Cell Rep. 2025 Mar 28;44(4):115476. doi: 10.1016/j.celrep.2025.115476. Online ahead of print.

ABSTRACT

The clustering of multiple transcription factor binding sites (TFBSs) for the same TF has proved to be a pervasive feature of cis-regulatory elements in the eukaryotic genome. However, the contribution of binding sites within the homotypic clusters of TFBSs (HCTs) to TF binding and target gene expression remains to be understood. Here, we characterize the CHD4 enhancers that harbor unique functional ZNF410 HCTs genome wide. We uncover that ZNF410 controls chromatin accessibility and activity of the CHD4 enhancer regions. We demonstrate that ZNF410 binds to the HCTs in a collaborative fashion, further conferring transcriptional activation. In particular, three ZNF410 motifs (sub-HCTs) located at 3' end of the distal enhancer act as "switch motifs" to control chromatin accessibility and enhancer activity. Mechanistically, the SWI/SNF complex is selectively required to mediate cooperative ZNF410 binding for CHD4 expression. Together, our findings expose a complex functional hierarchy of homotypic clustered motifs, which cooperate to fine-tune target gene expression.

PMID:40158221 | DOI:10.1016/j.celrep.2025.115476

J Hazard Mater. 2025 Mar 28;492:138044. doi: 10.1016/j.jhazmat.2025.138044. Online ahead of print.

ABSTRACT

Drug-induced osteotoxicity refers to the harmful effects certain pharmaceuticals have on the skeletal system, posing significant safety risks. These toxic effects are critical concerns in clinical practice, drug development, and environmental management. However, current toxicity assessment models lack specialized datasets and algorithms specifically designed to predict osteotoxicity In this study, we compiled a dataset of osteotoxic molecules and used clustering analysis to classify them into four distinct groups Furthermore, target prediction identified key genes (IL6, TNF, ESR1, and MAPK3), while GO and KEGG analyses were employed to explore the complex underlying mechanisms Additionally, we developed prediction models based on molecular fingerprints and descriptors. We further advanced our approach by incorporating models such as Transformer, SVM, XGBoost, and molecular graphs integrated with Weave GNN, ViT, and a pre-trained KPGT model. Specifically, the descriptor-based model achieved an accuracy of 0.82 and an AUC of 0.89; the molecular graph model reached an accuracy of 0.84 and an AUC of 0.86; and the KPGT model attained both an accuracy and an AUC of 0.86. These findings led to the creation of Bonetox, the first online platform specifically designed for predicting osteotoxicity. This tool aids in assessing the impact of hazardous substances on bone health during drug development, thereby improving safety protocols, mitigating skeletal side effects, and ultimately enhancing therapeutic outcomes and public safety.

PMID:40158503 | DOI:10.1016/j.jhazmat.2025.138044

Neurotherapeutics. 2025 Mar 28:e00576. doi: 10.1016/j.neurot.2025.e00576. Online ahead of print.

ABSTRACT

Glioblastoma (GB) is an incurable cancer of the brain, and there is an urgent need to identify effective treatments. This may be achieved by either identifying new molecules or through drug repurposing. To ascertain the therapeutic potential of known GSK-3β and/or PDE7 inhibitors in GB, a drug screening was conducted using a Drosophila melanogaster glioma model. VP3.15, a dual inhibitor with anti-inflammatory and neuroprotective roles in multiple sclerosis, was selected for further investigation. VP3.15 demonstrated robust anti-tumor efficacy against a panel of human and mouse GB cells; however, its capacity to inhibit orthotopic growth was only observed in a wild-type PTEN cell line. The in vivo dependence on PTEN was further suggested with the results in fly gliomas. The analysis of the VP3.15-treated tissues revealed a notable reduction in the number of myeloid cells and in the degree of vascularization. Mechanistic studies indicate that VP3.15 diminishes the production of GAL9, a key molecule that stimulates pro-angiogenic macrophages. Our findings substantiate the pro-tumoral function of GSK-3β, which might depend on the PTEN genetic status. Furthermore, we have delineated the therapeutic potential of VP3.15, which acts through the inhibition of the supportive role of the GB microenvironment. This molecule could be safely and effectively utilized after PTEN characterization in GB patients.

PMID:40157890 | DOI:10.1016/j.neurot.2025.e00576

Daru. 2025 Mar 29;33(1):17. doi: 10.1007/s40199-025-00560-3.

ABSTRACT

BACKGROUND: Mebendazole (MBZ) is an anthelmintic drug that was repurposed as an anti-cancer agent.

OBJECTIVES: This study aimed at formulating MBZ into stearylamine tailored spanlastics dispersed in nanogel for enhancing MBZ anti-tumor efficacy against skin cancer.

METHODS: MBZ spanlastics were prepared by thin film hydration using 21 × 31 factorial design. The formulation variables were the total amount (mg) of Span 60 and Tween 80 in the formulations and the ratio between Span 60 and Tween 80.

RESULTS: Optimal spanlastics formulation was composed of 400 mg of Span 60 and Tween 80 in a ratio of 2:1 and showed EE% of 78 ± 2.9% and PS of 284.00 ± 35.36 nm. Stearylamine (20 mg) was added to the optimized formulation and showed acceptable positive charge (zeta potential = 47.53 ± 1.50 mV). It was dispersed in 30% Tetronic®1107 solution to form a nanogel. MBZ nanogel was assessed for their cytotoxic effect on cell proliferation against human malignant melanoma and epidermoid carcinoma cell lines and showed 38.70 ± 1.70% and 48.60 ± 0.50% (respectively) cell proliferation compared to the control group (100%). Finally, its permeation through Wistar rat skin was tested.

CONCLUSION: SA-spanlastics nanogel holds potential as an effective nanocarrier for boosting MBZ anti-cancer efficacy.

PMID:40156679 | DOI:10.1007/s40199-025-00560-3

JMIR Serious Games. 2025 Mar 29. doi: 10.2196/66781. Online ahead of print.

ABSTRACT

BACKGROUND: The waste problem is a global issue all developed and developing countries face. Like many developing countries, Indonesia has inadequate infrastructure to process an extremely high volume of waste produced throughout the country and minimal public participation in proper waste management. Although the Indonesian government regulates Waste Bank as a community-based waste management solution, there is lack of integrated technological innovation to support Waste Bank. This study fills the gap by developing Circonomy, a model combining IoT, gamification, and semantic web technologies to advance community-based circular waste management.

OBJECTIVE: The proposed model Circonomy is inspired by the Waste Bank, the Indonesian Government's community-based waste management initiative. This research has objective to develop Circonomy as a circular waste model that integrate IoT-based smart-bin, semantic web, and gamification as an innovative technological solution.

METHODS: We identify the problem faced by the Indonesian Waste Bank from three locations in Jakarta and Yogyakarta as a basis for the Circonomy model and prototype development. The evaluation of the model focuses on Technical Performance and User Experience. The Technical Performance has three indicators, i.e., Bin Capacity Accuracy with a minimum of 80% precision, Bin Lid Response Time should be less than 5 seconds at a minimum of 80% of trials, and Data Transmission Success Rate at a minimum of 80%. While User Experience Metrics has two indicators, i.e., a minimum of 80% reported high usability and ease of use, and at least 80% of users feel more motivated using the prototype than the traditional Waste Bank. We select 10 random participants from ages 18 to 60 to perform User Experience evaluation on our prototype.

RESULTS: The Circonomy prototype demonstrates sound and stable performances related to Technical Performance and User Experience. Circonomy performs with at least 80% technical performance accuracy, comparable to industry standards. The accuracy problem lies in the placement of the ultrasonic sensor. The waste should be placed directly under the ultrasonic sensor to ensure the bin's capacity measurement accuracy. The User Experience testing results from 10 participants indicate that Circonomy has excellent user engagement, whereas 100% felt motivated by gamification, and 80% found the mobile application easy to use.

CONCLUSIONS: The testing result shows that Circonomy has acceptable performances for early-stage prototyping with at least 80% accuracy rate in technical performance and user experience. This ensures that Circonomy operates effectively in real-world conditions while remaining cost-efficient and scalable. For future development, Circonomy will prioritize enhancing the accuracy and reliability of sensor-based occupancy detection through improved sensor placement, multiple sensor integration, and exploring alternative technologies for regions with limited IT resources. In addition, more gamification features such as challenges and quiz should be added to improve the user experience and motivation.

PMID:40157387 | DOI:10.2196/66781

Parkinsonism Relat Disord. 2025 Mar 20:107804. doi: 10.1016/j.parkreldis.2025.107804. Online ahead of print.

NO ABSTRACT

PMID:40157818 | DOI:10.1016/j.parkreldis.2025.107804

Mol Cell Neurosci. 2025 Mar 27:104006. doi: 10.1016/j.mcn.2025.104006. Online ahead of print.

ABSTRACT

Hyperactivity of the hypothalamic-pituitary-adrenal (HPA) axis and oxidative stress represent important mechanisms that have been implicated in etiopathology of depression. Although first antidepressants were introduced in clinical practice more than six decades ago, approximately 30 % of patients with a diagnosis of depression show treatment resistance. A noncompetitive N-methyl-d-aspartate receptor antagonist ketamine has shown promising rapid antidepressant effects and has been approved for treatment-resistant depression (TRD). In the present study, we investigated antioxidant and antidepressant-like activity of a single subanesthetic dose of ketamine (10 mg/kg, ip) in a rodent model of TRD induced by adrenocorticotropic hormone (10 μg ACTH/day, sc, 21 days). Behavioral assessment was performed, and plasma biomarkers of oxidative stress and DNA damage in peripheral blood lymphocytes (PBLs) were determined. We observed that ACTH produced depressive-like behavior and significant increase in superoxide anion (O2·-), advanced oxidation protein products (AOPP), malondialdehyde (MDA) and total oxidant status (TOS) in male Wistar rats. This effect was accompanied by reduced activity of antioxidant enzymes - superoxide dismutase (SOD) and paraoxonase1 (PON1) in plasma and increase in DNA damage in PBLs. In the described model of TRD, we have demonstrated antidepressant effects of ketamine for the first time. Our results reveal that ketamine was effective in reducing O2.-, AOPP, MDA and TOS, while enhancing SOD and PON1 activity in ACTH-rats. Collectively, our study sheds light on molecular mechanisms implicated in antioxidant activity of ketamine, thus incentivizing further investigation of its effects on ROS metabolism and antioxidant defenses in clinical trials, particularly in depression.

PMID:40157469 | DOI:10.1016/j.mcn.2025.104006

Nucleic Acids Res. 2025 Mar 20;53(6):gkaf216. doi: 10.1093/nar/gkaf216.

ABSTRACT

Premature termination codon (PTC) diseases account for ∼12% of all human disease mutations. Although there are no FDA approved treatments for increasing PTC readthrough, one readthrough inducing drug, ataluren, has conditional approval for treatment of Duchenne muscular dystrophy elsewhere. Ataluren displays low toxicity in clinical trials for treatment of PTC diseases, but its therapeutic effects are inconsistent. The messenger RNA (mRNA) sequence context of a PTC is a major determinant of PTC readthrough efficiency. We have shown that ataluren stimulates readthrough exclusively by competitively inhibiting release factor complex (RFC) catalysis of translation termination. Here, using an in vitro reconstituted system, we demonstrate that PTC identity and the immediately adjacent mRNA sequence contexts modulate RFC activity in terminating peptide elongation. Such modulation largely determines the effectiveness of ataluren in stimulating readthrough, whether added alone or in combination with either the aminoglycoside G418 or an anticodon edited aa-tRNA, which stimulate readthrough by mechanisms orthogonal to that of ataluren. Our results suggest a potential rationale for the variability of ataluren effectiveness in stimulating readthrough. We hypothesize that patients harboring a PTC mutation within a sequence context promoting strong interaction with RFC will be resistant to ataluren, but that ataluren treatment will be more effective for patient sequences conferring weaker interaction with RFC.

PMID:40156864 | DOI:10.1093/nar/gkaf216

BMC Oral Health. 2025 Mar 29;25(1):455. doi: 10.1186/s12903-025-05803-y.

ABSTRACT

BACKGROUND: While artificial intelligence-driven approaches have shown great promise in dental diagnosis and treatment planning, most research focuses on dental radiographs. Only three studies have explored automated tooth numbering in oral photographs, all focusing on permanent dentition. Our study aimed to introduce an automated system for detection and numbering of teeth across mixed and permanent dentitions in occlusal photographs.

METHODS: A total of 3215 occlusal view images of maxilla and mandible were included. Five senior dental students, trained under the guidance of an associate professor in dental public health, annotated the dataset. Samples were distributed across the training, validation, and test sets using a ratio of 7:1.5:1.5, respectively. We employed two separate convolutional neural network (CNN) models working in conjunction. The first model detected tooth presence and position, generating bounding boxes, while the second model localized these boxes, conducted classification, and assigned tooth numbers. Python and YOLOv8 were utilized in model development. Overall performance was assessed using sensitivity, precision, and F1 score.

RESULTS: The model demonstrated a sensitivity of 99.89% and an overall precision of 95.72% across all tooth types, with an F1 score of 97.76%. Misclassifications were primarily observed in underrepresented teeth, including primary incisors and permanent third molars. Among primary teeth, maxillary molars showed the highest performance, with precisions above 94%, 100% sensitivities, and F1 scores exceeding 97%. The mandibular primary canine showed the lowest results, with a precision of 88.52% and an F1 score of 93.91%.

CONCLUSION: Our study advances dental diagnostics by developing a highly precise artificial intelligence model for detecting and numbering primary and permanent teeth on occlusal photographs. The model's performance, highlights its potential for real-world applications, including tele-dentistry and epidemiological studies in underserved areas. The model could be integrated with other systems to identify dental problems such as caries and orthodontic issues.

PMID:40158107 | DOI:10.1186/s12903-025-05803-y

BMC Med Genomics. 2025 Mar 29;18(1):58. doi: 10.1186/s12920-025-02131-6.

ABSTRACT

N6-methyladenine (6 mA) is a pivotal DNA modification that plays a crucial role in epigenetic regulation, gene expression, and various biological processes. With advancements in sequencing technologies and computational biology, there is an increasing focus on developing accurate methods for 6 mA site identification to enhance early detection and understand its biological significance. Despite the rapid progress of machine learning in bioinformatics, accurately detecting 6 mA sites remains a challenge due to the limited generalizability and efficiency of existing approaches. In this study, we present Deep-N6mA, a novel Deep Neural Network (DNN) model incorporating optimal hybrid features for precise 6 mA site identification. The proposed framework captures complex patterns from DNA sequences through a comprehensive feature extraction process, leveraging k-mer, Dinucleotide-based Cross Covariance (DCC), Trinucleotide-based Auto Covariance (TAC), Pseudo Single Nucleotide Composition (PseSNC), Pseudo Dinucleotide Composition (PseDNC), and Pseudo Trinucleotide Composition (PseTNC). To optimize computational efficiency and eliminate irrelevant or noisy features, an unsupervised Principal Component Analysis (PCA) algorithm is employed, ensuring the selection of the most informative features. A multilayer DNN serves as the classification algorithm to identify N6-methyladenine sites accurately. The robustness and generalizability of Deep-N6mA were rigorously validated using fivefold cross-validation on two benchmark datasets. Experimental results reveal that Deep-N6mA achieves an average accuracy of 97.70% on the F. vesca dataset and 95.75% on the R. chinensis dataset, outperforming existing methods by 4.12% and 4.55%, respectively. These findings underscore the effectiveness of Deep-N6mA as a reliable tool for early 6 mA site detection, contributing to epigenetic research and advancing the field of computational biology.

PMID:40158097 | DOI:10.1186/s12920-025-02131-6

Sci Rep. 2025 Mar 29;15(1):10902. doi: 10.1038/s41598-025-95596-5.

ABSTRACT

Underwater object detection (UOD) is essential in maritime environmental study and underwater species protection. The development of associated technology holds real-world importance. While current object recognition methods have attained an outstanding performance on terrestrial, they are less suitable in underwater conditions because of dual restrictions: the underwater objects are generally smaller, closely spread, and disposed to obstruction features, and underwater embedding tools have temporary storing and computation abilities. Image-based UOD has progressed fast recently, in addition to deep learning (DL) applications and development in computer vision (CV). Investigators utilize DL models to identify possible objects inside an image. Convolutional neural network (CNN) is the major technique of DL, which enhances the learning qualities. In this manuscript, an Underwater Object Detection and Classification Utilizing the Ensemble Deep Learning Approach and Hybrid Optimization Algorithms (UODC-EDLHOA) technique is developed. The UODC-EDLHOA technique mainly detects and classifies underwater objects using advanced DL and hyperparameter models. Initially, the UODC-EDLHOA model involved several levels of pre-processing and noise removal to improve the clearness of the underwater images. The backbone of EfficientNetB7, which has an attention mechanism, is employed for feature extraction. Furthermore, the YOLOv9-based object detection is utilized. For underwater object detection, an ensemble of three techniques, namely deep neural network (DNN), deep belief network (DBN), and long short-term memory (LSTM), is implemented. Finally, the hyperparameter selection uses the hybrid Siberian tiger and sand cat swarm optimization (STSC) methods. Extensive experimentation is conducted on the UOD dataset to illustrate the robust classification performance of the UODC-EDLHOA model. The performance validation of the UODC-EDLHOA model portrayed a superior accuracy value of 92.78% over existing techniques.

PMID:40158003 | DOI:10.1038/s41598-025-95596-5

Sci Rep. 2025 Mar 30;15(1):10942. doi: 10.1038/s41598-025-94799-0.

ABSTRACT

PURPOSE: The goal of this study was to evaluate the outpatient workflow efficiency of an optimized facility (OF) compared to an established reference facility (RF) for abdominal magnetic resonance imaging (MRI).

METHODS: In this retrospective study, we analyzed 2,723 contrast-enhanced liver and prostate MRI examinations conducted between March 2022 and April 2024. All examinations were performed on 3T scanners (MAGNETOM Vida, Siemens Healthineers) at two different imaging facilities within our institution. The optimized facility featured a three-bay setup, with each bay consisting of one magnet, two dockable tables, and one dedicated preparation room, while the reference facility utilized a single scanner-single table setup with one dedicated preparation room. Workflow metrics were extracted from scanner logs and electronic health records. Three-way ANOVA and chi-square tests were used to assess the impact of facility design, body region, and date on workflow metrics.

RESULTS: The OF significantly reduced mean table turnaround times (4.6 min vs. 8.3 min, p < 0.001) and achieved shorter total process cycle times for both liver (30.6 min vs. 32.7 min, p < 0.01) and prostate exams (32.5 min vs. 36.4 min, p < 0.001) compared to the RF. Additionally, the OF achieved turnaround times of ≤ 1 min in 37.2% of exams, compared to just 0.6% at the RF (p < 0.001). On-time performance was also notably higher at the OF (79.4% vs. 66.0%, p < 0.001). Furthermore, the mean time from patient arrival to exam start was reduced by 9 min at the OF (p < 0.001). Minor differences in acquisition times were observed between facilities, with both benefiting from deep learning reconstruction techniques.

CONCLUSION: The optimized MRI facility demonstrated superior outpatient workflow efficiency compared to an already efficient reference facility, particularly in table turnover time, resulting in increased patient throughput for abdominal MRI examinations. These findings highlight that even highly efficient MRI facilities can significantly benefit from comprehensive redesign strategies.

PMID:40157988 | DOI:10.1038/s41598-025-94799-0

Sci Rep. 2025 Mar 29;15(1):10926. doi: 10.1038/s41598-025-88958-6.

ABSTRACT

Defect recognition is crucial in steel production and quality control, but performing this detection task accurately presents significant challenges. ConvNeXt, a model based on self-attention mechanism, has shown excellent performance in image classification tasks. To further enhance ConvNeXt's ability to classify defects on steel surfaces, we propose a network architecture called ESG-ConvNeXt. First, in the image processing stage, we introduce a serial multi-attention mechanism approach. This method fully leverages the extracted information and improves image information retention by combining the strengths of each module. Second, we design a parallel multi-scale residual module to adaptively extract diverse discriminative features from the input image, thereby enhancing the model's feature extraction capability. Finally, in the downsampling stage, we incorporate a PReLU activation function to mitigate the problem of neuron death during downsampling. We conducted extensive experiments using the NEU-CLS-64 steel surface defect dataset, and the results demonstrate that our model outperforms other methods in terms of detection performance, achieving an average recognition accuracy of 97.5%. Through ablation experiments, we validated the effectiveness of each module; through visualization experiments, our model exhibited strong classification capability. Additionally, experiments on the X-SDD dataset confirm that the ESG-ConvNeXt network achieves solid classification results. Therefore, the proposed ESG-ConvNeXt network shows great potential in steel surface defect classification.

PMID:40157949 | DOI:10.1038/s41598-025-88958-6

Acad Radiol. 2025 Mar 28:S1076-6332(25)00187-4. doi: 10.1016/j.acra.2025.02.043. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: Ultrasound (US)-based deep learning (DL) models for grading the severity of carpal tunnel syndrome (CTS) are scarce. We aimed to advance CTS grading by developing a joint-DL model integrating clinical information and multimodal US features.

MATERIALS AND METHODS: A retrospective dataset of CTS patients from three hospitals was randomly divided into the training (n=680) and internal validation (n=173) sets. An external validation set was prospectively recruited from another hospital (n=174). To further test the model's generalizability, cross-vendor testing was conducted at three additional hospitals utilizing different US systems in the external validation set 2 (n=224). An US-based model was developed to grade CTS severity utilizing multimodal sonographic features, including cross-sectional area [CSA], echogenicity, longitudinal nerve appearance, and intraneural vascularity. A joint-DL model (CTSGrader) was constructed integrating sonographic features and clinical information. Diagnostic performance of both models was verified based on electrophysiological results. In the validation sets, the better-performing model was compared to two junior and two senior radiologists. Additionally, the radiologists' diagnostic performance with artificial intelligence (AI) assistance was evaluated in external validation sets.

RESULTS: CTSGrader achieved areas under the curve (AUCs) of 0.951, 0.910, and 0.897 in the validation sets. The accuracies of CTSGrader were 0.849, 0.833, and 0.827, which were higher than those of US-based model (all p<.05). It outperformed two junior and one senior radiologists (all p<.05) and was equivalent to 1 senior radiologist (all p>.05). With its assistance, the accuracies of two junior and one senior radiologists were improved (all p<.05).

CONCLUSION: The joint-DL model (CTSGrader) developed in our study outperformed the single-modality model. The AI-aided strategy suggested its potential to support clinical decision-making for grading CTS severity.

PMID:40157849 | DOI:10.1016/j.acra.2025.02.043

Spine J. 2025 Mar 27:S1529-9430(25)00165-2. doi: 10.1016/j.spinee.2025.03.011. Online ahead of print.

ABSTRACT

BACKGROUND CONTEXT: Lumbar foraminal stenosis (LFS) is a common spinal condition that requires accurate assessment. Current magnetic resonance imaging (MRI) reporting processes are often inefficient, and while deep learning has potential for improvement, challenges in generalization and interpretability limit its diagnostic effectiveness compared to physician expertise.

PURPOSE: The present study aimed to leverage a multimodal large language model to improve the accuracy and efficiency of LFS image classification, thereby enabling rapid and precise automated diagnosis, reducing the dependence on manually annotated data, and enhancing diagnostic efficiency.

STUDY DESIGN/SETTING: Retrospective study conducted from April 2017 to March 2023.

PATIENT SAMPLE: Sagittal T1-weighted MRI data for the lumbar spine were collected from 1,200 patients across three medical centers. A total of 810 patient cases were included in the final analysis, with data collected from seven different MRI devices.

OUTCOME MEASURES: Automated classification of LFS using the multi modal large language model. Accuracy, sensitivity, Specificity and Cohen's Kappa coefficient were calculated.

METHODS: An advanced multimodal fusion framework GPT4LFS was developed with the primary objective of integrating imaging data and natural language descriptions to comprehensively capture the complex LFS features. The model employed a pre-trained ConvNeXt as the image processing module for extracting high-dimensional imaging features. Concurrently, medical descriptive texts generated by the multimodal large language model GPT-4o and encoded and feature-extracted using RoBERTa were utilized to optimize the model's contextual understanding capabilities. The Mamba architecture was implemented during the feature fusion stage, effectively integrating imaging and textual features and thereby enhancing the performance of the classification task. Finally, the stability of the model's detection results was validated by evaluating classification task metrics, such as the accuracy, sensitivity, specificity, and Kappa coefficients.

RESULTS: The training set comprised 6,299 images from 635 patients, the internal test set included 820 images from 82 patients, and the external test set was composed of 930 images from 93 patients. The GPT4LFS model demonstrated an overall accuracy of 93.7%, sensitivity of 95.8%, and specificity of 94.5% in the internal test set (Kappa = 0.89,95% confidence interval (CI): 0.84-0.96, p<.001). In the external test set, the overall accuracy was 92.2%, with a sensitivity of 92.2% and a specificity of 97.4% (Kappa = 0.88, 95% CI: 0.84-0.89, p<.001). Both the internal and external test sets showed excellent consistency in the model. After the article is published, we will make the full code publicly available on GitHub.

CONCLUSIONS: Using the GPT4LFS model for LFS image categorization demonstrated accuracy and the capacity for feature description at a level commensurate with that of professional clinicians.

PMID:40157428 | DOI:10.1016/j.spinee.2025.03.011

Eur Heart J. 2025 Mar 30:ehaf073. doi: 10.1093/eurheartj/ehaf073. Online ahead of print.

ABSTRACT

BACKGROUND AND AIMS: Accurate near-term prediction of life-threatening ventricular arrhythmias would enable pre-emptive actions to prevent sudden cardiac arrest/death. A deep learning-enabled single-lead ambulatory electrocardiogram (ECG) may identify an ECG profile of individuals at imminent risk of sustained ventricular tachycardia (VT).

METHODS: This retrospective study included 247 254, 14 day ambulatory ECG recordings from six countries. The first 24 h were used to identify patients likely to experience sustained VT occurrence (primary outcome) in the subsequent 13 days using a deep learning-based model. The development set consisted of 183 177 recordings. Performance was evaluated using internal (n = 43 580) and external (n = 20 497) validation data sets. Saliency mapping visualized features influencing the model's risk predictions.

RESULTS: Among all recordings, 1104 (.5%) had sustained ventricular arrhythmias. In both the internal and external validation sets, the model achieved an area under the receiver operating characteristic curve of .957 [95% confidence interval (CI) .943-.971] and .948 (95% CI .926-.967). For a specificity fixed at 97.0%, the sensitivity reached 70.6% and 66.1% in the internal and external validation sets, respectively. The model accurately predicted future VT occurrence of recordings with rapid sustained VT (≥180 b.p.m.) in 80.7% and 81.1%, respectively, and 90.0% of VT that degenerated into ventricular fibrillation. Saliency maps suggested the role of premature ventricular complex burden and early depolarization time as predictors for VT.

CONCLUSIONS: A novel deep learning model utilizing dynamic single-lead ambulatory ECGs accurately identifies patients at near-term risk of ventricular arrhythmias. It also uncovers an early depolarization pattern as a potential determinant of ventricular arrhythmias events.

PMID:40157386 | DOI:10.1093/eurheartj/ehaf073

Comput Biol Med. 2025 Mar 28;190:110019. doi: 10.1016/j.compbiomed.2025.110019. Online ahead of print.

ABSTRACT

Communication involves exchanging information between individuals or groups through various media sources. However, limitations such as hearing loss can make it difficult for some individuals to understand the information delivered during speech communication. Conventional methods, including sign language, written text, and manual lipreading, offer some solutions; however, emerging software-based tools using artificial intelligence (AI) are introducing more effective approaches. Many approaches rely on AI to improve communication quality, with the current trend of leveraging deep learning being a particularly effective tool. This paper presents a comprehensive Systematic Literature Review (SLR) of research trends in automatic lipreading technologies, a critical field in enhancing communication among individuals with hearing impairments. The SLR, which followed the Preferred Reporting Items for Systematic Literature Review and Meta-Analysis (PRISMA) protocol, identified 114 original research articles published between 2014 and mid-2024. The essential information from these articles was summarized, including the trends in automatic lipreading research, dataset availability, task categories, existing approaches, and architectures for automatic lipreading systems. The results showed that various techniques and advanced deep learning models achieved convincing performance to become state-of-the-art in automatic lipreading tasks. However, several challenges, such as insufficient data quantity, inadequate environmental conditions, and language diversity, must be resolved in the future. Furthermore, many improvements have been made to the deep learning models to overcome these challenges and become a massive solution, particularly for automatic lipreading tasks in the near future.

PMID:40157316 | DOI:10.1016/j.compbiomed.2025.110019

Comput Biol Med. 2025 Mar 28;190:110048. doi: 10.1016/j.compbiomed.2025.110048. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Accurate medical tumor segmentation is critical for early diagnosis and treatment planning, significantly improving patient outcomes. This study aims to enhance liver and tumor segmentation from CT and liver images by developing a novel model, ResTransUNet, which combines convolutional and transformer blocks to improve segmentation accuracy.

METHODS: The proposed ResTransUNet model is a custom implementation inspired by the TransUNet architecture, featuring a Standalone Transformer Block and ResNet50 as the backbone for the encoder. The hybrid architecture leverages the strengths of Convolutional Neural Networks (CNNs) and Transformer blocks to capture both local features and global context effectively. The encoder utilizes a pre-trained ResNet50 to extract rich hierarchical features, with key feature maps to preserved it as skip connections. The Standalone Transformer Block, integrated into the model, employs multi-head attention mechanisms to capture long-range dependencies across the image, enhancing segmentation performance in complex cases. The decoder reconstructs the segmentation mask by progressively upsampling encoded features while integrating skip connections, ensuring both semantic information and spatial details are retained. This process culminates in a precise binary segmentation mask that effectively distinguishes liver and tumor regions.

RESULTS: The ResTransUNet model achieved superior Dice Similarity Coefficient (DSC) for liver segmentation (98.3% on LiTS and 98.4% on 3D-IRCADb-01) and for tumor segmentation from CT images (94.7% on LiTS and 89.8% on 3D-IRCADb-01) as well as from liver images (94.6% on LiTS and 91.1% on 3D-IRCADb-01). The model also demonstrated high precision, sensitivity, and specificity, outperforming current state-of-the-art methods in these tasks.

CONCLUSIONS: The ResTransUNet model demonstrates robust and accurate performance in complex medical image segmentation tasks, particularly in liver and tumor segmentation. These findings suggest that ResTransUNet has significant potential for improving the precision of surgical interventions and therapy planning in clinical settings.

PMID:40157314 | DOI:10.1016/j.compbiomed.2025.110048

Commun Eng. 2025 Mar 29;4(1):59. doi: 10.1038/s44172-025-00399-1.

NO ABSTRACT

PMID:40158063 | DOI:10.1038/s44172-025-00399-1

Sci Rep. 2025 Mar 29;15(1):10897. doi: 10.1038/s41598-025-95633-3.

ABSTRACT

Lung cancer is the leading cause of cancer-related deaths globally, with radiotherapy as a key treatment modality for inoperable cases. Lactate, once considered a by-product of anaerobic cellular metabolism, is now considered critical for cancer progression. Lactate dehydrogenase B (LDHB) converts lactate to pyruvate and supports mitochondrial metabolism. In this study, a re-analysis of our previous transcriptomic data revealed that LDHB silencing in the NSCLC cell lines A549 and H358 dysregulated 1789 genes, including gene sets associated with cell cycle and DNA repair pathways. LDHB silencing increased H2AX phosphorylation, a surrogate marker of DNA damage, and induced cell cycle arrest at the G1/S or G2/M checkpoint depending on the p53 status. Long-term LDHB silencing sensitized A549 cells to radiotherapy, resulting in increased DNA damage and genomic instability as evidenced by increased H2AX phosphorylation levels and micronuclei accumulation, respectively. The combination of LDHB silencing and radiotherapy increased protein levels of the senescence marker p21, accompanied by increased phosphorylation of Chk2, suggesting persistent DNA damage. Metabolomics analysis revealed that LDHB silencing decreased nucleotide metabolism, particularly purine and pyrimidine biosynthesis, in tumor xenografts. Nucleotide supplementation partially attenuated DNA damage caused by combined LDHB silencing and radiotherapy. These findings suggest that LDHB supports metabolic homeostasis and DNA damage repair in NSCLC, while its silencing enhances the effects of radiotherapy by impairing nucleotide metabolism and promoting persistent DNA damage.

PMID:40158058 | DOI:10.1038/s41598-025-95633-3