DEN Open. 2025 Apr 29;6(1):e70124. doi: 10.1002/deo2.70124. eCollection 2026 Apr.

ABSTRACT

A 74-year-old man with decreased appetite, weight, and heartburn was referred to our hospital. His medications included olmesartan. Esophagogastroduodenoscopy (EGD) revealed antral-dominant erosive gastritis and nodular mucosa. A gastric biopsy revealed inflammatory cell infiltration. The serum anti-Helicobacter pylori immunoglobulin G antibody test result was negative. Famotidine was ineffective in relieving his symptoms, and esomeprazole failed to prevent overt gastric bleeding, which required endoscopic hemostasis. The working diagnosis was drug-induced gastritis, particularly olmesartan-induced gastritis. His appetite loss started to improve within a week of olmesartan withdrawal. The erosions healed on EGD 2 months later. Over the next 10 months, he remained in his usual state until olmesartan was inadvertently administered. Subsequent EGD revealed a mild gastritis relapse. We diagnosed olmesartan-induced gastritis and discontinued olmesartan treatment. Mucosal healing was confirmed by EGD 1 year later. Olmesartan is known to cause angiotensin II receptor blocker-induced enteropathy. Although angiotensin II receptor blocker-induced enteropathy affects the stomach, angiotensin II receptor blocker-induced gastritis without lower gastrointestinal symptoms is rare. The characteristic endoscopic appearance may provide a clue to the correct diagnosis.

PMID:40309044 | PMC:PMC12038180 | DOI:10.1002/deo2.70124

Cureus. 2025 Mar 31;17(3):e81513. doi: 10.7759/cureus.81513. eCollection 2025 Mar.

ABSTRACT

Capivasertib, a protein kinase B (AKT) inhibitor manufactured by AstraZeneca pharmaceutical and used in the treatment of various malignancies, has been implicated in cases of drug-induced diabetic ketoacidosis (DKA). We present a case of capivasertib-induced DKA in a patient with no prior history of diabetes, highlighting the metabolic complications associated with this targeted therapy. The proposed mechanism involves AKT inhibition leading to impaired insulin signaling, reduced glucose uptake, and increased lipolysis, ultimately resulting in ketogenesis. This case underscores the need for vigilant glucose monitoring in patients receiving capivasertib, especially those with predisposing risk factors for insulin resistance or pancreatic dysfunction.

PMID:40308416 | PMC:PMC12043024 | DOI:10.7759/cureus.81513

Am J Hum Genet. 2025 Jun 5;112(6):1376-1387. doi: 10.1016/j.ajhg.2025.04.003. Epub 2025 Apr 29.

ABSTRACT

The diagnosis of mitochondrial DNA (mtDNA) diseases remains challenging with next-generation sequencing, where bioinformatic analysis is usually more focused on the nuclear genome. We developed a workflow for the evaluation of mtDNA diseases and applied it in a large European rare disease cohort (Solve-RD). A semi-automated bioinformatic pipeline with MToolBox was used to filter the unsolved Solve-RD cohort for rare mtDNA variants after validating this pipeline on exome datasets of 42 individuals previously diagnosed with mtDNA variants. Variants were filtered based on blood heteroplasmy levels (≥1%) and reported association with disease. Overall, 10,157 exome and genome datasets from 9,923 affected individuals from 9,483 families within Solve-RD met the quality inclusion criteria. 136 mtDNA variants in 135 undiagnosed individuals were prioritized using the filtering approach. A focused MitoPhen-based phenotype similarity scoring method was tested in a separate genetically diagnosed "phenotype test cohort" consisting of nuclear gene and mtDNA diseases using a receiving operator characteristic evaluation. We applied the MitoPhen-based phenotype similarity score of >0.3, which was highly sensitive for detecting mtDNA diseases in the phenotype test cohort, to the filtered cohort of 135 undiagnosed individuals. This aided the prioritization of 34 out of 37 (92%) individuals who received confirmed and likely causative mtDNA disease diagnoses. The phenotypic evaluation was limited by the quality of input data in some individuals. The overall pipeline led to an additional diagnostic yield of 0.4% in a cohort where mitochondrial disease was not initially suspected. This highlights the value of our mtDNA analysis pipeline in diverse datasets.

PMID:40306282 | DOI:10.1016/j.ajhg.2025.04.003

Sci Rep. 2025 Apr 30;15(1):15160. doi: 10.1038/s41598-025-99646-w.

ABSTRACT

Laser cleaning is widely used industrially to remove surface contaminants with high precision. Conventional methods, however, lack real-time monitoring and feedback loops, often necessitating over-machining to ensure complete contaminant removal, which leads to inefficient energy use and potential substrate damage. In this work, we demonstrate a concept of selective laser cleaning via the application of femtosecond laser pulses and polystyrene microbeads with a diameter of 15 μm. These microbeads model challenging scenarios in high-precision optical work and delicate surface treatments across laboratory and production settings. To enable adaptive, real-time cleaning, we integrated a neural network that predicts the sample's appearance after each laser pulse into a feedback loop, tailoring the cleaning process to a bespoke target pattern. This method ensures precise contaminant removal with minimal energy use, making it highly promising for applications demanding strict material control, such as wafer cleaning, sensitive surface treatments, and heritage restoration. By combining machine learning with ultrafast laser technology, our approach significantly enhances the efficiency and precision of cleaning processes.

PMID:40307358 | DOI:10.1038/s41598-025-99646-w

Sci Rep. 2025 Apr 30;15(1):15166. doi: 10.1038/s41598-025-99309-w.

ABSTRACT

Recent advancements in deep learning have significantly impacted medical image processing domain, enabling sophisticated and accurate diagnostic tools. This paper presents a novel hybrid deep learning framework that combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for diabetic retinopathy (DR) early detection and progression monitoring using retinal fundus images. Utilizing the sequential nature of disease progression, the proposed method integrates temporal information across multiple retinal scans to enhance detection accuracy. The proposed model utilizes publicly available DRIVE and Kaggle diabetic retinopathy datasets to evaluate the performance. The benchmark datasets provide a diverse set of annotated retinal images and the proposed hybrid model employs a CNN to extract spatial features from retinal images. The spatial feature extraction is enhanced by multi-scale feature extraction to capture fine details and broader patterns. These enriched spatial features are then fed into an RNN with attention mechanism to capture temporal dependencies so that most relevant data aspects can be considered for analysis. This combined approach enables the model to consider both current and previous states of the retina, improving its ability to detect subtle changes indicative of early-stage DR. Proposed model experimental evaluation demonstrate the superior performance over traditional deep learning models like CNN, RNN, InceptionV3, VGG19 and LSTM in terms of both sensitivity and specificity, achieving 97.5% accuracy on the DRIVE dataset, 94.04% on the Kaggle dataset, 96.9% on the Eyepacs Dataset. This research work not only advances the field of automated DR detection but also provides a framework for utilizing temporal information in medical image analysis.

PMID:40307328 | DOI:10.1038/s41598-025-99309-w

Sci Data. 2025 Apr 30;12(1):719. doi: 10.1038/s41597-025-05030-8.

ABSTRACT

Virological plaque assay is the major method of detecting and quantifying infectious viruses in research and diagnostic samples. Furthermore, viral plaque phenotypes contain information about the life cycle and spreading mechanism of the virus forming them. While some modernisations have been proposed, the conventional assay typically involves manual quantification of plaque phenotypes, which is both laborious and time-consuming. Here, we present an annotated dataset of digital photographs of plaque assay plates of Vaccinia virus - a prototypic propoxvirus. We demonstrate how analysis of these plates can be performed using deep learning by training models based on the leading architecture for biomedical instance segmentation - StarDist. Finally, we show that the entire analysis can be achieved in a single step by HydraStarDist - the modified architecture we propose.

PMID:40307255 | DOI:10.1038/s41597-025-05030-8

Korean J Radiol. 2025 May;26(5):446-445. doi: 10.3348/kjr.2024.1059.

ABSTRACT

OBJECTIVE: To compare the quality of deep learning-reconstructed turbo spin-echo (DL-TSE) and conventionally interpolated turbo spin-echo (Conv-TSE) techniques in contrast-enhanced MRI of the neck.

MATERIALS AND METHODS: Contrast-enhanced T1-weighted DL-TSE and Conv-TSE images were acquired using 3T scanners from 106 patients. DL-TSE employed a closed-source, 'work-in-progress' (WIP No. 1062, iTSE, version 10; Siemens Healthineers) algorithm for interpolation and denoising to achieve the same in-plane resolution (axial: 0.26 × 0.26 mm²; coronal: 0.29 × 0.29 mm²) while reducing scan times by 15.9% and 52.6% for axial and coronal scans, respectively. The full width at half maximum (FWHM) and percent signal ghosting were measured using stationary and flow phantom scans, respectively. In patient images, non-uniformity (NU), contrast-to-noise ratio (CNR), and regional mucosal FWHM were evaluated. Two neuroradiologists visually rated the patient images for overall quality, sharpness, regional mucosal conspicuity, artifacts, and lesions using a 5-point Likert scale.

RESULTS: FWHM in the stationary phantom scan was consistently sharper in DL-TSE. The percent signal ghosting outside the flow phantom was lower in DL-TSE (0.06% vs. 0.14%) but higher within the phantom (8.92% vs. 1.75%) compared to Conv-TSE. In patient scans, DL-TSE showed non-inferior NU and higher CNR. Regional mucosal FWHM was significantly better in DL-TSE, particularly in the oropharynx (coronal: 1.08 ± 0.31 vs. 1.52 ± 0.46 mm) and hypopharynx (coronal: 1.26 ± 0.35 vs. 1.91 ± 0.56 mm) (both P < 0.001). DL-TSE demonstrated higher overall image quality (axial: 4.61 ± 0.49 vs. 3.32 ± 0.54) and sharpness (axial: 4.40 ± 0.56 vs. 3.11 ± 0.53) (both P < 0.001). In addition, mucosal conspicuity was improved, especially in the oropharynx (axial: 4.41 ± 0.67 vs. 3.40 ± 0.69) and hypopharynx (axial: 4.45 ± 0.58 vs. 3.58 ± 0.63) (both P < 0.001). Extracorporeal ghost artifacts were reduced in DL-TSE (axial: 4.32 ± 0.60 vs. 3.90 ± 0.71, P < 0.001) but artifacts overlapping anatomical structures were slightly more pronounced (axial: 3.78 ± 0.74 vs. 3.95 ± 0.72, P < 0.001). Lesions were detected with higher confidence in DL-TSE.

CONCLUSION: DL-based reconstruction applied to accelerated neck MRI improves overall image quality, sharpness, mucosal conspicuity in motion-prone regions, and lesion detection confidence. Despite more pronounced ghost artifacts overlapping anatomical structures, DL-TSE enables substantial scan time reduction while enhancing diagnostic performance.

PMID:40307199 | DOI:10.3348/kjr.2024.1059

BMC Bioinformatics. 2025 Apr 30;26(1):117. doi: 10.1186/s12859-025-06132-1.

ABSTRACT

Accelerating drug discovery for glucocorticoid receptor (GR)-related disorders, including innovative machine learning (ML)-based approaches, holds promise in advancing therapeutic development, optimizing treatment efficacy, and mitigating adverse effects. While experimental methods can accurately identify GR antagonists, they are often not cost-effective for large-scale drug discovery. Thus, computational approaches leveraging SMILES information for precise in silico identification of GR antagonists are crucial, enabling efficient and scalable drug discovery. Here, we develop a new ensemble learning approach using a multi-step stacking strategy (M3S), termed M3S-GRPred, aimed at rapidly and accurately discovering novel GR antagonists. To the best of our knowledge, M3S-GRPred is the first SMILES-based predictor designed to identify GR antagonists without the use of 3D structural information. In M3S-GRPred, we first constructed different balanced subsets using an under-sampling approach. Using these balanced subsets, we explored and evaluated heterogeneous base-classifiers trained with a variety of SMILES-based feature descriptors coupled with popular ML algorithms. Finally, M3S-GRPred was constructed by integrating probabilistic feature from the selected base-classifiers derived from a two-step feature selection technique. Our comparative experiments demonstrate that M3S-GRPred can precisely identify GR antagonists and effectively address the imbalanced dataset. Compared to traditional ML classifiers, M3S-GRPred attained superior performance in terms of both the training and independent test datasets. Additionally, M3S-GRPred was applied to identify potential GR antagonists among FDA-approved drugs confirmed through molecular docking, followed by detailed MD simulation studies for drug repurposing in Cushing's syndrome. We anticipate that M3S-GRPred will serve as an efficient screening tool for discovering novel GR antagonists from vast libraries of unknown compounds in a cost-effective manner.

PMID:40307679 | DOI:10.1186/s12859-025-06132-1

J Glob Antimicrob Resist. 2025 Apr 28:S2213-7165(25)00082-7. doi: 10.1016/j.jgar.2025.04.010. Online ahead of print.

ABSTRACT

OBJECTIVES: Chronic Pseudomonas aeruginosa infections are a leading cause of acute pulmonary exacerbations in people with cystic fibrosis (pwCF). Intrinsic antibiotic resistance and biofilm formation complicate treatment. This study investigates the genomic diversity and cefiderocol efficacy against planktonic and biofilm-associated forms of P. aeruginosa isolates from pwCF.

METHODS: Eight P. aeruginosa clinical isolates and three laboratory strains underwent whole genome sequencing (WGS). Biofilm formation was assessed through biomass, cell count, metabolic activity, and extracellular DNA (eDNA). The minimum bactericidal concentration (MBC90) and biofilm eradication concentration (MBEC90) were also determined.

RESULTS: WGS revealed significant genomic diversity, identifying ten distinct sequence types (STs). Antibiotic susceptibility testing (AST) showed that 10/11 strains were susceptible to cefiderocol, with one isolate (MPA9) displaying resistance linked to the blaOXA486 gene. Adding the β-lactamase inhibitor avibactam (AVI) restored susceptibility in this resistant strain. Although iron metabolism genes were highly conserved across isolates, MPA9 lacked the fpvA iron receptor, potentially contributing to cefiderocol resistance. Biofilm formation significantly increased tolerance to cefiderocol, with an 8-fold rise in MBEC90 compared to MBC90.

CONCLUSION: These findings highlight the genomic diversity and adaptive potential of P. aeruginosa in pwCF. Cefiderocol shows promise against planktonic and biofilm-associated P. aeruginosa, and combining it with AVI may counteract β-lactamase-mediated resistance.

PMID:40306463 | DOI:10.1016/j.jgar.2025.04.010

Endocr Pract. 2025 Apr 28:S1530-891X(25)00129-6. doi: 10.1016/j.eprac.2025.04.011. Online ahead of print.

ABSTRACT

Cystic fibrosis (CF) is a multisystem autosomal recessive disease arising from mutations in the cystic fibrosis transmembrane conductance regulator (CFTR) gene. Dysfunction of the CFTR protein leads to progressive pulmonary disease, pancreatic exocrine insufficiency, and nutritional deficiencies. Survival has significantly increased over the last several decades due to improved pulmonary and nutritional management, including CFTR modulator therapy. The adult CF population now faces new challenges of aging, such as menopause-related symptoms and age-related osteoporosis superimposed on underlying CF-related bone disease. The menopausal transition and early post-menopause are characterized by rapid bone loss and represent a window of opportunity to preserve bone mass. Menopausal hormone therapy may alleviate vasomotor symptoms and improve bone density in appropriately selected people. This review will discuss the current knowledge of menopause and bone health in females with CF, address CF-specific considerations on osteoporosis and menopause treatment options, and explore opportunities for future areas of research.

PMID:40306365 | DOI:10.1016/j.eprac.2025.04.011

Med. 2025 Apr 25:100676. doi: 10.1016/j.medj.2025.100676. Online ahead of print.

ABSTRACT

BACKGROUND: Anti-melanoma differentiation-associated protein 5 dermatomyositis (MDA5+DM) is a potentially fatal subtype of dermatomyositis. The most severe cases are characterized by rapidly progressive interstitial lung disease (RPILD), the leading cause of death in these patients. There is currently no curative treatment for these patients, and indeed, MDA5+DM-RPILD is considered one of the most challenging pathologies in medicine. Nevertheless, the recent introduction of CD19 chimeric antigen receptor (CAR)-T cell therapies appears to offer a serious opportunity to develop solutions for complex autoimmune diseases refractory to multiple immunosuppressant treatments, mainly rheumatic diseases such as rheumatoid arthritis, dermatomyositis, and systemic lupus erythematosus.

METHODS: In this report, we describe the first use of a second-generation CD19 CAR-T cell therapy (ARI-0001) in a pediatric patient with severe MDA5+DM-RPILD.

FINDINGS: Conventional treatments stabilized MDA5+DM-RPILD before CAR-T cell inoculation (-34 days). The presence of CD19+ B lymphocytes that might serve as target cells in deeper tissues was suspected due to CAR-T cell expansion in a context of B cell aplasia. No fever or cytokine release syndrome/cell-associated neurotoxicity syndrome was evident. In global terms, B cell reconstitution and cutaneous, motor, respiratory, and neurological improvements were observed gradually in the patient in an immunosuppressant-free context (-7 to +325 days).

CONCLUSIONS: A pediatric patient with aggressive MDA5+DM-RPILD achieved progressive long-term improvement and immunosuppressant-free remission over 11 months after compassionate use of a CD19 CAR-T cell therapy (ARI-0001).

FUNDING: This work was supported by the Programa Investigo (PI_SEPE_APM) and grants from the ISC-III (PI22/01226) from the Comunidad de Madrid (S2022/BMD-7225) and from the CRIS Cancer Foundation.

PMID:40306284 | DOI:10.1016/j.medj.2025.100676

Radiat Oncol. 2025 Apr 30;20(1):68. doi: 10.1186/s13014-025-02643-6.

ABSTRACT

BACKGROUND: To quantify morphological and dosimetric variations in nasopharyngeal carcinoma (NPC) radiotherapy via autosegmented fan-beam computed tomography (FBCT) and to inform decision-making regarding appropriate objectives and optimal timing for adaptive radiotherapy (ART).

METHODS: This retrospective study analyzed 23 NPC patients (681 FBCT scans) treated at Sun Yat-sen Cancer Center from August 2022 to May 2024. The inclusion criterion was as follows: ≥1 weekly FBCT via a CT-linac with ≤ 2 fractions between scans. Four deep learning-based autosegmentation models were developed to assess weekly volume, Dice similarity coefficient (DSC), and dose variations in organs at risk (OARs) and target volumes.

RESULTS: A systematic review of autosegmentation on FBCT scans demonstrated satisfactory accuracy overall, and missegmentation was manually modified. Linear decreases in volume and/or DSC were observed in the parotid glands, submandibular glands, thyroid, spinal cord, and target volumes (R² > 0.7). The linear dose variation included coverage of the low risk planning target volume (-3.01%), the mean dose to the parotid glands (+ 2.45 Gy) and thyroid (+ 1.18 Gy), the D1% of the brainstem (+ 0.56 Gy), and the maximum dose to the spinal cord (+ 1.12 Gy). The greatest reduction in target volume coverage was noted in PGTVns, reaching 7.15%. The most significant dose changes occurred during weeks 3-6.

CONCLUSIONS: During NPC radiotherapy, the progressive dose deviations may not be corrected through repositioning alone, necessitating ART intervention. As dose variations in OARs rarely exceed 3 Gy and target coverage fluctuations remain within 10%, ART does not need to be performed frequently, and weeks 3-6 represent the most appropriate window.

PMID:40307931 | DOI:10.1186/s13014-025-02643-6

BMC Res Notes. 2025 Apr 30;18(1):200. doi: 10.1186/s13104-025-07263-7.

ABSTRACT

OBJECTIVE: Detecting small, faraway objects in real-time surveillance is challenging due to limited pixel representation, affecting classifier performance. Deep Learning (DL) techniques generate feature maps to enhance detection, but conventional methods suffer from high computational costs. To address this, we propose Multi-Scale Region-wise Pixel Analysis with GAN for Tiny Object Detection (MSRP-TODNet). The model is trained and tested on VisDrone VID 2019 and MS-COCO datasets. First, images undergo two-fold pre-processing using Improved Wiener Filter (IWF) for artifact removal and Adjusted Contrast Enhancement Method (ACEM) for blurring correction. The Multi-Agent Reinforcement Learning (MARL) algorithm splits the pre-processed image into four regions, analyzing each pixel to generate feature maps. These are processed by the Enhanced Feature Pyramid Network (EFPN), which merges them into a single feature map. Finally, a Generative Adversarial Network (GAN) detects objects with bounding boxes.

RESULTS: Experimental results on the DOTA dataset demonstrate that MSRP-TODNet outperforms existing state-of-the-art methods. Specifically, it achieves an mAP @0.5 of 84.2%, mAP @0.5:0.95 of 54.1%, and an F1-Score of 84.0%, surpassing improved TPH-YOLOv5, YOLOv7-Tiny, and DRDet by margins of 1.7%-6.1% in detection performance. These results demonstrate the framework's effectiveness for accurate, real-time small object detection in UAV surveillance and aerial imagery.

PMID:40307915 | DOI:10.1186/s13104-025-07263-7

J Cheminform. 2025 Apr 30;17(1):66. doi: 10.1186/s13321-025-01015-2.

ABSTRACT

The cytochrome P450 (CYP) superfamily metabolises a wide range of compounds; however, drug-induced CYP inhibition can lead to adverse interactions. Identifying potential CYP inhibitors is crucial for safe drug administration. This study investigated the application of deep learning techniques to the prediction of CYP inhibition, focusing on the challenges posed by limited datasets for CYP2B6 and CYP2C8 isoforms. To tackle these limitations, we leveraged larger datasets for related CYP isoforms, compiling comprehensive data from public databases containing IC50 values for 12,369 compounds that target seven CYP isoforms. We constructed single-task, fine-tuning, multitask, and multitask models incorporating data imputation on the missing values. Notably, the multitask models with data imputation demonstrated significant improvement in CYP inhibition prediction over the single-task models. Using the most accurate prediction models, we evaluated the inhibitory activity of approved drugs against CYP2B6 and CYP2C8. Among the 1,808 approved drugs analysed, our multitask models with data imputation identified 161 and 154 potential inhibitors of CYP2B6 and CYP2C8, respectively. This study underscores the significant potential of multitask deep learning, particularly when utilising a graph convolutional network with data imputation, to enhance the accuracy of CYP inhibition predictions under the conditions of limited data availability.Scientific contributionThis study demonstrates that even with small datasets, accurate prediction models can be constructed by utilising related data effectively. Also, our imputation techniques on the missing values improved the prediction accuracy of CYP2B6 and CYP2C8 inhibition significantly.

PMID:40307863 | DOI:10.1186/s13321-025-01015-2

Vis Comput Ind Biomed Art. 2025 May 1;8(1):11. doi: 10.1186/s42492-025-00194-x.

ABSTRACT

Hypertensive retinopathy (HR) occurs when the choroidal vessels, which form the photosensitive layer at the back of the eye, are injured owing to high blood pressure. Artificial intelligence (AI) in retinal image analysis (RIA) for HR diagnosis involves the use of advanced computational algorithms and machine learning (ML) strategies to recognize and evaluate signs of HR in retinal images automatically. This review aims to advance the field of HR diagnosis by investigating the latest ML and deep learning techniques, and highlighting their efficacy and capability for early diagnosis and intervention. By analyzing recent advancements and emerging trends, this study seeks to inspire further innovation in automated RIA. In this context, AI shows significant potential for enhancing the accuracy, effectiveness, and consistency of HR diagnoses. This will eventually lead to better clinical results by enabling earlier intervention and precise management of the condition. Overall, the integration of AI into RIA represents a considerable step forward in the early identification and treatment of HR, offering substantial benefits to both healthcare providers and patients.

PMID:40307650 | DOI:10.1186/s42492-025-00194-x