockers (such as esmolol). The findings accentuated the critical need for a tailored approach to managing these iatrogenic arrhythmias, emphasizing clinical vigilance and individualized patient care.

PMID:39835019 | PMC:PMC11743927 | DOI:10.7759/cureus.76089

Front Immunol. 2025 Jan 6;15:1505752. doi: 10.3389/fimmu.2024.1505752. eCollection 2024.

ABSTRACT

BACKGROUND: Factors leading to severe COVID-19 remain partially known. New biomarkers predicting COVID-19 severity that are also causally involved in disease pathogenesis could improve patient management and contribute to the development of innovative therapies. Autophagy, a cytosolic structure degradation pathway is involved in the maintenance of cellular homeostasis, degradation of intracellular pathogens and generation of energy for immune responses. Acyl-CoA binding protein (ACBP) is a key regulator of autophagy in the context of diabetes, obesity and anorexia. The objective of our work was to assess whether circulating ACBP levels are associated with COVID-19 severity, using proteomics data from the plasma of 903 COVID-19 patients.

METHODS: Somalogic proteomic analysis was used to detect 5000 proteins in plasma samples collected between March 2020 and August 2021 from hospitalized participants in the province of Quebec, Canada. Plasma samples from 903 COVID-19 patients collected during their admission during acute phase of COVID-19 and 295 hospitalized controls were assessed leading to 1198 interpretable proteomic profiles. Levels of anti-SARS-CoV-2 IgG were measured by ELISA and a cell-binding assay.

RESULTS: The median age of the participants was 59 years, 46% were female, 65% had comorbidities. Plasma ACBP levels correlated with COVID-19 severity, in association with inflammation and anti-SARS-CoV-2 antibody levels, independently of sex or the presence of comorbidities. Samples collected during the second COVID-19 wave in Quebec had higher levels of plasma ACBP than during the first wave. Plasma ACBP levels were negatively correlated with biomarkers of T and NK cell responses interferon-γ, tumor necrosis factor-α and interleukin-21, independently of age, sex, and severity.

CONCLUSIONS: Circulating ACBP levels can be considered a biomarker of COVID-19 severity linked to inflammation. The contribution of extracellular ACBP to immunometabolic responses during viral infection should be further studied.

PMID:39835130 | PMC:PMC11743960 | DOI:10.3389/fimmu.2024.1505752

Cureus. 2024 Dec 19;16(12):e76002. doi: 10.7759/cureus.76002. eCollection 2024 Dec.

ABSTRACT

Aquagenic syringeal acrokeradermatoma (ASA) is a dermatological condition characterized by the transient appearance of edematous, white, translucent papules on the palms, typically triggered by water exposure. While ASA is most commonly associated with cystic fibrosis (CF) and predominantly affects young females, there has been a significant increase in ASA cases since the most recent update in 2015. The COVID-19 pandemic increased the number of patients diagnosed with ASA following exposure to the viral infection. The growing body of literature suggests a multifactorial etiology for ASA, with potential links to CF, medication use, and possibly COVID-19-related behavioral changes. Due to the recent increase in cases of ASA, an updated review seeks to quantify the existing literature that has been published on the prevalence of this condition. This review sought to find those newly diagnosed cases between the years 2014 and 2024. Through a literature review, we were able to find 57 cases of ASA since the last significant update to the total number of cases found in the literature. This review includes the prevalence of CF, a known etiology of ASA, as well as demographic information and known status of exposure to COVID-19.

PMID:39835050 | PMC:PMC11743320 | DOI:10.7759/cureus.76002

Respir Med Case Rep. 2024 Dec 27;53:102159. doi: 10.1016/j.rmcr.2024.102159. eCollection 2025.

ABSTRACT

INTRODUCTION: Acute fibrinous and organizing pneumonia (AFOP) is a severe form of acute lung injury which can occur after lung transplantation. Treatment is empiric, based on immunosuppressive regimens and the mortality rate is very high.

CASE PRESENTATION: We report the case of a young lung transplant (LT) recipient who developed AFOP following a respiratory viral infection while on suboptimal maintenance immunosuppression due to adherence issues. Diagnosis was confirmed by cryobiopsies showing intra-alveolar fibrin balls. Despite high dose systemic corticosteroids, the patient developed severe respiratory failure requiring mechanical ventilation. IV infliximab and tocilizumab were administered. The patient was extubated 11 days later and discharged to home 42 days after intubation with 1L/min O2. She developed severe pleuritic pain needing opioid treatment and died 4 months later.

CONCLUSION: While high-dose systemic corticosteroids remain the first line of treatment, the use of anti TNF-α has shown promising results in case reports. Furthermore, we propose prompt realization of a cytokine panel analysis in both blood and bronchoalveolar lavage to better guide the adjuvant administration of a targeted anti-inflammatory therapy.

PMID:39834689 | PMC:PMC11743898 | DOI:10.1016/j.rmcr.2024.102159

Cureus. 2025 Jan 19;17(1):e77681. doi: 10.7759/cureus.77681. eCollection 2025 Jan.

ABSTRACT

Bronchiectasis is a well-recognized chronic respiratory disease characterized by a productive cough and multi-microbial activation syndrome (MMAS) of various respiratory infections due to what can be the permanent dilatation of the bronchi. Bronchiectasis represents an ongoing challenge to conventional antibiotic treatment as the damaged bronchial environment remains conducive to ongoing opportunistic infections and microbial mutations, leading to multi-drug resistance. Standard treatment guidelines are designed to promptly identify and address the primary infection. Despite the strong focus on identification of the primary infection in each new episode, by combining clinical history, and high-resolution computed tomography (HRCT), a high proportion of patients remain classified as "idiopathic". Important underlying infections, such as Aspergillus and other mold infections, Pseudomonas aeruginosa, Mycobacterium, Mycoplasma, and various viruses, are frequently not identified for prolonged periods of time, and selected broad-spectrum antibiotics are often ineffective. The introduction of Induced Native Phage Therapy in 2021 and Induced Native Phage cocktails in 2024 provides a new treatment alternative that induces naturally occurring phages to eliminate specifically targeted acute and chronic mixed infections even in cases of multi-drug resistant infections as seen in chronic bronchiectasis. This article will present the successful long-term results in a case study demonstrating the speed, gentleness, and effectiveness of induced native phage cocktails in a 45-year-old male with life-long asthma resulting in multi-microbial activation syndrome in severe non-cystic fibrosis bronchiectasis for the last 20 years.

PMID:39834667 | PMC:PMC11744022 | DOI:10.7759/cureus.77681

Front Public Health. 2025 Jan 6;12:1442114. doi: 10.3389/fpubh.2024.1442114. eCollection 2024.

ABSTRACT

INTRODUCTION: Diabetic retinopathy grading plays a vital role in the diagnosis and treatment of patients. In practice, this task mainly relies on manual inspection using human visual system. However, the human visual system-based screening process is labor-intensive, time-consuming, and error-prone. Therefore, plenty of automated screening technique have been developed to address this task.

METHODS: Among these techniques, the deep learning models have demonstrated promising outcomes in various types of machine vision tasks. However, most of the medical image analysis-oriented deep learning approaches are built upon the convolutional operations, which might neglect the global dependencies between long-range pixels in the medical images. Therefore, the vision transformer models, which can unveil the associations between global pixels, have been gradually employed in medical image analysis. However, the quadratic computation complexity of attention mechanism has hindered the deployment of vision transformer in clinical practices. Bearing the analysis above in mind, this study introduces an integrated self-attention mechanism with both softmax and linear modules to guarantee efficiency and expressiveness, simultaneously. To be specific, a portion of query and key tokens, which are much less than the original query and key tokens, are adopted in the attention module by adding a set of proxy tokens. Note that the proxy tokens can fully utilize both the advantages of softmax and linear attention.

RESULTS: To evaluate the performance of the presented approach, the comparison experiments between state-of-the-art algorithms and the proposed approach are conducted. Experimental results demonstrate that the proposed approach achieves superior outcome over the state-of-the-art algorithms on the publicly available datasets.

DISCUSSION: Accordingly, the proposed approach can be taken as a potentially valuable instrument in clinical practices.

PMID:39835306 | PMC:PMC11743363 | DOI:10.3389/fpubh.2024.1442114

Front Med (Lausanne). 2025 Jan 6;11:1510792. doi: 10.3389/fmed.2024.1510792. eCollection 2024.

ABSTRACT

Sepsis remains a leading cause of morbidity and mortality worldwide due to its rapid progression and heterogeneous nature. This review explores the potential of Artificial Intelligence (AI) to transform sepsis management, from early detection to personalized treatment and real-time monitoring. AI, particularly through machine learning (ML) techniques such as random forest models and deep learning algorithms, has shown promise in analyzing electronic health record (EHR) data to identify patterns that enable early sepsis detection. For instance, random forest models have demonstrated high accuracy in predicting sepsis onset in intensive care unit (ICU) patients, while deep learning approaches have been applied to recognize complications such as sepsis-associated acute respiratory distress syndrome (ARDS). Personalized treatment plans developed through AI algorithms predict patient-specific responses to therapies, optimizing therapeutic efficacy and minimizing adverse effects. AI-driven continuous monitoring systems, including wearable devices, provide real-time predictions of sepsis-related complications, enabling timely interventions. Beyond these advancements, AI enhances diagnostic accuracy, predicts long-term outcomes, and supports dynamic risk assessment in clinical settings. However, ethical challenges, including data privacy concerns and algorithmic biases, must be addressed to ensure fair and effective implementation. The significance of this review lies in addressing the current limitations in sepsis management and highlighting how AI can overcome these hurdles. By leveraging AI, healthcare providers can significantly enhance diagnostic accuracy, optimize treatment protocols, and improve overall patient outcomes. Future research should focus on refining AI algorithms with diverse datasets, integrating emerging technologies, and fostering interdisciplinary collaboration to address these challenges and realize AI's transformative potential in sepsis care.

PMID:39835096 | PMC:PMC11743359 | DOI:10.3389/fmed.2024.1510792

Front Med (Lausanne). 2025 Jan 6;11:1478842. doi: 10.3389/fmed.2024.1478842. eCollection 2024.

ABSTRACT

BACKGROUND: The conventional treatment for locally advanced head and neck squamous cell carcinoma (LA-HNSCC) is surgery; however, the efficacy of definitive chemoradiotherapy (CRT) remains controversial.

OBJECTIVE: This study aimed to evaluate the ability of deep learning (DL) models to identify patients with LA-HNSCC who can achieve organ preservation through definitive CRT and provide individualized adjuvant treatment recommendations for patients who are better suited for surgery.

METHODS: Five models were developed for treatment recommendations. Their performance was assessed by comparing the difference in overall survival rates between patients whose actual treatments aligned with the model recommendations and those whose treatments did not. Inverse probability treatment weighting (IPTW) was employed to reduce bias. The effect of the characteristics on treatment plan selection was quantified through causal inference.

RESULTS: A total of 7,376 patients with LA-HNSCC were enrolled. Balanced Individual Treatment Effect for Survival data (BITES) demonstrated superior performance in both the CRT recommendation (IPTW-adjusted hazard ratio (HR): 0.84, 95% confidence interval (CI), 0.72-0.98) and the adjuvant therapy recommendation (IPTW-adjusted HR: 0.77, 95% CI, 0.61-0.85), outperforming other models and the National Comprehensive Cancer Network guidelines (IPTW-adjusted HR: 0.87, 95% CI, 0.73-0.96).

CONCLUSION: BITES can identify the most suitable treatment option for an individual patient from the three most common treatment options. DL models facilitate the establishment of a valid and reliable treatment recommendation system supported by quantitative evidence.

PMID:39835092 | PMC:PMC11744519 | DOI:10.3389/fmed.2024.1478842

Cureus. 2024 Dec 20;16(12):e76095. doi: 10.7759/cureus.76095. eCollection 2024 Dec.

ABSTRACT

Preeclampsia is one of the leading causes of maternal and perinatal morbidity and mortality. Early prediction is the need of the hour so that interventions like aspirin prophylaxis can be started. Nowadays, machine learning (ML) is increasingly being used to predict the disease and its prognosis. This review explores the methodologies, predictors, and performance of ML models for preeclampsia prediction, emphasizing their comparative advantages, challenges, and clinical applicability. We conducted a systematic search of databases including PubMed, Cochrane, and Scopus for studies published in the last 10 years using terms such as "preeclampsia", "risk factors", "machine learning", "artificial intelligence", and "deep learning". Words and phrases were selected using MeSH, a controlled vocabulary. Appropriate articles were selected using Boolean operators "OR" and "AND". The database search yielded 325 records. After removing duplicates and non-English articles, and completing a title and abstract search 55 research articles were assessed for eligibility of which 11 were included in this review. The risk of bias was found to be high in three of the studies and low in the rest. Clinicodemographic characteristics, laboratory reports, Doppler ultrasound, and some innovative ones like genotypic data and fundal images were predictors used to train ML models. More than ten different ML models were used in the 11 studies from diverse countries like the United States, the United Kingdom, China, and Korea. The area under the curve varied from 0.76 to 0.97. ML algorithms such as extreme gradient boosting (XGBoost), random forest, and neural networks consistently demonstrated superior predictive accuracy Non-interpretable or black box ML models may not find clinical application on ethical grounds. The future of preeclampsia prediction using ML lies in balancing model performance with interpretability. Human oversight remains indispensable in implementing and interpreting these models to achieve better maternal outcomes. Further research and validation across diverse populations are critical to establishing the universal applicability of these promising ML-based approaches.

PMID:39834976 | PMC:PMC11743919 | DOI:10.7759/cureus.76095

Front Oncol. 2025 Jan 6;14:1428929. doi: 10.3389/fonc.2024.1428929. eCollection 2024.

ABSTRACT

OBJECTIVE: This meta-analysis aims to evaluate the diagnostic accuracy of magnetic resonance imaging (MRI) based radiomic features for predicting epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients with brain metastases.

METHODS: We systematically searched PubMed, Embase, Cochrane Library, Web of Science, Scopus, Wanfang, and China National Knowledge Infrastructure (CNKI) for studies published up to April 30, 2024. We included those studies that utilized MRI-based radiomic features to detect EGFR mutations in NSCLC patients with brain metastases. Sensitivity, specificity, positive and negative likelihood ratios (PLR, NLR), and area under the curve (AUC) were calculated to evaluate the accuracy. Quality assessment was performed using the quality assessment of prognostic accuracy studies 2 (QUADAS-2) tool. Meta-analysis was conducted using random-effects models.

RESULTS: A total of 13 studies involving 2,348 patients were included. The pooled sensitivity and specificity of MRI-based radiomic features for detecting EGFR mutations were 0.86 (95% CI: 0.74-0.93) and 0.83 (95% CI: 0.72-0.91), respectively. The PLR and NLR were calculated as 5.14 (3.09, 8.55) and 0.17 (0.10, 0.31), respectively. Substantial heterogeneity was observed, with I² values exceeding 50% for all parameters. The AUC for the receiver operating characteristic analysis was 0.91 (95% CI: 0.88-0.93). Subgroup analysis indicated that deep learning models and studies conducted in Asian showed higher diagnostic accuracy compared to their respective counterparts.

CONCLUSIONS: MRI-based radiomic features demonstrate a high potential for accurately detecting EGFR mutations in NSCLC patients with brain metastases, particularly when advanced deep learning techniques were employed. However, the variability in diagnostic performance across different studies underscores the need for standardized radiomic protocols to enhance reproducibility and clinical utility.

SYSTEMATIC REVIEW REGISTRATION: https://www.crd.york.ac.uk/prospero/, identifier CRD42024544131.

PMID:39834943 | PMC:PMC11743156 | DOI:10.3389/fonc.2024.1428929

Front Oncol. 2025 Jan 6;14:1423549. doi: 10.3389/fonc.2024.1423549. eCollection 2024.

ABSTRACT

BACKGROUND: Improvements in the clinical diagnostic use of magnetic resonance imaging (MRI) for the identification of liver disorders have been made possible by gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA). Gd-EOB-DTPA-enhanced magnetic resonance imaging (MRI) technology is in high demand.

OBJECTIVES: The purpose of the study is to segment the liver using an enhanced multi-gradient deep convolution neural network (EMGDCNN) and to identify and categorize a localized liver lesion using a Gd-EOB-DTPA-enhanced MRI.

METHODS: We provided the classifier images of the liver in five states (unenhanced, arterial, portal venous, equilibrium, and hepatobiliary) and labeled them with localized liver diseases (hepatocellular carcinoma, metastasis, hemangiomas, cysts, and scarring). The Shanghai Public Health Clinical Center ethics committee recruited 132 participants between August 2021 and February 2022. Fisher's exact test analyses liver lesion Gd-EOB-DTPA-enhanced MRI data.

RESULTS: Our method could identify and classify liver lesions at the same time. On average, 25 false positives and 0.6 real positives were found in the test instances. The percentage of correct answers was 0.790. AUC, sensitivity, and specificity evaluate the procedure. Our technique outperforms others in extensive testing.

CONCLUSION: EMGDCNN may identify and categorize a localized hepatic lesion in Gd-EOB-DTPA-enhanced MRI. We found that one network can detect and classify. Radiologists need higher detection capability.

PMID:39834934 | PMC:PMC11743610 | DOI:10.3389/fonc.2024.1423549

Front Artif Intell. 2025 Jan 6;7:1501184. doi: 10.3389/frai.2024.1501184. eCollection 2024.

ABSTRACT

Traditional Chinese medicine (TCM) has long utilized tongue diagnosis as a crucial method for assessing internal visceral condition. This study aims to modernize this ancient practice by developing an automated system for analyzing tongue images in relation to the five organs, corresponding to the heart, liver, spleen, lung, and kidney-collectively known as the "five viscera" in TCM. We propose a novel tongue image partitioning algorithm that divides the tongue into four regions associated with these specific organs, according to TCM principles. These partitioned regions are then processed by our newly developed OrganNet, a specialized neural network designed to focus on organ-specific features. Our method simulates the TCM diagnostic process while leveraging modern machine learning techniques. To support this research, we have created a comprehensive tongue image dataset specifically tailored for these five visceral pattern assessment. Results demonstrate the effectiveness of our approach in accurately identifying correlations between tongue regions and visceral conditions. This study bridges TCM practices with contemporary technology, potentially enhancing diagnostic accuracy and efficiency in both TCM and modern medical contexts.

PMID:39834879 | PMC:PMC11743429 | DOI:10.3389/frai.2024.1501184

Front Cardiovasc Med. 2025 Jan 6;11:1473482. doi: 10.3389/fcvm.2024.1473482. eCollection 2024.

ABSTRACT

INTRODUCTION: The risk of mortality associated with cardiac arrhythmias is considerable, and their diagnosis presents significant challenges, often resulting in misdiagnosis. This situation highlights the necessity for an automated, efficient, and real-time detection method aimed at enhancing diagnostic accuracy and improving patient outcomes.

METHODS: The present study is centered on the development of a portable deep learning model for the detection of arrhythmias via electrocardiogram (ECG) signals, referred to as CardioAttentionNet (CANet). CANet integrates Bi-directional Long Short-Term Memory (BiLSTM) networks, Multi-head Attention mechanisms, and Depthwise Separable Convolution, thereby facilitating its application in portable devices for early diagnosis. The architecture of CANet allows for effective processing of extended ECG patterns and detailed feature extraction without a substantial increase in model size.

RESULTS: Empirical results indicate that CANet outperformed traditional models in terms of predictive performance and stability, as confirmed by comprehensive cross-validation. The model demonstrated exceptional capabilities in detecting cardiac arrhythmias, surpassing existing models in both cross-validation and external testing scenarios. Specifically, CANet achieved high accuracy in classifying various arrhythmic events, with the following accuracies reported for different categories: Normal (97.37 ± 0.30%), Supraventricular (98.09 ± 0.25%), Ventricular (92.92 ± 0.09%), Atrial Fibrillation (99.07 ± 0.13%), and Unclassified arrhythmias (99.68 ± 0.06%). In external evaluations, CANet attained an average accuracy of 94.41%, with the area under the curve (AUC) for each category exceeding 99%, thereby demonstrating its substantial clinical applicability and significant advancements over traditional models.

DISCUSSION: The deep learning model proposed in this study has the potential to enhance the accuracy of early diagnosis for various types of arrhythmias. Looking ahead, this technology is anticipated to provide improved medical services for patients with heart disease through continuous, non-invasive monitoring and timely intervention.

PMID:39834732 | PMC:PMC11744002 | DOI:10.3389/fcvm.2024.1473482

Proc IEEE Int Symp Biomed Imaging. 2024 May;2024. doi: 10.1109/isbi56570.2024.10635530. Epub 2024 Aug 22.

ABSTRACT

Real-time dynamic MRI is important for visualizing time-varying processes in several applications, including cardiac imaging, where it enables free-breathing images of the beating heart without ECG gating. However, current real-time MRI techniques commonly face challenges in achieving the required spatio-temporal resolutions due to limited acceleration rates. In this study, we propose a deep learning (DL) technique for improving the estimation of stationary outer-volume signal from shifted time-interleaved undersampling patterns. Our approach utilizes the pseudo-periodic nature of the ghosting artifacts arising from the moving organs. Subsequently, this estimated outer-volume signal is subtracted from individual timeframes of the real-time MR time series, and each timeframe is reconstructed individually using physics-driven DL methods. Results show improved image quality at high acceleration rates, where conventional methods fail.

PMID:39834646 | PMC:PMC11742269 | DOI:10.1109/isbi56570.2024.10635530

Front Surg. 2025 Jan 6;11:1424716. doi: 10.3389/fsurg.2024.1424716. eCollection 2024.

ABSTRACT

INTRODUCTION: To develop an intelligent system based on artificial intelligence (AI) deep learning algorithms using deep learning tools, aiming to assist in the diagnosis of lumbar degenerative diseases by identifying lumbar spine magnetic resonance images (MRI) and improve the clinical efficiency of physicians.

METHODS: The PP-YOLOv2 algorithm, a deep learning technique, was used to design a deep learning program capable of automatically identifying the spinal diseases (lumbar disc herniation or lumbar spondylolisthesis) based on the lumbar spine MR images. A retrospective analysis was conducted on lumbar spine MR images of patients who visited our hospital from January 2017 to January 2022. The collected images were divided into a training set and a testing set. The training set images were used to establish and validate the deep learning program's algorithm. The testing set images were annotated, and the experimental results were recorded by three spinal specialists. The training set images were also validated using the deep learning program, and the experimental results were recorded. Finally, a comparison of the accuracy of the deep learning algorithm and that of spinal surgeons was performed to determine the clinical usability of deep learning technology based on the PP-YOLOv2 algorithm. A total of 654 patients were included in the final study, with 604 cases in the training set and 50 cases in the testing set.

RESULTS: The mean average precision (mAP) value of the deep learning algorithm reached 90.08% based on the PP-YOLOv2 algorithm. Through classification of the testing set, the deep learning algorithm showed higher sensitivity, specificity, and accuracy in diagnosing lumbar spine MR images compared to manual identification. Additionally, the testing time of the deep learning program was significantly shorter than that of manual identification, and the differences were statistically significant (P < 0.05).

CONCLUSIONS: Deep learning technology based on the PP-YOLOv2 algorithm can be used to identify normal intervertebral discs, lumbar disc herniation, and lumbar spondylolisthesis from lumbar MRI images. Its diagnostic performance is significantly higher than that of most spinal surgeons and can be practically applied in clinical settings.

PMID:39834502 | PMC:PMC11743461 | DOI:10.3389/fsurg.2024.1424716