JAMA Netw Open. 2025 May 1;8(5):e256908. doi: 10.1001/jamanetworkopen.2025.6908.

ABSTRACT

IMPORTANCE: Current therapeutic approaches are inaccessible to many people with chronic pain and frequently fail to address emotion dysregulation as a key factor in psychological comorbidity and pain intensity. An effective and accessible emotion regulation-focused intervention is needed.

OBJECTIVES: To compare the efficacy of online dialectical behavioral therapy for chronic pain plus treatment as usual (iDBT-Pain) with only treatment as usual on emotion dysregulation in people with chronic pain.

DESIGN, SETTING, AND PARTICIPANTS: This 2-arm randomized clinical trial was conducted from March 2023 to September 2024 in Australia. Participants were adults with chronic pain (lasting ≥3 months) and weekly pain intensity of 3 or higher out of 10 (10 indicating worst pain), without psychotic or personality disorders, and without dementia. Eligible participants were randomly assigned (1:1 ratio) to receive either iDBT-Pain for 9 weeks or treatment as usual only. Intention-to-treat data analyses were performed between August and September 2024.

INTERVENTIONS: The iDBT-Pain group received 8 group-based 90-minute therapist-guided online sessions as well as an app and a handbook for self-learning. Content focused on DBT skills training, including pain science education. Participants in the treatment-as-usual group continued usual care, which consisted of treatment options that can be accessed in the community.

MAIN OUTCOMES AND MEASURES: The primary outcome was emotion dysregulation at 9 weeks after randomization. The Difficulties in Emotion Regulation Scale (score range: 18-90, with higher scores indicating higher emotion dysregulation) was used in assessment.

RESULTS: Among 89 participants (mean [SD] age, 51.5 [14.2] years; 74 females [83%]), 44 (49%) were randomly assigned to the treatment-as-usual group and 45 (51%) were randomly assigned to the iDBT-Pain group. Overall, 79 participants (89%) completed the 9-week assessment. Between-group difference in emotion dysregulation over time favored iDBT-Pain over treatment as usual at 9 weeks (-4.88; 95% CI, -9.20 to -0.55; P = .03; Cohen d = -0.46 [95% CI, -0.87 to -0.08]).

CONCLUSIONS AND RELEVANCE: In this randomized clinical trial, the iDBT-Pain intervention, delivered through a self-learning and therapist-guided hybrid approach, resulted in sustained improvements in emotion dysregulation in people with chronic pain.

TRIAL REGISTRATION: Anzctr.org.au Identifier: ACTRN12622000113752.

PMID:40327344 | PMC:PMC12056567 | DOI:10.1001/jamanetworkopen.2025.6908

Orphanet J Rare Dis. 2025 May 6;20(1):215. doi: 10.1186/s13023-025-03715-2.

ABSTRACT

BACKGROUND: Onasemnogene abeparvovec (OA) is an adeno-associated virus vector-based gene therapy indicated for the treatment of paediatric patients with spinal muscular atrophy(SMA) with biallelic mutations in the survival motor neuron 1 (SMN1) gene. This study focused on analysis of the postmarketing adverse events(AEs) of onasemnogene abeparvovec (OA) reported in the US Food and Drug Administration public data open project (openFDA) database to assess the safety of OA in the real world and to provide a reference for the rational use of this drug in the clinic.

RESULTS: In total, 1,959 AEs were reported with "onasemnogene abeparvovec" as the primary suspected drug. The top 5 most frequent AEs were pyrexia (461 cases), vomiting (434 cases), aspartate aminotransferase increase (284 cases), alanine aminotransferase increase (260 cases), and hepatic enzyme increase (237 cases). A total of 77 alert signals were generated, 60 of which were not included in the drug label. The top 5 signals included troponin I increase ( ROR of 895.21, 95% CI: 734.43-1091.18), troponin T increase ( ROR of 313.30, 95% CI:220.85-444.44), rhinovirus infection ( ROR of 175.80, 95% CI:130.86-236.17), troponin increase ( ROR of 143.49, 95% CI:114.96-179.10), and increased bronchial secretion ( ROR of 142.71, 95% CI:96.63-210.77). Further analysis of AEs associated with gender and age differences identified 14 high-risk signals related to gender and 10 high-risk signals related to age. Female patients should be vigilant for vomiting, thrombotic microangiopathy, increased troponin T, proteinuria, haematuria, haemolytic anaemia, urinary tract infection, generalised oedema, and atypical haemolytic uraemic syndrome. Male patients should be alert to increased hepatic enzyme, increased bronchial secretion, respiratory tract infection, pallor, and increased blood creatine phosphokinase MB. Patients under 2 years of age should be vigilant for lethargy, increased monocyte count, decreased blood creatinine, and decreased neutrophil count. Patients over 2 years of age should be alert to hypertension, haematuria, rhinovirus infection, increased blood creatine phosphokinase, headache, and malaise.

CONCLUSIONS: Mining of OA alert signals using the openFDA database provides supplementary information on AEs not included in the drug label. Clinical attention should be focused on common, strong-signal, and label-unmentioned AEs to optimise medication regimens and control risks in clinical use.

PMID:40329332 | DOI:10.1186/s13023-025-03715-2

Sci Rep. 2025 May 6;15(1):15760. doi: 10.1038/s41598-025-00231-y.

ABSTRACT

This study employs a comprehensive approach to systematically identify drugs associated with Drug-Induced Erectile Dysfunction (DIED) risk and constructs a DIED risk assessment platform. Utilizing the FAERS database, we identified "Erectile Dysfunction," "Organic Erectile Dysfunction," and "Psychogenic Erectile Dysfunction" as relevant Preferred Terms (PTs) for DIED. After excluding patients diagnosed with Erectile Dysfunction (ED), drugs suspected as primary suspects (PS) in ≥ 10 DIP events were selected as target drugs. Through disproportionality analysis, we identified positive signals for these drugs using ROR, PRR, BCPNN, and EBGM. We further assessed the independent effects of positive drugs by adjusting for confounding factors such as age using multivariate logistic regression. Subsequently, we obtained the median onset time and outcome events of DIED for target drugs and compared them by age. The DIED platform is accessible for free at http://116.196.73.86:3838/ADR-DATABASE/DIED/. A total of 67 target drugs were identified as PS in DIED events with 10 or more cases. Based on disproportionality analysis, we further identified 28 drugs with DIED risk signals. Multivariate logistic regression revealed that 23 of these drugs were independent risk factors for DIED (OR > 1 and P < 0.05). Analysis of outcome events showed a significant difference in the median onset time of DIED between different age groups. This study identified 28 drugs associated with DIED risk. We also found some previously unreported DIP risk drugs, including omeprazole, antihypertensive drugs, etc., which should be of clinical concern.

PMID:40328828 | DOI:10.1038/s41598-025-00231-y

Diabetes Res Clin Pract. 2025 May 4:112221. doi: 10.1016/j.diabres.2025.112221. Online ahead of print.

ABSTRACT

Diabetes mellitus (DM) is a highly prevalent chronic condition with significant health and economic impacts; therefore, an accurate diagnosis is essential for the effective management and prevention of its complications. This review explores the latest advances in artificial intelligence (AI) focusing on machine learning (ML) and deep learning (DL) for the diagnosis of diabetes. Recent developments in AI-driven diagnostic tools were analyzed, with an emphasis on breakthrough methodologies and their real-world clinical applications. This review also discusses the role of various data sources, datasets, and preprocessing techniques in enhancing diagnostic accuracy. Key advancements in integrating AI into clinical workflows and improving early detection are highlighted along with challenges related to model interpretability, ethical considerations, and practical implementation. By offering a comprehensive overview of these advancements and their implications, this review contributes significantly to the understanding of how AI technologies can enhance the diagnosis of diabetes and support their integration into clinical practice, thereby aiming to improve patient outcomes and reduce the burden of diabetes.

PMID:40328407 | DOI:10.1016/j.diabres.2025.112221

Radiother Oncol. 2025 May 4:110914. doi: 10.1016/j.radonc.2025.110914. Online ahead of print.

ABSTRACT

PURPOSES: This study aimed to develop a computed tomography (CT)-based multi-organ segmentation model for delineating organs-at-risk (OARs) in pediatric upper abdominal tumors and evaluate its robustness across multiple datasets.

MATERIALS AND METHODS: In-house postoperative CTs from pediatric patients with renal tumors and neuroblastoma (n = 189) and a public dataset (n = 189) with CTs covering thoracoabdominal regions were used. Seventeen OARs were delineated: nine by clinicians (Type 1) and eight using TotalSegmentator (Type 2). Auto-segmentation models were trained using in-house (Model-PMC-UMCU) and a combined dataset of public data (Model-Combined). Performance was assessed with Dice Similarity Coefficient (DSC), 95 % Hausdorff Distance (HD95), and mean surface distance (MSD). Two clinicians rated clinical acceptability on a 5-point Likert scale across 15 patient contours. Model robustness was evaluated against sex, age, intravenous contrast, and tumor type.

RESULTS: Model-PMC-UMCU achieved mean DSC values above 0.95 for five of nine OARs, while the spleen and heart ranged between 0.90 and 0.95. The stomach-bowel and pancreas exhibited DSC values below 0.90. Model-Combined demonstrated improved robustness across both datasets. Clinical evaluation revealed good usability, with both clinicians rating six of nine Type 1 OARs above four and six of eight Type 2 OARs above three. Significant performance differences were only found across age groups in both datasets, specifically in the left lung and pancreas. The 0-2 age group showed the lowest performance.

CONCLUSION: A multi-organ segmentation model was developed, showcasing enhanced robustness when trained on combined datasets. This model is suitable for various OARs and can be applied to multiple datasets in clinical settings.

PMID:40328363 | DOI:10.1016/j.radonc.2025.110914

Proc Biol Sci. 2025 May;292(2046):20242233. doi: 10.1098/rspb.2024.2233. Epub 2025 May 7.

ABSTRACT

Traditional biomarkers, such as those obtained from blood tests, are essential for early disease detection, improving health outcomes and reducing healthcare costs. However, they often involve invasive procedures, specialized laboratory equipment or special handling of biospecimens. The retinal age gap (RAG) has emerged as a promising new biomarker that can overcome these limitations, making it particularly suitable for disease screening in low- and middle-income countries. This study aimed to evaluate the potential of the RAG as a biomarker for broad disease screening across a vast spectrum of diseases. Fundus images were collected from 86 522 UK Biobank participants aged 40-83 (mean age: 56.2 ± 8.3 years). A deep learning model was trained to predict retinal age using 17 791 images from healthy participants. The remaining images were categorized into disease/injury groups based on clinical codes. Additionally, 8524 participants from the Brazilian Multilabel Ophthalmological Dataset (BRSET) were used for external validation. Among the 159 disease/injury groups from the 2019 Global Burden of Disease Study, 56 groups (35.2%) exhibited RAG distributions significantly different from healthy controls. Notable examples included chronic kidney disease, cardiovascular disease, blindness, vision loss and diabetes. Overall, the RAG shows great promise as a cost-effective, non-invasive biomarker for early disease screening.

PMID:40328303 | DOI:10.1098/rspb.2024.2233

BMC Chem. 2025 May 6;19(1):119. doi: 10.1186/s13065-025-01468-4.

ABSTRACT

Trichinellosis represents great public health and economic problems worldwide. Moreover, the development of parasitic resistance against conventional anthelminthic treatment led to the urgent search for new therapeutic strategies, including drug repurposing. Bisphosphonates have been used to inhibit the growth of many parasites and have also emerged as promising candidates for the treatment of cryptosporidiosis and amoebic liver abscess. Alendronate is a second-generation bisphosphonate that is widely used for the treatment and prevention of osteoporosis. Till date, there is not enough data on the effect of this drug on Trichinella spiralis and it is unknown whether the regular use of this drug in osteoporotic patients may alter the course of the infection. ALN showed a significant lethal effect on both adult worms and juveniles, with severe tegumental damage in the form of fissures in the cuticle, widening of the hypodermal gland, and flattening of the cuticular annulation, ending with the appearance of multiple vesicles and large cauliflower masses. Molecular docking outcomes unveiled the potential inhibition of ALN against T. spiralis surface proteins (i.e., Ts-SP, Ts-PPase, Ts-MAPRC2, Ts-TS, Ts-MIF, etc.), with promising results confirmed its ability to defeat T. spiralis via targeting its surface proteins. Moreover, molecular dynamics simulation, through the analysis of RMSD, RMSF, RG, SASA and cluster analysis, proved the prolonged effective inhibition of ALN on T. spiralis inorganic pyrophosphatase, as an essential surface protein required for molting and developmental process of intestinal larval stages. Thus, ALN might be a valuable drug candidate for the treatment of trichinellosis and warrant further investigation in animal models of disease.

PMID:40329381 | DOI:10.1186/s13065-025-01468-4

Naunyn Schmiedebergs Arch Pharmacol. 2025 May 6. doi: 10.1007/s00210-025-04212-w. Online ahead of print.

ABSTRACT

Inflammatory bowel disease (IBD) is a chronic inflammatory condition of the gastrointestinal tract with a multifactorial etiology. Given the limitations and adverse effects of current therapies, there is a need for novel therapeutic approaches. Drug repurposing presents a promising opportunity to utilize medications with known safety and pharmacological profiles for alternative colitis treatment. Emerging evidence suggests the renin-angiotensin system (RAS) plays a significant role in the colitis pathophysiology. Angiotensin-converting enzyme (ACE) inhibitors may offer therapeutic potential by modulating pro-inflammatory cytokines and reducing oxidative stress. This study aims to evaluate the efficacy of lisinopril (LIS) in a 2,4,6-trinitrobenzene sulfonic acid (TNBS)-induced colitis model in Wistar rats. Colitis was induced in Wistar rats via a single intracolonic TNBS dose (100 mg/kg). Treatment groups received oral interventions for 5 days: 5-aminosalicylic acid (5-ASA; 25.5 mg/kg), LIS (10 mg/kg), or LIS (20 mg/kg). Efficacy was evaluated using the disease activity score rate (DASR), colon/body weight ratio (CBWR), and colon length, diameter, and pH. Colonic tissue was analyzed macroscopically and histopathologically. Inflammatory biomarkers interleukin-6 (IL-6), tumor necrosis factor-alpha (TNF-α), oxidative stress markers glutathione (GSH), and malondialdehyde (MDA), as well as C-reactive protein (CRP) and complete blood count (CBC), were measured. LIS significantly reduced colitis severity, decreasing DASR and CBWR, while restoring colon dimensions and pH. LIS showed potent anti-colitic effects by suppressing TNF-α and IL-6 levels, reducing MDA, and increasing GSH. LIS restored RBC and WBC levels while normalizing CRP and hemoglobin levels. Histopathological and macroscopic analyses confirmed colonic protection with minimal detrimental effects on the stomach and liver. LIS, particularly at 20 mg/kg, exhibited dose-dependent anti-inflammatory, antioxidant, and tissue-protective effects, showing promise as a therapeutic agent for colitis treatment.

PMID:40328912 | DOI:10.1007/s00210-025-04212-w

Cell Death Differ. 2025 May 6. doi: 10.1038/s41418-025-01521-8. Online ahead of print.

ABSTRACT

Oxysterol-binding proteins (OSBPs), lipid transfer proteins functioning at intracellular membrane contact sites, are recently found to be dysregulated in cancer and promote cancer cell survival. However, their role as potential targets in cancer therapy remains largely unexplored. In this study, we found OSW-1, a natural compound and OSBP inhibitor, potently and selectively kills colon cancer cells by activating a previously unknown necroptosis pathway that is independent of receptor-interacting protein 1 (RIP1) and RIP3. OSW-1 stabilizes p53 and degrades OSBPs to promote endoplasmic reticulum (ER) stress and glycogen synthase kinase 3β (GSK3β)/Tip60-mediated p53 acetylation at Lysine 120, which selectively induces its target PUMA. PUMA-mediated mitochondrial calcium influx activates calcium/calmodulin-dependent protein kinase IIδ (CamKIIδ) to promote mixed lineage kinase domain-like (MLKL) phosphorylation and necroptotic cell death. Furthermore, OSW-1-induced necroptosis is highly immunogenic and sensitizes syngeneic colorectal tumors to anti-PD-1 immunotherapy. Together, our results identified a novel RIP1/RIP3-independent necroptosis pathway underlying the extremely potent anticancer activity of OSW-1, which can be harnessed to develop new anticancer therapies by selectively stimulating antitumor immunity.

PMID:40329104 | DOI:10.1038/s41418-025-01521-8

Sci Rep. 2025 May 6;15(1):15789. doi: 10.1038/s41598-025-94171-2.

ABSTRACT

To translate, cross-culturally adapt, and evaluate the psychometric properties of the Cystic Fibrosis (CF) Stigma Scale. This exploratory methodological study involved the translation and cross-cultural adaptation using the translation, back-translation, review by experts committee, and pre-test steps. The psychometric properties were analyzed by applying the adapted instrument to a sample of 52 Brazilian individuals with CF over 18 years old. Moreover, the participants responded to the Short-Form 12-Item Survey - version 2 (SF-12v2), General Anxiety Disorder 7-item scale (GAD-7) and Cystic Fibrosis Quality of Life Questionnaire - Revised (CFQ-R). The content validity, test-retest reliability, and convergent validity were also assessed. The translation and cross-cultural adaptation obtained Cohen's kappa coefficients > 0.61 in the experts committee step and ranged between 0.48 and 0.72 in the pre-test. The Brazilian version of the CF Stigma Scale showed excellent psychometric properties, observed by the internal consistency (α = 0.836), mean correlation between items (0.3) and test-retest reliability (r = 0.886; p < 0.0001), and convergent validity (positive correlation with the anxiety scale and negative correlation with scores of overall and specific quality of life for CF). The Brazilian version of the CF Stigma Scale was accurately translated and cross-culturally adapted, with favorable psychometric properties for future studies involving the stigma experience in Brazilian individuals with CF over 18 years.

PMID:40328878 | DOI:10.1038/s41598-025-94171-2

J Cyst Fibros. 2025 May 5:S1569-1993(25)01463-8. doi: 10.1016/j.jcf.2025.04.008. Online ahead of print.

ABSTRACT

The introduction of cystic fibrosis transmembrane conductance regulator (CFTR) modulators has changed the landscape of therapy for persons with cystic fibrosis. However, the steep cost of targeted therapy poses significant financial burden for individuals and health systems. We aimed to determine the trends in Medicare and Medicaid spending on CFTR modulators between the years 2015 and 2022 through retrospective analysis of the Medicare and Medicaid claims data. The outcome measures included total dosage units prescribed, number of claims, spending per claim, and total spending on CFTR modulators for Medicare and Medicaid between 2015 to 2022. Average annual percentage changes (AAPC) were calculated for all outcome measures. Our results show that from 2015 to 2022, Medicaid consistently had higher total dosage units prescribed, number of claims, spending per claim, and overall spending on CFTR modulators compared to Medicare. Total spending for both Medicaid [AAPC 38.9, 95 % confidence interval [CI] 27.2-51.6, p < 0.01] and Medicare [AAPC 39.2, 95 % CI 30.2-55.1, p < 0.01] increased significantly during this period. Increases in CFTR spending was accelerated beginning in 2019, when the triple combination CFTR modulator therapy, elexacaftor/tezacaftor/ivacaftor, was introduced to the US market. This increase has been accompanied by a reduction in spending and use of other CFTR agents. This study evaluated the increases in spending for CFTR modulators over the years and the main drivers behind them, which may help inform future negotiations between healthcare systems and pharmaceutical companies, as well as policy makers and stakeholders.

PMID:40328584 | DOI:10.1016/j.jcf.2025.04.008

Klin Padiatr. 2025 May 6. doi: 10.1055/a-2551-2560. Online ahead of print.

NO ABSTRACT

PMID:40328282 | DOI:10.1055/a-2551-2560

Biomed Eng Online. 2025 May 6;24(1):53. doi: 10.1186/s12938-025-01388-3.

ABSTRACT

BACKGROUND: Accurate measurement of anterior segment parameters is crucial for diagnosing and managing ophthalmic conditions, such as glaucoma, cataracts, and refractive errors. However, traditional clinical measurement methods are often time-consuming, labor-intensive, and susceptible to inaccuracies. With the growing potential of artificial intelligence in ophthalmic diagnostics, this study aims to develop and evaluate a deep learning model capable of automatically extracting key points and precisely measuring multiple clinically significant anterior segment parameters from ultrasound biomicroscopy (UBM) images. These parameters include central corneal thickness (CCT), anterior chamber depth (ACD), pupil diameter (PD), angle-to-angle distance (ATA), sulcus-to-sulcus distance (STS), lens thickness (LT), and crystalline lens rise (CLR).

METHODS: A data set of 716 UBM anterior segment images was collected from Tianjin Medical University Eye Hospital. YOLOv8 was utilized to segment four key anatomical structures: cornea-sclera, anterior chamber, pupil, and iris-ciliary body-thereby enhancing the accuracy of keypoint localization. Only images with intact posterior capsule lentis were selected to create an effective data set for parameter measurement. Ten keypoints were localized across the data set, allowing the calculation of seven essential parameters. Control experiments were conducted to evaluate the impact of segmentation on measurement accuracy, with model predictions compared against clinical gold standards.

RESULTS: The segmentation model achieved a mean IoU of 0.8836 and mPA of 0.9795. Following segmentation, the binary classification model attained an mAP of 0.9719, with a precision of 0.9260 and a recall of 0.9615. Keypoint localization exhibited a Euclidean distance error of 58.73 ± 63.04 μm, improving from the pre-segmentation error of 71.57 ± 67.36 μm. Localization mAP was 0.9826, with a precision of 0.9699, a recall of 0.9642 and an FPS of 32.64. In addition, parameter error analysis and Bland-Altman plots demonstrated improved agreement with clinical gold standards after segmentation.

CONCLUSIONS: This deep learning approach for UBM image segmentation, keypoint localization, and parameter measurement is feasible, enhancing clinical diagnostic efficiency for anterior segment parameters.

PMID:40329288 | DOI:10.1186/s12938-025-01388-3

BMC Cancer. 2025 May 6;25(1):830. doi: 10.1186/s12885-025-14113-z.

ABSTRACT

Non-coding RNAs (ncRNAs) play a crucial role in breast cancer progression, necessitating advanced computational approaches for precise disease classification. This study introduces a Deep Reinforcement Learning (DRL)-based framework for predicting ncRNA-disease associations in metaplastic breast cancer (MBC) using a multi-dimensional descriptor system (ncRNADS) integrating 550 sequence-based features and 1,150 target gene descriptors (miRDB score ≥ 90). The model achieved 96.20% accuracy, 96.48% precision, 96.10% recall, and a 96.29% F1-score, outperforming traditional classifiers such as support vector machines (SVM) and neural networks. Feature selection and optimization reduced dimensionality by 42.5% (4,430 to 2,545 features) while maintaining high accuracy, demonstrating computational efficiency. External validation confirmed model specificity to breast cancer subtypes (87-96.5% accuracy) and minimal cross-reactivity with unrelated diseases like Alzheimer's (8-9% accuracy), ensuring robustness. SHAP analysis identified key sequence motifs (e.g., "UUG") and structural free energy (ΔG = - 12.3 kcal/mol) as critical predictors, validated by PCA (82% variance) and t-SNE clustering. Survival analysis using TCGA data revealed prognostic significance for MALAT1, HOTAIR, and NEAT1 (associated with poor survival, HR = 1.76-2.71) and GAS5 (protective effect, HR = 0.60). The DRL model demonstrated rapid training (0.08 s/epoch) and cloud deployment compatibility, underscoring its scalability for large-scale applications. These findings establish ncRNA-driven classification as a cornerstone for precision oncology, enabling patient stratification, survival prediction, and therapeutic target identification in MBC.

PMID:40329245 | DOI:10.1186/s12885-025-14113-z

J Imaging Inform Med. 2025 May 6. doi: 10.1007/s10278-025-01528-0. Online ahead of print.

ABSTRACT

Quantitative cardiovascular PET/CT imaging is useful in the diagnosis of multiple cardiac perfusion and motion pathologies. The common approach for cardiac segmentation consists in using co-registered CT images, exploiting publicly available deep learning (DL)-based segmentation models. However, the mismatch between structural CT images and PET uptake limits the usefulness of these approaches. Besides, the performance of DL models is not consistent over low-dose or ultra-low-dose CT images commonly used in clinical PET/CT imaging. In this work, we developed a DL-based methodology to tackle this issue by segmenting directly cardiac PET images. This study included 406 cardiac PET images from 146 patients (43 18F-FDG, 329 13N-NH3, and 37 82Rb images). Using previously trained DL nnU-Net models in our group, we segmented the whole heart and the three main cardiac components, namely the left myocardium (LM), left ventricle cavity (LV), and right ventricle (RV) on co-registered CT images. The segmentation was resampled to PET resolution and edited through a combination of automated image processing and manual correction. The corrected segmentation masks and SUV PET images were fed to a nnU-Net V2 pipeline to be trained in fivefold data split strategy by defining two tasks: task #1 for whole cardiac segmentation and task #2 for segmentation of three cardiac components. Fifteen cardiac images were used as external validation set. The DL delineated masks were compared with standard of reference masks using Dice coefficient, Jaccard distance, mean surface distance, and segment volume relative error (%). Task #1 average Dice coefficient in internal validation fivefold was 0.932 ± 0.033. The average Dice on the 15 external cases were comparable with the fivefold Dice reaching an average of 0.941 ± 0.018. Task #2 average Dice in fivefold validation was 0.88 ± 0.063, 0.828 ± 0.091, and 0.876 ± 0.062 for LM, LV, and RV, respectively. There was no statistically significant difference among the Dice coefficients, neither between images acquired by three radiotracers nor between the different folds (P-values > > 0.05). The overall average volume prediction error in cardiac components segmentation was less than 2%. We developed an automated DL-based segmentation pipeline to segment the whole heart and cardiac components with acceptable accuracy and robust performance in the external test set and over three radiotracers used in nuclear cardiovascular imaging. The proposed methodology can overcome unreliable segmentations performed on CT images.

PMID:40329157 | DOI:10.1007/s10278-025-01528-0

J Imaging Inform Med. 2025 May 6. doi: 10.1007/s10278-025-01527-1. Online ahead of print.

ABSTRACT

Deep learning techniques have demonstrated potential in various fields, including segmentation, and have recently been applied to medical image processing. This study aims to develop and evaluate computer-based diagnostic software designed to assess the segmentation of the mandibular condyle in ultrasound images. A total of 668 retrospective ultrasound images of anonymous adult mandibular condyles were analyzed. The CranioCatch labeling program (CranioCatch, Eskişehir, Turkey) was utilized to annotate the mandibular condyle using a polygonal labeling method. These annotations were subsequently reviewed and validated by experts in oral and maxillofacial radiology. In this study, all test images were detected and segmented using the YOLOv8 deep learning artificial intelligence (AI) model. When evaluating the model's performance in image estimation, it achieved an F1 score of 0.93, a sensitivity of 0.90, and a precision of 0.96. The automatic segmentation of the mandibular condyle from ultrasound images presents a promising application of artificial intelligence. This approach can help surgeons, radiologists, and other specialists save time in the diagnostic process.

PMID:40329156 | DOI:10.1007/s10278-025-01527-1

J Imaging Inform Med. 2025 May 6. doi: 10.1007/s10278-025-01525-3. Online ahead of print.

ABSTRACT

The purpose of this study is to assess the ability of deep learning models to classify different subtypes of solid renal parenchymal tumors using contrast-enhanced ultrasound (CEUS) images and to compare their classification performance. A retrospective study was conducted using CEUS images of 237 kidney tumors, including 46 angiomyolipomas (AML), 118 clear cell renal cell carcinomas (ccRCC), 48 papillary RCCs (pRCC), and 25 chromophobe RCCs (chRCC), collected from January 2017 to December 2019. Two deep learning models, based on the ResNet-18 and RepVGG architectures, were trained and validated to distinguish between these subtypes. The models' performance was assessed using sensitivity, specificity, positive predictive value, negative predictive value, F1 score, Matthews correlation coefficient, accuracy, area under the receiver operating characteristic curve (AUC), and confusion matrix analysis. Class activation mapping (CAM) was applied to visualize the specific regions that contributed to the models' predictions. The ResNet-18 and RepVGG-A0 models achieved an overall accuracy of 76.7% and 84.5% across all four subtypes. The AUCs for AML, ccRCC, pRCC, and chRCC were 0.832, 0.829, 0.806, and 0.795 for the ResNet-18 model, compared to 0.906, 0.911, 0.840, and 0.827 for the RepVGG-A0 model, respectively. The deep learning models could reliably differentiate between various histological subtypes of renal tumors using CEUS images in an objective and non-invasive manner.

PMID:40329155 | DOI:10.1007/s10278-025-01525-3

J Imaging Inform Med. 2025 May 6. doi: 10.1007/s10278-025-01465-y. Online ahead of print.

ABSTRACT

Breast cancer has remained one of the most frequent and life-threatening cancers in females globally, putting emphasis on better diagnostics in its early stages to solve the problem of therapy effectiveness and survival. This work enhances the assessment of breast cancer by employing progressive residual networks (PRN) and ResNet-50 within the framework of Progressive Residual Multi-Class Support Vector Machine-Net. Built on concepts of deep learning, this creative integration optimizes feature extraction and raises the bar for classification effectiveness, earning an almost perfect 99.63% on our tests. These findings indicate that PRMS-Net can serve as an efficient and reliable diagnostic tool for early breast cancer detection, aiding radiologists in improving diagnostic accuracy and reducing false positives. The separation of the data into different segments is possible to determine the architecture's reliability using the fivefold cross-validation approach. The total variability of precision, recall, and F1 scores clearly depicted in the box plot also endorse the competency of the model for marking proper sensitivity and specificity-highly required for combating false positive and false negative cases in real clinical practice. The evaluation of error distribution strengthens the model's rationale by giving validation of practical application in medical contexts of image processing. The high levels of feature extraction sensitivity together with highly sophisticated classification methods make PRMS-Net a powerful tool that can be used in improving the early detection of breast cancer and subsequent patient prognosis.

PMID:40329154 | DOI:10.1007/s10278-025-01465-y

Sci Rep. 2025 May 6;15(1):15773. doi: 10.1038/s41598-025-99694-2.

ABSTRACT

Passive localization is necessary for Internet of Things (IoT) applications to observe and follow people without requiring them to carry massive equipment. This is crucial in private settings like security and medical monitoring, where individuals are reluctant to wear tracking equipment. Localizing and tracking objects in these spaces are vital since wall loss causes GPS signals to perform poorly in indoor environments. Therefore, passive localization using Radio Tomography Images (RTI) has gained significant importance in present life. Because there are flaws in the RSSI data that models might exploit, previous problems with RTI sparked innovation and resulted in the development of more complex systems, such as a passive localization system that leverages deep learning. This paper employs a set of ESP32 nodes for a mesh network and utilizes a radio frequency sensor network with ESP32 modules to collect RSSI values. We have developed and thoroughly examined the working of radio tomography generation algorithms and present a deep learning approach using a convolutional neural network (CNN) to address the inverse problem. Two CNN models are developed to reconstruct static tomographic images, improve the quality of these images, and localize targeted objects. The targeted object localization accuracy is above 92% by using the proposed system. The results of the proposed system are also compared with previously developed approaches, and it is clearly shown that the proposed system outperforms the previously developed approaches.

PMID:40328896 | DOI:10.1038/s41598-025-99694-2

Sci Rep. 2025 May 6;15(1):15820. doi: 10.1038/s41598-025-96577-4.

ABSTRACT

Accurate high-resolution runoff predictions are essential for effective flood mitigation and water planning. In hydrology, conceptual models are preferred for their simplicity, despite their limited capacity for accurate predictions. Deep-learning applications have recently shown promise for runoff predictions; however, they usually require longer input data sequences, especially for high-temporal resolution simulations, thus leading to increased model complexity. To address these challenges, this study evaluates the robustness of two novel approaches using Long Short-Term Memory (LSTM) models. The first model integrates the outputs of a simple conceptual model with LSTM capabilities, while the second model is a stand-alone model that combines coarse and fine temporal inputs to capture both long and short dependencies. To ensure accuracy and reliability, we utilized a century-long meteorological dataset generated from a sophisticated physics-based model, eliminating any influence of measurement errors. The training phase employed multiple sub-periods ranging from 7- to 50-year, with a separate 50-year subset for validation. Our findings highlight the consistent improvement of both LSTM models with increasing training dataset lengths, while conceptual models show no notable enhancement beyond 15 years of training data. Both LSTM models demonstrate superior performance in capturing the reference flow duration curve, offering a promising pathway for more computationally efficient models for runoff predictions.

PMID:40328848 | DOI:10.1038/s41598-025-96577-4