PLoS One. 2025 May 30;20(5):e0322488. doi: 10.1371/journal.pone.0322488. eCollection 2025.

ABSTRACT

Lung cancer imaging plays a crucial role in early diagnosis and treatment, where machine learning and deep learning have significantly advanced the accuracy and efficiency of disease classification. This study introduces the Explainable and Lightweight Lung Cancer Net (XLLC-Net), a streamlined convolutional neural network designed for classifying lung cancer from histopathological images. Using the LC25000 dataset, which includes three lung cancer classes and two colon cancer classes, we focused solely on the three lung cancer classes for this study. XLLC-Net effectively discerns complex disease patterns within these classes. The model consists of four convolutional layers and contains merely 3 million parameters, considerably reducing its computational footprint compared to existing deep learning models. This compact architecture facilitates efficient training, completing each epoch in just 60 seconds. Remarkably, XLLC-Net achieves a classification accuracy of 99.62% [Formula: see text] 0.16%, with precision, recall, and F1 score of 99.33% [Formula: see text] 0.30%, 99.67% [Formula: see text] 0.30%, and 99.70% [Formula: see text] 0.30%, respectively. Furthermore, the integration of Explainable AI techniques, such as Saliency Map and GRAD-CAM, enhances the interpretability of the model, offering clear visual insights into its decision-making process. Our results underscore the potential of lightweight DL models in medical imaging, providing high accuracy and rapid training while ensuring model transparency and reliability.

PMID:40445896 | DOI:10.1371/journal.pone.0322488

IEEE Trans Biomed Eng. 2025 May 30;PP. doi: 10.1109/TBME.2025.3575252. Online ahead of print.

ABSTRACT

OBJECTIVE: Myoelectric prostheses offer great promise in enabling amputees to perform daily activities independently. However, existing neural interfaces generally cannot simultaneously and proportionally decode kinematics and kinetics in real time, nor can they directly interpret neural commands. We thus propose a novel framework that integrates motor unit activity with deep learning and demonstrate its efficiency in the real-time, simultaneous, and proportional estimation of wrist angles and grasp forces.

METHODS: This framework utilizes real-time high-density surface electromyography decomposition to identify motor neuron discharges, followed by neural drive computation integrated with a modular Long Short-Term Memory-based neural network. Ten subjects participated in the experiments involving wrist pronation/supination, flexion/extension, and abduction/adduction, with varying grasp force.

RESULTS: The proposed framework significantly outperformed five baseline methods, achieving an nRMSE of 13.6% and 11.1% and an R2 of 73.2% and 76.8% for wrist angle and grasp force, respectively. In addition, we further characterized the spatial distribution and recruitment patterns of motor units during movement generation.

CONCLUSION: These findings highlight the feasibility of integrating neural drive insights with deep learning methods to improve simultaneous and proportional estimation performance.

SIGNIFICANCE: The proposed framework has the potential to enhance the independence and quality of life of prosthetic users by enabling them to perform a wider range of tasks with improved precision and control over both kinematics and kinetics.

PMID:40445821 | DOI:10.1109/TBME.2025.3575252

IEEE Trans Biomed Eng. 2025 May 30;PP. doi: 10.1109/TBME.2025.3575268. Online ahead of print.

ABSTRACT

OBJECTIVE: We present the first multimodal deep learning framework combining ultrasound (US) and electrocardiography (ECG) data to predict cardiac quiescent periods (QPs) for optimized computed tomography angiography gating (CTA).

METHODS: The framework integrates a 3D convolutional neural network (CNN) for US data and an artificial neural network (ANN) for ECG data. A dynamic heart motion phantom, replicating diverse cardiac conditions, including arrhythmias, was used to validate the framework. Performance was assessed across varying QP lengths, cardiac segments, and motions to simulate real-world conditions.

RESULTS: The multimodal US-ECG 3D CNN-ANN framework demonstrated improved QP prediction accuracy compared to single-modality ECG-only gating, achieving 96.87% accuracy compared to 85.56%, including scenarios involving arrhythmic conditions. Notably, the framework shows higher accuracy for longer QP durations (100 ms - 200 ms) compared to shorter durations (<100ms), while still outperforming single-modality methods, which often fail to detect shorter quiescent phases, especially in arrhythmic cases. Consistently outperforming single-modality approaches, it achieves reliable QP prediction across cardiac regions, including the whole phantom, interventricular septum, and cardiac wall regions. Analysis of QP prediction accuracy across cardiac segments demonstrated an average accuracy of 92% in clinically relevant echocardiographic views, highlighting the framework's robustness.

CONCLUSION: Combining US and ECG data using a multimodal framework improves QP prediction accuracy under variable cardiac motion, particularly in arrhythmic conditions.

SIGNIFICANCE: Since even small errors in cardiac CTA can result in non-diagnostic scans, the potential benefits of multimodal gating may improve diagnostic scan rates in patients with high and variable heart rates and arrhythmias.

PMID:40445820 | DOI:10.1109/TBME.2025.3575268

PLoS One. 2025 May 30;20(5):e0323784. doi: 10.1371/journal.pone.0323784. eCollection 2025.

ABSTRACT

BACKGROUND: This study evaluated the role of blood Krebs von den Lungen-6 (KL-6) in predicting acute exacerbation (AE) in patients with idiopathic pulmonary fibrosis (IPF).

METHODS: From April 2018 to March 2023, clinical data of 233 IPF patients with baseline and follow-up KL-6 values at Haeundae Paik Hospital were retrospectively analyzed. AE was defined following the criteria proposed by Collard et al. in 2016.

RESULTS: The mean age was 71.8 years; 79% were male. During follow-up (median: 18.7 months), 33 (14.2%) patients experienced AE. Throughout the entire period from baseline, KL-6 values were higher in the AE group compared to the non-AE group (P < 0.001), and the patterns of change over time also showed significant differences between both groups (P < 0.001). The KL-6 values in the post-exacerbation phase were higher than those in the pre-exacerbation phase among the AE group (P = 0.004). The AE group showed lower 1-year (86.4% vs. 95.9%) and 3-year (50.2% vs. 91.4%) survival rates compared to the non-AE group (P < 0.001). The occurrence of AE (hazard ratio (HR) 74.09, 95% confidence interval (CI) 31.97-171.7, P < 0.001) and higher lactate dehydrogenase (HR 1.02, 95% CI: 1.01-1.02, P < 0.001) were independently associated with mortality in patients with IPF.

CONCLUSIONS: Our data suggest that the trend in changes in KL-6 values may be utilized as a tool for predicting AE-IPF. Further research is needed to establish the clinical significance of changes in KL-6 for predicting AE-IPF and to validate the cut-off values for prediction.

PMID:40446067 | DOI:10.1371/journal.pone.0323784

Adv Sci (Weinh). 2025 May 30:e01956. doi: 10.1002/advs.202501956. Online ahead of print.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a prototype of chronic, progressive, and fibrotic lung disease. While advancing age is recognized as the most significant risk factor for both the development and mortality associated with pulmonary fibrosis, precise mechanisms underlying this association remain elusive. Here, Nephronectin (NPNT) is identified as an antiaging molecule, a potential major regulator of the progression of pulmonary fibrosis. In IPF patients, a marked reduction in NPNT expression is detected in lung tissues, which correlated with a decline in lung function. The study reveals that NPNT deficiency exacerbates bleomycin-induced senescence in alveolar epithelial cells, potentially intensifying fibrosis severity due to diminishes extracellular matrix turnover. Conversely, NPNT overexpression in the alveolar epithelium improves lung respiratory function and enhances resistance to aging and fibrosis. Mechanistically, NPNT inhibits the hyperactivation of LATS1 and MOB1, facilitates YAP1 nuclear translocation, and suppresses YAP1 ubiquitination and degradation, contingent upon the interaction between NPNT and ITGA3. Notably, pharmacological elevation of NPNT protein levels using Escin has been shown to alleviate pulmonary fibrosis and improve lung function in mice. The findings shed light on the key mechanism underlying stress-induced senescence and fibrosis, and offer a promising framework for interventions targeting aging-related diseases.

PMID:40444575 | DOI:10.1002/advs.202501956

PLoS Genet. 2025 May 30;21(5):e1011492. doi: 10.1371/journal.pgen.1011492. Online ahead of print.

ABSTRACT

Genome-wide association studies (GWAS) have identified many quantitative trait loci (QTL) associated with complex traits, predominantly in non-coding regions, posing challenges in pinpointing the causal variants and their target genes. Three types of evidence can help identify the gene through which QTL acts: (1) proximity to the most significant GWAS variant, (2) correlation of gene expression with the trait, and (3) the gene's physiological role in the trait. However, there is still uncertainty about the success of these methods in identifying the correct genes. Here, we test the ability of these methods in a comparatively simple series of traits associated with the concentration of polar lipids in milk. We conducted single-trait GWAS for ~14 million imputed variants and 56 individual milk polar lipid (PL) phenotypes in 336 cows. A multi-trait meta-analysis of GWAS identified 10,063 significant SNPs at FDR ≤ 10% (P ≤ 7.15E-5). Transcriptome data from blood (~12.5K genes, 143 cows) and mammary tissue (~12.2K genes, 169 cows) were analyzed using the genetic score omics regression (GSOR) method. This method links observed gene expression to genetically predicted phenotypes and was used to find associations between gene expression and 56 PL phenotypes. GSOR identified 2,186 genes in blood and 1,404 in mammary tissue associated with at least one PL phenotype (FDR ≤ 1%). We partitioned the genome into non-overlapping windows of 100 Kb to test for overlap between GSOR-identified genes and GWAS signals. We found a significant overlap between these two datasets, indicating that GSOR-significant genes were more likely to be located within 100 Kb windows that include GWAS signals than those that do not (P = 0.01; odds ratio = 1.47). These windows included 70 significant genes expressed in mammary tissue and 95 in blood. Compared to all expressed genes in each tissue, these genes were enriched for lipid metabolism gene ontology (GO). That is, seven of the 70 significant mammary transcriptome genes (P < 0.01; odds ratio = 3.98) and five of the 95 significant blood genes (P < 0.10; odds ratio = 2.24) were involved in lipid metabolism GO. The candidate causal genes include DGAT1, ACSM5, SERINC5, ABHD3, CYP2U1, PIGL, ARV1, SMPD5, and NPC2, with some overlap between the two tissues. The overlap between GWAS, GSOR, and GO analyses suggests that together, these methods are more likely to identify genes mediating QTL, though their power remains limited, as reflected by modest odds ratios. Larger sample sizes would enhance the power of these analyses, but issues like linkage disequilibrium would remain.

PMID:40446200 | DOI:10.1371/journal.pgen.1011492

Development. 2025 May 30:dev.204606. doi: 10.1242/dev.204606. Online ahead of print.

ABSTRACT

Self-organization, such as the emergence of a pattern from a homogenous state, is a fascinating property of biological systems. Early limb bud outgrowth and patterning in mice are controlled by a robust and self-regulatory signaling system, and initiation of the periodic digit-interdigit pattern appears under control of a self-regulatory Turing system. Previous studies established the requirement of WNT and BMP signaling for both early limb bud and digit-interdigit morphogenesis, but the molecular changes underlying the transition from early limb bud signaling to the digit-interdigit patterning system remained unknown. Here, we use small molecule inhibitors to rapidly but transiently block WNT signaling to identify the early transcriptional targets that are altered during disruption and recovery of limb bud and digit development. Together, this study highlights the overarching role of WNT signaling in controlling early limb bud outgrowth and patterning, and establishment of the periodic digit-interdigit pattern. Finally, the transient WNT signaling disruption approach reveals the plasticity and robustness of these self-organizing limb bud and digit patterning systems.

PMID:40446196 | DOI:10.1242/dev.204606

Sci Adv. 2025 May 30;11(22):eadu1864. doi: 10.1126/sciadv.adu1864. Epub 2025 May 30.

ABSTRACT

H3K9 methylation, a conserved heterochromatin marker, is crucial for chromosome segregation and gene regulation. Clr4 is the sole known methyltransferase catalyzing H3K9 methylation in Schizosaccharomyces pombe. Clr4 K455/K472 automethylation and H3K14 ubiquitination (H3K14Ub) are vital activators of Clr4, ensuring appropriate heterochromatin deposition and preventing deleterious silencing. While automethylation's activation mechanism is uncovered, the mechanism of H3K14Ub's significantly stronger stimulation on Clr4 remains unclear. Here, we determined the crystal structures of Clr4 bound to ubiquitinated and unmodified H3 peptides at 2.60 and 2.39 angstrom, which revealed a synergistic mechanism underlying the pronounced stimulatory effect: H3K14Ub increases substrate affinity through multivalent interactions and facilitates the allosteric transition of Clr4 from an inactive apo conformation to a hyperactive "catalyzing state," including conformational changes in the αC-SET-insertion region, autoregulatory loop, and the β9/10 loop. We finally propose a multilevel structural model for the Clr4 catalytic-regulatory cycle. This work provides structural insights into the interplay between histone modifications and their collective impact on epigenetic regulation.

PMID:40446033 | DOI:10.1126/sciadv.adu1864

Adv Sci (Weinh). 2025 May 30:e01956. doi: 10.1002/advs.202501956. Online ahead of print.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a prototype of chronic, progressive, and fibrotic lung disease. While advancing age is recognized as the most significant risk factor for both the development and mortality associated with pulmonary fibrosis, precise mechanisms underlying this association remain elusive. Here, Nephronectin (NPNT) is identified as an antiaging molecule, a potential major regulator of the progression of pulmonary fibrosis. In IPF patients, a marked reduction in NPNT expression is detected in lung tissues, which correlated with a decline in lung function. The study reveals that NPNT deficiency exacerbates bleomycin-induced senescence in alveolar epithelial cells, potentially intensifying fibrosis severity due to diminishes extracellular matrix turnover. Conversely, NPNT overexpression in the alveolar epithelium improves lung respiratory function and enhances resistance to aging and fibrosis. Mechanistically, NPNT inhibits the hyperactivation of LATS1 and MOB1, facilitates YAP1 nuclear translocation, and suppresses YAP1 ubiquitination and degradation, contingent upon the interaction between NPNT and ITGA3. Notably, pharmacological elevation of NPNT protein levels using Escin has been shown to alleviate pulmonary fibrosis and improve lung function in mice. The findings shed light on the key mechanism underlying stress-induced senescence and fibrosis, and offer a promising framework for interventions targeting aging-related diseases.

PMID:40444575 | DOI:10.1002/advs.202501956

Front Pharmacol. 2025 May 13;16:1599297. doi: 10.3389/fphar.2025.1599297. eCollection 2025.

ABSTRACT

Major depressive disorder (MDD) is a serious neuropsychiatric condition that affects millions of people worldwide, causing significant psychological distress and lifestyle deterioration. The serotonin transporter, which plays a critical role in regulating the uptake of serotonin (5-HT) back into presynaptic cells, is a primary target for antidepressants. Though selective serotonin reuptake inhibitors (SSRIs) are still the pharmacologic treatment of choice, alternative methods remain in demand to enhance the efficacy of treatment and offer more therapeutic options. Drug repurposing provides an efficient solution to speed up antidepressant research because it identifies existing FDA-approved medications that might inhibit the serotonin transporter. A virtual screening method was integrated into the study that examined 3620 FDA-approved drugs to discover new repurposed serotonin transporter-inhibiting molecules. The binding affinity, structural stability, and inhibitory potential were assessed using molecular docking and molecular dynamics (MD) simulations. Among the screened compounds, Flunarizine, a well-known calcium channel blocker, emerged as a promising serotonin transporter inhibitor due to its strong and stable binding configuration within the transporter's active site. Detailed molecular docking studies revealed that Flunarizine formed key interactions with critical residues of the serotonin transporter, suggesting its potential as an effective modulator. Subsequent 500-nanosecond MD simulations further confirmed the stability of the serotonin transporter-Flunarizine complex, demonstrating minimal structural deviations and maintaining crucial dynamic properties throughout the simulation trajectory. These findings highlight Flunarizine's potential for repurposing as a novel therapeutic agent targeting serotonin transport modulation. The study provides a solid foundation for further preclinical and clinical investigations into the antidepressant repurposing of Flunarizine.

PMID:40444039 | PMC:PMC12120357 | DOI:10.3389/fphar.2025.1599297

Arch Clin Biomed Res. 2025;9(3):183-195. Epub 2025 May 5.

ABSTRACT

Antidepressants are widely prescribed for major depressive disorder and anxiety, yet their long-term use is associated with weight gain, affecting up to 55-65% of patients. This adverse effect contributes to treatment discontinuation, relapse, and worsened metabolic health outcomes, including increased risk for obesity and type 2 diabetes. This artic le presents a critical evaluation of the published reports on the mechanisms underlying antidepressant-induced weight gain, comparative effects across drug classes, and mitigation strategies. Weight gain varies significantly by antidepressant class. Tricyclic antidepressants, monoamine oxidase inhibitors, and a tetracyclic antidepressant, mirtazapine, are associated with the most substantial weight increases, while selective serotonin reuptake inhibitors typically induce weight gain after prolonged use. Mechanisms involve serotonergic and dopaminergic signaling, receptor desensitization, insulin resistance, and altered leptin and ghrelin levels. Genetic factors, including CYP2C19 metabolizer status, and lifestyle factors such as baseline body mass index and diet, further influence risk. Bupropion, a norepinephrine-dopamine reuptake inhibitor, is the only commonly prescribed antidepressant consistently associated with weight loss or neutrality. Mitigation strategies include switching medications, adding agents like metformin or GLP-1 receptor agonists, and incorporating behavioral interventions. Antidepressant-induced weight gain is a multifactorial issue requiring individualized management. Understanding pharmacologic mechanisms and patient-specific risk factors is essential for optimizing treatment efficacy while minimizing metabolic burden.

PMID:40444017 | PMC:PMC12121960

Expert Opin Drug Metab Toxicol. 2025 May 29. doi: 10.1080/17425255.2025.2510302. Online ahead of print.

ABSTRACT

INTRODUCTION: Dravet syndrome (DS) and Lennox-Gastaut syndrome (LGS) are rare, severe epileptic encephalopathies requiring complex, individualized treatment due to drug-resistant seizures, non-seizure outcomes, and comorbidities. Polytherapy is an inevitable aspect of managing these conditions, making the management of drug-drug interactions (DDIs) crucial for optimizing efficacy, minimizing toxicity, and addressing broader patient needs.

AREAS COVERED: This review discusses current and emerging pharmacological therapies for seizures in DS and LGS. We explore documented and theoretical DDIs between these drugs and other antiseizure medications (ASMs), focusing on pharmacokinetic and pharmacodynamic characteristics. The clinical significance of these DDIs is emphasized, with practical recommendations for their management.

EXPERT OPINION: Advances in understanding DDIs are key to optimizing treatment, particularly through the combination of ASMs with distinct mechanisms of action. A rational therapeutic approach should consider not only seizure control but also comorbidities. Understanding metabolic pathways involved in pharmacokinetic interactions is essential for predicting and avoiding adverse effects. Digital tools and decision-support apps can assist clinicians in quickly assessing DDIs and selecting the most effective drug combinations. Ongoing research in pharmacogenetics and personalized medicine holds promise for improving the management of complex conditions like DS and LGS, offering potential for better, individualized therapeutic strategies.

PMID:40443019 | DOI:10.1080/17425255.2025.2510302

Clin Transl Sci. 2025 Jun;18(6):e70220. doi: 10.1111/cts.70220.

ABSTRACT

Leukopenia is a common dose-dependent side effect of azathioprine, often leading to drug discontinuation. Variants in TPMT and NUDT15 are associated with azathioprine-induced leukopenia but only explain 25% of cases. Thus, we aimed to identify novel genetic risk factors among TPMT and NUDT15 normal metabolizers through a genome-wide association study (GWAS). Using BioVU, Vanderbilt's electronic health record linked to genetic data, we assembled a discovery cohort of new users of azathioprine. The analysis was conducted in 1184 new users of azathioprine who had no history of prior thiopurine use or an organ transplant. A replication cohort of 521 patients was derived from All of Us, an NIH-funded project that links healthcare data and genetics. The GWAS was adjusted for sex, age, indication (inflammatory bowel disease, systemic lupus erythematosus, other autoimmune condition, or unknown), concurrent use of xanthine oxidase inhibitors (allopurinol or febuxostat) or immunosuppressants, prior TPMT or NUDT15 testing, and 10 principal components of ancestry. In BioVU, 65% of patients were female with a median age of 44 [IQR: 30, 57] and 125 patients developed leukopenia. In All of Us, 69% were female with a median age of 51 [36, 61], and 44 patients developed leukopenia. An intronic variant in PTPN2, rs11664064, reached genome-wide significance in BioVU (OR = 3.61; p = 1.96E-8) and replicated in All of Us (OR = 2.42, p = 0.039). Our finding suggests an association between rs11664064 in PTPN2 and azathioprine-induced leukopenia. PTPN2 plays a role in immune cell development and differentiation, providing a plausible mechanism for this association.

PMID:40442974 | DOI:10.1111/cts.70220

Lin Chuang Er Bi Yan Hou Tou Jing Wai Ke Za Zhi. 2025 Jun;39(6):590-596. doi: 10.13201/j.issn.2096-7993.2025.06.017.

ABSTRACT

One of the main pathological features of airway inflammatory diseases is hypersecretion of airway mucus, which is manifested by goblet cell hyperplasia and mucociliary clearance dysfunction. In recent years, it has been found that the molecular structure of calcium activated chloride ion channels, transmenbrane protein 16A（TMEM16A）, is closely related to airway mucus hypersecretion.TMEM16A not only mediates ion transepithelial transport and hydration, but also participates in the regulation of mucin secretion. TMEM16A is highly expressed in airway epithelium of a variety of inflammatory diseases of upper and lower airway, such as asthma, cystic fibrosis, allergic rhinitis, chronic sinusitis and so on. Understanding the expression level and regulation mechanism of TMEM16A in different airway diseases and revealing its physiological function and pathological mechanism is critical for targeted disease treatment. This paper summarizes the research status of the discovery process, structural characteristics and regulatory mechanism of TMEM16A, and then summarizes the expression level of TMEM16A in asthma, cystic fibrosis, allergic rhinitis and chronic sinusitis ant related pathological mechanisms, clarifies the potential value of TMEM16A as a therapeutic target for the above four diseases, in order to guide treatment of airway inflammatory diseases.

PMID:40443386 | DOI:10.13201/j.issn.2096-7993.2025.06.017

Q J Nucl Med Mol Imaging. 2025 May 30. doi: 10.23736/S1824-4785.25.03640-4. Online ahead of print.

ABSTRACT

INTRODUCTION: This systematic review investigates the potential of artificial intelligence (AI) in improving the accuracy and efficiency of prostate-specific membrane antigen positron emission tomography (PSMA PET) scans for detecting metastatic prostate cancer.

EVIDENCE ACQUISITION: A comprehensive literature search was conducted across Medline, Embase, and Web of Science, adhering to PRISMA guidelines. Key search terms included "artificial intelligence," "machine learning," "deep learning," "prostate cancer," and "PSMA PET." The PICO framework guided the selection of studies focusing on AI's application in evaluating PSMA PET scans for staging lymph node and distant metastasis in prostate cancer patients. Inclusion criteria prioritized original English-language articles published up to October 2024, excluding studies using non-PSMA radiotracers, those analyzing only the CT component of PSMA PET-CT, studies focusing solely on intra-prostatic lesions, and non-original research articles.

EVIDENCE SYNTHESIS: The review included 22 studies, with a mix of prospective and retrospective designs. AI algorithms employed included machine learning (ML), deep learning (DL), and convolutional neural networks (CNNs). The studies explored various applications of AI, including improving diagnostic accuracy, sensitivity, differentiation from benign lesions, standardization of reporting, and predicting treatment response. Results showed high sensitivity (62% to 97%) and accuracy (AUC up to 98%) in detecting metastatic disease, but also significant variability in positive predictive value (39.2% to 66.8%).

CONCLUSIONS: AI demonstrates significant promise in enhancing PSMA PET scan analysis for metastatic prostate cancer, offering improved efficiency and potentially better diagnostic accuracy. However, the variability in performance and the "black box" nature of some algorithms highlight the need for larger prospective studies, improved model interpretability, and the continued involvement of experienced nuclear medicine physicians in interpreting AI-assisted results. AI should be considered a valuable adjunct, not a replacement, for expert clinical judgment.

PMID:40444499 | DOI:10.23736/S1824-4785.25.03640-4

Phys Med Biol. 2025 May 29. doi: 10.1088/1361-6560/addea5. Online ahead of print.

ABSTRACT

OBJECTIVE: High-dose-rate (HDR) brachytherapy is integral to the standard-of-care for locally advanced cervical cancer (LACC). Currently, selection of brachytherapy applicators relies on physician's clinical experience, which can lead to variability in treatment quality and outcomes. This study presents a deep learning-based decision-support tool for selecting between interstitial Syed applicators and intracavitary tandem & ovoids applicators.

APPROACH: The network architecture consists of six 3D convolutional-pooling-ReLU blocks, followed by a fully connected block. The input to the network includes three channels: a 3D contour mask of clinical target volume (CTV), organs at risk (OAR), and central tandem, and two 3D distance maps of CTV and OAR voxels relative to the tandem's central axis. The network outputs a probability score, indicating the suitability of Syed applicators. Binary cross-entropy loss combined with L1 regularization was used for network training.

MAIN RESULTS: A retrospective study was performed on 184 LACC patients with 422 instances of applicator insertion. The data was divided into three sets: Dataset-1 of 163 patients with 372 insertions for training and hyperparameter tuning, Dataset-2 of 17 patients with 36 insertions and Dataset-3 of four complex cases with 14 insertions for testing. Five-fold cross-validation was performed on Dataset-1, during which hyperparameters were heuristically tuned to optimize classification accuracy across the folds. The highest average accuracy was 92.1 ± 3.8%. Using the hyperparameters that resulted in this highest accuracy, the final model was then trained on the full Dataset-1, and evaluated on the other two independent datasets, achieving 96.0% accuracy, 90.9% sensitivity, and 97.4% specificity.

SIGNIFICANCE: These results demonstrate the potential of our model as a quality assurance tool in LACC HDR brachytherapy, providing feedback on physicians' applicator choice and supporting continuous improvement in decision-making. Future work will focus on collecting more data for further validation and extending its application for prospective applicator selection.

PMID:40444332 | DOI:10.1088/1361-6560/addea5

Comput Diffus MRI. 2025;15171:119-131. doi: 10.1007/978-3-031-86920-4_11. Epub 2025 Apr 18.

ABSTRACT

We propose an image-conditioned diffusion model to estimate high angular resolution diffusion weighted imaging (DWI) from a low angular resolution acquisition. Our model, which we call QID2, takes as input a set of low angular resolution DWI data and uses this information to estimate the DWI data associated with a target gradient direction. We leverage a U-Net architecture with cross-attention to preserve the positional information of the reference images, further guiding the target image generation. We train and evaluate QID2 on single-shell DWI samples curated from the Human Connectome Project (HCP) dataset. Specifically, we sub-sample the HCP gradient directions to produce low angular resolution DWI data and train QID2 to reconstruct the missing high angular resolution samples. We compare QID2 with two state-of-the-art GAN models. Our results demonstrate that QID2 not only achieves higher-quality generated images, but it consistently outperforms state-of-the-art baseline methods in downstream tensor estimation across multiple metrics and in generalizing to downsampling scenario during testing. Taken together, this study highlights the potential of diffusion models, and QID2 in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications.

PMID:40444168 | PMC:PMC12122016 | DOI:10.1007/978-3-031-86920-4_11

J Med Imaging (Bellingham). 2025 Sep;12(5):051805. doi: 10.1117/1.JMI.12.5.051805. Epub 2025 May 28.

ABSTRACT

PURPOSE: The accurate assessment of computed tomography (CT) image quality is crucial for ensuring diagnostic reliability while minimizing radiation dose. Radiologists' evaluations are time-consuming and labor-intensive. Existing automated approaches often require large CT datasets with predefined image quality assessment (IQA) scores, which often do not align well with clinical evaluations. We aim to develop a reference-free, automated method for CT IQA that closely reflects radiologists' evaluations, reducing the dependency on large annotated datasets.

APPROACH: We propose Task-Focused Knowledge Transfer (TFKT), a deep learning-based IQA method leveraging knowledge transfer from task-similar natural image datasets. TFKT incorporates a hybrid convolutional neural network-transformer model, enabling accurate quality predictions by learning from natural image distortions with human-annotated mean opinion scores. The model is pre-trained on natural image datasets and fine-tuned on low-dose computed tomography perceptual image quality assessment data to ensure task-specific adaptability.

RESULTS: Extensive evaluations demonstrate that the proposed TFKT method effectively predicts IQA scores aligned with radiologists' assessments on in-domain datasets and generalizes well to out-of-domain clinical pediatric CT exams. The model achieves robust performance without requiring high-dose reference images. Our model is capable of assessing the quality of ∼ 30 CT image slices in a second.

CONCLUSIONS: The proposed TFKT approach provides a scalable, accurate, and reference-free solution for CT IQA. The model bridges the gap between traditional and deep learning-based IQA, offering clinically relevant and computationally efficient assessments applicable to real-world clinical settings.

PMID:40444137 | PMC:PMC12116730 | DOI:10.1117/1.JMI.12.5.051805

J Biomed Opt. 2025 Dec;30(Suppl 3):S34102. doi: 10.1117/1.JBO.30.S3.S34102. Epub 2025 May 28.

ABSTRACT

SIGNIFICANCE: Molecular photoacoustic (PA) imaging with exogenous dyes faces a significant challenge due to the photobleaching of the dye that can compromise tissue visualization, particularly in 3D imaging. Addressing this limitation can revolutionize the field by enabling safer, more reliable imaging and improve real-time visualization, quantitative analysis, and clinical decision-making in various molecular PA imaging applications such as image-guided surgeries.

AIM: We tackle photobleaching in molecular PA imaging by introducing a platform-flexible deep learning framework that enhances SNR from single-laser pulse data, preserving contrast and signal integrity without requiring averaging of signals from multiple laser pulses.

APPROACH: The generative deep learning network was trained with an LED-illuminated PA image dataset and tested on acoustic resolution PA microscopy images obtained with single-laser pulse illumination. In vitro and ex vivo samples were first tested for demonstrating SNR improvement, and then, a 3D-scanning experiment with an ICG-filled tube was conducted to depict the usability of the technique in reducing the impact of photobleaching during PA imaging.

RESULTS: Our generative deep learning model outperformed traditional nonlearning, filter-based algorithms and the U-Net deep learning network when tested with in vitro and ex vivo single pulse-illuminated images, showing superior performance in terms of signal-to-noise ratio ( 93.54 ± 6.07 , and 92.77 ± 10.74 compared with 86.35 ± 3.97 , and 84.52 ± 11.82 with U-Net for kidney, and tumor, respectively) and contrast-to-noise ratio ( 11.82 ± 4.42 , and 9.9 ± 4.41 compared with 7.59 ± 0.82 , and 6.82 ± 2.12 with U-Net for kidney, and tumor respectively). The use of cGAN with single-pulse rapid imaging has the potential to prevent photobleaching ( 9.51 ± 3.69 % with cGAN, and 35.14 ± 5.38 % with long-time laser exposure by averaging 30 pulses), enabling accurate, quantitative imaging suitable for real-time implementation, and improved clinical decision support.

CONCLUSIONS: We demonstrate the potential of a platform-flexible generative deep learning-based approach to mitigate the effects of photobleaching in PA imaging by enhancing signal-to-noise ratio from single pulse-illuminated data, thereby improving image quality and preserving contrast in real time.

PMID:40443946 | PMC:PMC12118878 | DOI:10.1117/1.JBO.30.S3.S34102

Front Psychol. 2025 May 15;16:1578457. doi: 10.3389/fpsyg.2025.1578457. eCollection 2025.

ABSTRACT

INTRODUCTION: The use of information and communication technologies such as the Internet, smartphones, social media, and gaming has gained significant popularity in recent years. While the benefits are immense and ICTs have become essential in people's daily lives, the inappropriate use of these technologies has led to addiction, causing negative consequences in family, academic, and work environments.

METHODS: This study analyzes existing research related to ICT addiction (Internet, smartphone, social media, and gaming), reviewing relevant contributions. Historical trends, regions, relevance, factors, and instruments were analyzed to map out the existing research on ICT addiction.

RESULTS AND DISCUSSION: The findings revealed that although the number of relevant studies has grown in recent years, there is still a lack of attention on ICT addiction and its relationship with psychological factors, social factors, physical factors, phenomenological experiences, and treatment/prevention approaches. In this regard, psychology scholars should consider appropriate methods to raise awareness about ICT addiction and emphasize the need for an in-depth understanding of the meaning, context, and practices associated with Internet, smartphone, social media, and gaming addiction.

PMID:40443730 | PMC:PMC12120558 | DOI:10.3389/fpsyg.2025.1578457