J Transl Med. 2025 May 26;23(1):586. doi: 10.1186/s12967-025-06609-w.

ABSTRACT

BACKGROUND: Approximately 60% of rare disease cases remain unsolved after exome and genome sequencing (ES/GS). Blood RNA sequencing (RNA-seq) complements DNA-level diagnosis by revealing the functional impact of variants on gene expression and splicing, but to what extent RNA-driven approaches offer diagnostic benefits across different scenarios-with and without pre-existing candidate variants-remains uncertain.

METHODS: 128 unrelated probands with suspected Mendelian disorders who had previously undergone ES/GS were recruited. A validation cohort (n = 7, with variants expected to alter RNA) and a test cohort (n = 121, including 10 with variants of uncertain significance (VUS) and 111 with no previously identified candidate variants) were analyzed. Blood RNA-seq was performed, and aberrant splicing (AS) and aberrant expression (AE) were detected using the DROP pipeline. SpliceAI predictions were compared with RNA-seq results for splicing-related VUS variants, and pathogenicity was re-evaluated. AS/AE outliers were evaluated for diagnostic potential in cases without candidate variants. The feasibility of an RNA-driven approach was assessed by ranking causal variant-associated aberrant events.

RESULTS: The pipeline correctly identified all expected AS/AE events in the validation cohort. In the test cohort with candidate VUS, RNA-seq provided a 60% (6/10) diagnostic uplift. Notably, SpliceAI predictions matched RNA-seq observations perfectly only in 40% of these VUS. A 2.7% (3/111) diagnostic uplift was achieved in the test cohort with no prior candidates. Overall, target AS and AE events ranked among the top eight in 14 of the 16 diagnosed cases using a purely RNA-driven approach; however, two cases would have been missed without prior candidate identification from DNA sequencing.

CONCLUSION: Blood RNA-seq is highly effective in refining the interpretation of splicing VUS, frequently leading to reclassification and diagnosis. Meanwhile, RNA-driven identification of causal variants shows a more modest yield in cases without prior candidates. This study supports an RNA-complementary approach as the preferred strategy for clinical utility.

PMID:40420094 | DOI:10.1186/s12967-025-06609-w

BMC Med Imaging. 2025 May 26;25(1):183. doi: 10.1186/s12880-025-01709-x.

ABSTRACT

BACKGROUND: Microcephaly and macrocephaly, which are abnormal congenital markers, are associated with developmental and neurologic deficits. Hence, there is a medically imperative need to conduct ultrasound imaging early on. However, resource-limited countries such as Ethiopia are confronted with inadequacies such that access to trained personnel and diagnostic machines inhibits the exact and continuous diagnosis from being met.

OBJECTIVE: This study aims to develop a fetal head abnormality detection model from ultrasound images via deep learning.

METHODS: Data were collected from three Ethiopian healthcare facilities to increase model generalizability. The recruitment period for this study started on November 9, 2024, and ended on November 30, 2024. Several preprocessing techniques have been performed, such as augmentation, noise reduction, and normalization. SegNet, UNet, FCN, MobileNetV2, and EfficientNet-B0 were applied to segment and measure fetal head structures using ultrasound images. The measurements were classified as microcephaly, macrocephaly, or normal using WHO guidelines for gestational age, and then the model performance was compared with that of existing industry experts. The metrics used for evaluation included accuracy, precision, recall, the F1 score, and the Dice coefficient.

RESULTS: This study was able to demonstrate the feasibility of using SegNet for automatic segmentation, measurement of abnormalities of the fetal head, and classification of macrocephaly and microcephaly, with an accuracy of 98% and a Dice coefficient of 0.97. Compared with industry experts, the model achieved accuracies of 92.5% and 91.2% for the BPD and HC measurements, respectively.

CONCLUSION: Deep learning models can enhance prenatal diagnosis workflows, especially in resource-constrained settings. Future work needs to be done on optimizing model performance, trying complex models, and expanding datasets to improve generalizability. If these technologies are adopted, they can be used in prenatal care delivery.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40419983 | DOI:10.1186/s12880-025-01709-x

BMC Med Imaging. 2025 May 26;25(1):186. doi: 10.1186/s12880-025-01740-y.

ABSTRACT

BACKGROUND: Structural remodeling of the left atrial appendage (LAA) is characteristic of atrial fibrillation (AF), and LAA morphology impacts radiofrequency catheter ablation (RFCA) outcomes. In this study, we aimed to develop and validate a predictive model for AF ablation outcomes using LAA morphological features, deep learning (DL) radiomics, and clinical variables.

METHODS: In this multicenter retrospective study, 480 consecutive patients who underwent RFCA for AF at three tertiary hospitals between January 2016 and December 2022 were analyzed, with follow-up through December 2023. Preprocedural CT angiography (CTA) images and laboratory data were systematically collected. LAA segmentation was performed using an nnUNet-based model, followed by radiomic feature extraction. Cox proportional hazard regression analysis assessed the relationship between AF recurrence and LAA volume. The dataset was randomly split into training (70%) and validation (30%) cohorts using stratified sampling. An AF recurrence prediction model integrating LAA DL radiomics with clinical variables was developed.

RESULTS: The cohort had a median follow-up of 22 months (IQR 15-32), with 103 patients (21.5%) experiencing AF recurrence. The nnUNet segmentation model achieved a Dice coefficient of 0.89. Multivariate analysis showed that LAA volume was associated with a 5.8% increase in hazard risk per unit increase (aHR 1.058, 95% CI 1.021-1.095; p = 0.002). The model combining LAA DL radiomics with clinical variables demonstrated an AUC of 0.92 (95% CI 0.87-0.96) in the test set, maintaining robust predictive performance across subgroups.

CONCLUSION: LAA morphology and volume are strongly linked to AF RFCA outcomes. We developed an LAA segmentation network and a predictive model that combines DL radiomics and clinical variables to estimate the probability of AF recurrence.

PMID:40419973 | DOI:10.1186/s12880-025-01740-y

NPJ Digit Med. 2025 May 27;8(1):312. doi: 10.1038/s41746-025-01624-z.

ABSTRACT

This is a multi-institutional study to evaluate a head-and-neck CT auto-segmentation software across seven institutions globally. 11 lymph node levels and 7 organs-at-risk contours were evaluated in a two-phase study design. Time savings were measured in both phases, and the inter-observer variability across the seven institutions was quantified in phase two. Overall time savings were found to be 42% in phase one and 49% in phase two. Lymph node levels IA, IB, III, IVA, and IVB showed no significant time savings, with some centers reporting longer editing times than manual delineation. All the edited ROIs showed reduced inter-observer variability compared to manual segmentation. Our study shows that auto-segmentation plays a crucial role in harmonizing contouring practices globally. However, the clinical benefits of auto-segmentation software vary significantly across ROIs and between clinics. To maximize its potential, institution-specific commissioning is required to optimize the clinical benefits.

PMID:40419731 | DOI:10.1038/s41746-025-01624-z

Sci Rep. 2025 May 26;15(1):18429. doi: 10.1038/s41598-025-98801-7.

ABSTRACT

This study aims to predict the optimal imaging parameters using a deep learning algorithm in 3D heads-up vitreoretinal surgery and assess its effectiveness on improving the vitreoretinal surface visibility during surgery. To develop the deep learning algorithm, we utilized 212 manually-optimized still images extracted from epiretinal membrane (ERM) surgical videos. These images were applied to a two-stage Generative Adversarial Network (GAN) and Convolutional Neural Network (CNN) architecture. The algorithm's performance was evaluated based on the peak signal-to-noise ratio (PSNR) and structural similarity index map (SSIM), and the degree of surgical image enhancement by the algorithm was evaluated based on sharpness, brightness, and contrast values. A survey was conducted to evaluate the intraoperative suitability of optimized images. For an in-vitro experiment, 121 anonymized high-resolution ERM fundus images were optimized using a 3D display based on the algorithm. The PSNR and SSIM values are 34.59 ± 5.34 and 0.88 ± 0.08, respectively. The algorithm enhances the sharpness, brightness and contrast values of the surgical images. In the in-vitro experiment, both the ERM size and color contrast ratio increased significantly in the optimized fundus images. Both surgical and fundus images are digitally enhanced using a deep learning algorithm. Digital image enhancement using this algorithm can be potentially applied to 3D heads-up vitreoretinal surgeries.

PMID:40419711 | DOI:10.1038/s41598-025-98801-7

Microb Pathog. 2025 May 24:107724. doi: 10.1016/j.micpath.2025.107724. Online ahead of print.

ABSTRACT

The pandemic of COVID-19 has ignited a global race to locate effective therapies with drug repositioning emerging as a leading strategy due to its cost-effectiveness and established safety profiles. Remdesivir, Favipiravir, Hydroxychloroquine, and Chloroquine have been the focus of rigorous clinical trials to determine their therapeutic potential against SARS-CoV-2. This article delves into the innovative synthetic strategies behind these drugs, providing a blueprint for researchers navigating the complex landscape of antiviral development. Beyond synthesis, we explore the fascinating mechanisms of action: hydroxychloroquine and chloroquine elevate lysosomal pH to impede autophagy and viral replication; favipiravir, a nucleoside analogue, induces lethal mutagenesis or RNA chain termination and remdesivir disrupts viral RNA synthesis through delayed chain termination. By merging synthetic methodologies with mechanistic insights, this article offers a comprehensive resource aimed at accelerating the development of potent COVID-19 therapies and underscores the crucial part that chemistry in addressing global health emergencies. It also underscores the vital function of chemistry in addressing global health emergencies and highlights how innovative drug design and repurposing can provide rapid responses to emerging infectious diseases. This fusion of chemistry and virology not only advances our understanding of drug action but also paves the way for the discovery of new therapeutic agents crucial in future pandemics.

PMID:40419200 | DOI:10.1016/j.micpath.2025.107724

Plant Methods. 2025 May 26;21(1):70. doi: 10.1186/s13007-025-01387-4.

ABSTRACT

Despite the significant progress in deep learning-based object detection, existing models struggle to perform optimally in complex agricultural environments. To address these challenges, this study introduces YOLO-Pepper, an enhanced model designed specifically for greenhouse pepper disease and pest detection, overcoming three key obstacles: small target recognition, multi-scale feature extraction under occlusion, and real-time processing demands. Built upon YOLOv10n, YOLO-Pepper incorporates four major innovations: (1) an Adaptive Multi-Scale Feature Extraction (AMSFE) module that improves feature capture through multi-branch convolutions; (2) a Dynamic Feature Pyramid Network (DFPN) enabling context-aware feature fusion; (3) a specialized Small Detection Head (SDH) tailored for minute targets; and (4) an Inner-CIoU loss function that enhances localization accuracy by 18% compared to standard CIoU. Evaluated on a diverse dataset of 8046 annotated images, YOLO-Pepper achieves state-of-the-art performance, with 94.26% mAP@0.5 at 115.26 FPS, marking an 11.88 percentage point improvement over YOLOv10n (82.38% mAP@0.5) while maintaining a lightweight structure (2.51 M parameters, 5.15 MB model size) optimized for edge deployment. Comparative experiments highlight YOLO-Pepper's superiority over nine benchmark models, particularly in detecting small and occluded targets. By addressing computational inefficiencies and refining small object detection capabilities, YOLO-Pepper provides robust technical support for intelligent agricultural monitoring systems, making it a highly effective tool for early disease detection and integrated pest management in commercial greenhouse operations.

PMID:40420214 | DOI:10.1186/s13007-025-01387-4

Genome Med. 2025 May 26;17(1):60. doi: 10.1186/s13073-025-01484-y.

ABSTRACT

BACKGROUND: Digital pathology (DP) has revolutionized cancer diagnostics and enabled the development of deep-learning (DL) models aimed at supporting pathologists in their daily work and improving patient care. However, the clinical adoption of such models remains challenging. Here, we describe a proof-of-concept framework that, leveraging Health Level 7 (HL7) standard and open-source DP resources, allows a seamless integration of both publicly available and custom developed DL models in the clinical workflow.

METHODS: Development and testing of the framework were carried out in a fully digitized Italian pathology department. A Python-based server-client architecture was implemented to interconnect through HL7 messaging the anatomic pathology laboratory information system (AP-LIS) with an external artificial intelligence-based decision support system (AI-DSS) containing 16 pre-trained DL models. Open-source toolboxes for DL model deployment were used to run DL model inference, and QuPath was used to provide an intuitive visualization of model predictions as colored heatmaps.

RESULTS: A default deployment mode runs continuously in the background as each new slide is digitized, choosing the correct DL model(s) on the basis of the tissue type and staining. In addition, pathologists can initiate the analysis on-demand by selecting a specific DL model from the virtual slide tray. In both cases, the AP-LIS transmits an HL7 message to the AI-DSS, which processes the message, runs DL model inference, and creates the appropriate visualization style for the employed classification model. The AI-DSS transmits model inference results to the AP-LIS, where pathologists can visualize the output in QuPath and/or directly as slide description in the virtual slide tray.

CONCLUSIONS: Taken together, the developed integration framework through the use of the HL7 standard and freely available DP resources offers a standardized, portable, and open-source solution that lays the groundwork for the future widespread adoption of DL models in pathology diagnostics.

PMID:40420213 | DOI:10.1186/s13073-025-01484-y

J Cheminform. 2025 May 26;17(1):84. doi: 10.1186/s13321-025-01027-y.

ABSTRACT

Predicting surfactant adsorption using the currently available isotherm model is limited to one or two independent variables: equilibrium concentration and temperature. This study aims to develop an adsorption model that includes molecular features, testing conditions, and solid properties in the model. A Physics-Informed Neural Network (PINN) was structured by integrating adsorption isotherm into artificial neural networks (ANN). The model was trained using a dataset containing 56 adsorption isotherms and 20 types of anionic and nonionic surfactants under various conditions with sand and silica oxide as their solids. The surfactants were quantified using sets of descriptors generated from molecular counting, charge distribution, and Conductor-like Screening Model (COSMO) screened charge density. The COSMO-screened charge density descriptors provide the highest accuracy in representing the surfactant molecule. The interpretation of molecular structure effect and surfactant-solid interaction described using COSMO-screened charge density showed that adsorption between the surfactant and solid media involves hydrogen bonding and hydrophobic interaction. The PINN model achieves high accuracy with 93% training and 85% validation with fivefold cross-validation. Later, the model was evaluated and used to generate an adsorption isotherm and predict unseen surfactant adsorption. Adsorption prediction with unseen surfactants showed high accuracy with the surfactant for familiar structure (RMSE 0.07 mg/g) and promising profile for the whole new structure (RMSE 2.95 mg/g). Scientific contribution This study advances the field by integrating COSMO-screened charge density descriptors into a physics-informed deep learning model to predict surfactant adsorption isotherms, accounting for molecular features, testing conditions, and solid properties. The incorporation of COSMO-screened charge density offers a novel approach to accurately represent surfactant molecules, enabling accurate prediction of their adsorption behavior. This approach extends conventional models, which are often limited to empirical parameters or fewer variables. This physics-informed framework significantly enhances the understanding of surfactant-solid interactions and offers a robust predictive tool for optimizing surfactant formulations, aiming to minimize adsorption losses in chemical enhanced oil recovery and environmental remediation.

PMID:40420147 | DOI:10.1186/s13321-025-01027-y

Crit Care. 2025 May 26;29(1):212. doi: 10.1186/s13054-025-05457-w.

ABSTRACT

BACKGROUND: Major Adverse Kidney Events within 30 days (MAKE30) is an important patient-centered outcome for assessing the impact of acute kidney injury (AKI). Existing prediction models for MAKE30 are static and overlook dynamic changes in clinical status. We introduce ORAKLE, a novel deep-learning model that utilizes evolving time-series data to predict MAKE30, enabling personalized, patient-centered approaches to AKI management and outcome improvement.

METHODS: We conducted a retrospective study using three publicly available critical care databases: MIMIC-IV as the development cohort, and SiCdb and eICU-CRD as external validation cohorts. Patients with sepsis-3 criteria who developed AKI within 48 h of intensive care unit admission were identified. Our primary outcome was MAKE30, defined as a composite of death, new dialysis or persistent kidney dysfunction within 30 days of ICU admission. We developed ORAKLE using Dynamic DeepHit framework for time-series survival analysis and its performance against Cox and XGBoost models. We further assessed model calibration using Brier score.

RESULTS: We analyzed 16,671 patients from MIMIC-IV, 2665 from SICdb, and 11,447 from eICU-CRD. ORAKLE outperformed the XGBoost and Cox models in predicting MAKE30, achieving AUROCs of 0.84 (95% CI: 0.83-0.86) vs. 0.81 (95% CI: 0.79-0.83) vs. 0.80 (95% CI: 0.78-0.82) in MIMIC-IV internal test set, 0.83 (95% CI: 0.81-0.85) vs. 0.80 (95% CI: 0.78-0.83) vs. 0.79 (95% CI: 0.77-0.81) in SICdb, and 0.85 (95% CI: 0.84-0.85) vs. 0.83 (95% CI: 0.83-0.84) vs. 0.81 (95% CI: 0.80-0.82) in eICU-CRD. The AUPRC values for ORAKLE were also significantly better than that of XGBoost and Cox models. The Brier score for ORAKLE was 0.21 across the internal test set, SICdb, and eICU-CRD, suggesting good calibration.

CONCLUSIONS: ORAKLE is a robust deep-learning model for predicting MAKE30 in critically ill patients with AKI that utilizes evolving time series data. By incorporating dynamically changing time series features, the model captures the evolving nature of kidney injury, treatment effects, and patient trajectories more accurately. This innovation facilitates tailored risk assessments and identifies varying treatment responses, laying the groundwork for more personalized and effective management approaches.

PMID:40420108 | DOI:10.1186/s13054-025-05457-w

BMC Oral Health. 2025 May 26;25(1):801. doi: 10.1186/s12903-025-06104-0.

ABSTRACT

PURPOSE: Numerous studies have investigated the use of convolutional neural network (CNN) models for detecting periapical lesions(PLs). However, limited research has focused on evaluating their potential in assisting clinicians with diagnosis. This study aims to utilize two deep learning(DL) models, ConvNeXt and ResNet34, to aid novice dentists in the detection of PLs on periapical radiographs (PRs). By assessing the diagnostic support provided by these models, this research seeks to promote the clinical application of DL in dentistry.

MATERIALS AND METHODS: In this study, 1,305 PRs were gathered and then split into a training set of 1,044 images and a validation set of 261 images, following an 80/20 ratio. The model's effectiveness was assessed using various measures, including precision, sensitivity, F1 score, specificity, accuracy, and the area under the curve (AUC). To evaluate the impact of the model on diagnostic performance by novice dentists, we used an additional set of 800 individual teeth PRs, which were not included in the training or validation sets. The diagnostic performance and time of three novice dentists were measured both with and without model assistance.

RESULTS: The precision of ConvNeXt was 85.93%, with an F1 score of 0.92, accuracy of 91.25%, sensitivity of 98.49%, specificity of 84.11%, and an AUC of 0.9693, outperforming ResNet34 across all metrics. In comparison, ResNet34 achieved a precision of 83.08%, an F1 score of 0.84, accuracy of 81.63%, sensitivity of 84.38%, specificity of 78.13%, and an AUC of 0.8988. In the model-assisted diagnosis phase, both ConvNeXt and ResNet34 improved the diagnostic performance of novice dentists. With the help of ConvNeXt, the average AUC of three dentists increased from 0.88 to 0.94, while with ResNet34, the average AUC of the three dentists improved from 0.88 to 0.91. ConvNeXt performed better than ResNet34 (p < 0.05). Additionally, ConvNeXt reduced the average diagnostic time of the three dentists from 178.8 min to 141.9 min, while ResNet34 reduced the average diagnostic time from 178.8 min to 153.6 min.

CONCLUSION: ConvNeXt significantly improved the diagnostic performance of novice dentists and reduced the time required for diagnosis, thereby enhancing clinical efficiency in both diagnosis and treatment. This model shows potential for application in dental clinics or educational institutions where experienced specialists are limited, but there is a large presence of novice, less-experienced dentists.

PMID:40420083 | DOI:10.1186/s12903-025-06104-0

BMC Oral Health. 2025 May 26;25(1):800. doi: 10.1186/s12903-025-05984-6.

ABSTRACT

BACKGROUND: Deep learning has been utilized to segment teeth from computed tomography (CT) or cone-beam CT (CBCT). However, the performance of deep learning is unknown due to multiple models and diverse evaluation metrics. This systematic review and meta-analysis aims to evaluate the evolution and performance of deep learning in tooth segmentation.

METHODS: We systematically searched PubMed, Web of Science, Scopus, IEEE Xplore, arXiv.org, and ACM for studies investigating deep learning in human tooth segmentation from CT/CBCT. Included studies were assessed using the Quality Assessment of Diagnostic Accuracy Study (QUADAS-2) tool. Data were extracted for meta-analyses by random-effects models.

RESULTS: A total of 30 studies were included in the systematic review, and 28 of them were included for meta-analyses. Various deep learning algorithms were categorized according to the backbone network, encompassing single-stage convolutional models, convolutional models with U-Net architecture, Transformer models, convolutional models with attention mechanisms, and combinations of multiple models. Convolutional models with U-Net architecture were the most commonly used deep learning algorithms. The integration of attention mechanism within convolutional models has become a new topic. 29 evaluation metrics were identified, with Dice Similarity Coefficient (DSC) being the most popular. The pooled results were 0.93 [0.93, 0.93] for DSC, 0.86 [0.85, 0.87] for Intersection over Union (IoU), 0.22 [0.19, 0.24] for Average Symmetric Surface Distance (ASSD), 0.92 [0.90, 0.94] for sensitivity, 0.71 [0.26, 1.17] for 95% Hausdorff distance, and 0.96 [0.93, 0.98] for precision. No significant difference was observed in the segmentation of single-rooted or multi-rooted teeth. No obvious correlation between sample size and segmentation performance was observed.

CONCLUSIONS: Multiple deep learning algorithms have been successfully applied to tooth segmentation from CT/CBCT and their evolution has been well summarized and categorized according to their backbone structures. In future, studies are needed with standardized protocols and open labelled datasets.

PMID:40420051 | DOI:10.1186/s12903-025-05984-6

BMC Musculoskelet Disord. 2025 May 27;26(1):521. doi: 10.1186/s12891-025-08784-9.

ABSTRACT

BACKGROUND: Planning an osteotomy or arthroplasty surgery on a lower limb requires prior classification/identification of its deformities. The detection of skeletal landmarks and the calculation of angles required to identify the deformities are traditionally done manually, with measurement accuracy relying considerably on the experience of the individual doing the measurements. We propose a novel, image pyramid-based approach to skeletal landmark detection.

METHODS: The proposed approach uses a Convolutional Neural Network (CNN) that receives the raw X-ray image as input and produces the coordinates of the landmarks. The landmark estimations are modified iteratively via the error feedback method to come closer to the target. Our clinically produced full-leg X-Rays dataset is made publically available and used to train and test the network. Angular quantities are calculated based on detected landmarks. Angles are then classified as lower than normal, normal or higher than normal according to predefined ranges for a normal condition.

RESULTS: The performance of our approach is evaluated at several levels: landmark coordinates accuracy, angles' measurement accuracy, and classification accuracy. The average absolute error (difference between automatically and manually determined coordinates) for landmarks was 0.79 ± 0.57 mm on test data, and the average absolute error (difference between automatically and manually calculated angles) for angles was 0.45 ± 0.42°.

CONCLUSIONS: Results from multiple case studies involving high-resolution images show that the proposed approach outperforms previous deep learning-based approaches in terms of accuracy and computational cost. It also enables the automatic detection of the lower limb misalignments in full-leg x-ray images.

PMID:40420033 | DOI:10.1186/s12891-025-08784-9

BMC Med Imaging. 2025 May 26;25(1):191. doi: 10.1186/s12880-025-01676-3.

ABSTRACT

OBJECTIVES: To develop a deep learning network for extracting features from the blood-supplying regions of the lenticulostriate artery (LSA) and to establish these features as an imaging biomarker for the comprehensive assessment of the lenticulostriate artery-neural complex (LNC).

MATERIALS AND METHODS: Automatic segmentation of brain regions on T1-weighted images was performed, followed by the development of the ResNet18 framework to extract and visualize deep learning features from three regions of interest (ROIs). The root mean squared error (RMSE) was then used to assess the correlation between these features and fractional anisotropy (FA) values from diffusion tensor imaging (DTI) and cerebral blood flow (CBF) values from arterial spin labeling (ASL). The correlation of these features with LSA root numbers and three disease categories was further validated using fine-tuning classification (Task1 and Task2).

RESULTS: Seventy-nine patients were enrolled and classified into three groups. No significant differences were found in the number of LSA roots between the right and left hemispheres, nor in the FA and CBF values of the ROIs. The RMSE loss, relative to the mean FA and CBF values across different ROI inputs, ranged from 0.154 to 0.213%. The model's accuracy in Task1 and Task2 fine-tuning classification reached 100%.

CONCLUSIONS: Deep learning features extracted from the basal ganglia nuclei effectively reflect cerebrovascular and neurological functions and reveal the damage status of the LSA. This approach holds promise as a novel imaging biomarker for the comprehensive assessment of the LNC.

PMID:40420012 | DOI:10.1186/s12880-025-01676-3

BMC Med Imaging. 2025 May 26;25(1):190. doi: 10.1186/s12880-025-01738-6.

ABSTRACT

BACKGROUND: This paper presents a deep learning model for the automated segmentation of cerebral cavernous malformations (CCMs).

METHODS: The model was trained using treatment planning data from 199 Gamma Knife (GK) exams, comprising 171 cases with a single CCM and 28 cases with multiple CCMs. The training data included initial MRI images with target CCM regions manually annotated by neurosurgeons. For the extraction of data related to the brain parenchyma, we employed a mask region-based convolutional neural network (Mask R-CNN). Subsequently, this data was processed using a 3D convolutional neural network known as DeepMedic.

RESULTS: The efficacy of the brain parenchyma extraction model was demonstrated via five-fold cross-validation, resulting in an average Dice similarity coefficient of 0.956 ± 0.002. The segmentation models used for CCMs achieved average Dice similarity coefficients of 0.741 ± 0.028 based solely on T2W images. The Dice similarity coefficients for the segmentation of CCMs types were as follows: Zabramski Classification type I (0.743), type II (0.742), and type III (0.740). We also developed a user-friendly graphical user interface to facilitate the use of these models in clinical analysis.

CONCLUSIONS: This paper presents a deep learning model for the automated segmentation of CCMs, demonstrating sufficient performance across various Zabramski classifications.

TRIAL REGISTRATION: not applicable.

PMID:40420000 | DOI:10.1186/s12880-025-01738-6

BMC Cancer. 2025 May 26;25(1):940. doi: 10.1186/s12885-025-14369-5.

ABSTRACT

BACKGROUND AND AIM: Breast cancer is highly prevalent, with an increasing trend in women globally. Although the survival of breast cancer is relatively high, the recurrence rate is also high, demanding effective predictive solutions to breast cancer prognosis among post-operative patients. So far, Artificial intelligence algorithms integrated with various clinical data have demonstrated potential predictive capability regarding breast cancer recurrence.

OBJECTIVE: This study aims to specifically conduct a predictive analysis of one-year recurrence of breast cancer by comparing and analyzing different machine learning and deep learning algorithms trained by structural prognostic data.

MATERIALS AND METHODS: This retrospective study was carried out using one database, including 1156 post-operative breast cancer data from 30 January 2020 to 30 December 2022, in three clinical centers in Tehran City. The inclusion criteria were patients who had undergone at least one surgery, had at least one year of medical records, and did not have other conditions. The patients who were diagnosed with malignant BC and had undergone adjuvant therapies without surgery were excluded from the study. Twenty-three prognostic factors were utilized to train algorithms to establish prediction models for the one-year recurrence of breast cancer. The data were analyzed using univariate and adjusted correlation-based methods and chosen machine learning and deep learning algorithms. The discrimination, calibration, and clinical utility were leveraged to assess the algorithms' performance efficiency. The SHapley Additive exPlanations plot was generated to identify the prominent prognostic factors affecting the one-year recurrence of breast cancer.

RESULTS: Totally, 445 relapsed and 711 non-relapsed cases were utilized in this study. Our empirical study showed that the random forest with a positive predictive value of 0.96, negative predictive value of 0.92, sensitivity of 0.92, specificity of 0.96, accuracy of 0.94, F-score of 0.94, area under the receiver operator characteristics curve of 0.919 was the best-performing model for predicting the breast cancer recurrence. As the analysis of SHapley Additive exPlanations indicated, the tumor grade, HER-2, and the number of lymph nodes involved were more significant predictors.

CONCLUSION: The current study demonstrated the potential predictive power of the random forest for early predicting tumors among breast cancer patients who have undergone surgery and its utility in enhancing decision-making in clinical environments. It is crucial in promoting the prognosis, more effectively choosing therapies, augmenting post-operative breast cancer patients' survival, and controlling the limited healthcare resources.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40419997 | DOI:10.1186/s12885-025-14369-5

BMC Pulm Med. 2025 May 26;25(1):263. doi: 10.1186/s12890-025-03706-w.

ABSTRACT

Intestitial lung diseases (ILDs) include a group of inflammatory and fibrotic pulmonary disorders with different etiologies which in several patients might lead to a progressive reduction of respiratory capacities and chronic respiratory failure. Nowadays, biomarkers for predicting the ILD progression and response to therapies are lacking. Adiponectin, the most abundant peptide secreted by adipocytes, has emerged as a potential response biomarker in fibrotic progressive ILDs. The aim of this observational prospective single-center cross-sectional study is therefore to verify whether serum adiponectin levels were altered in patients with fibrotic ILDs (f-ILDs) and its correlation with clinical and pulmonary function data. Sixty-four f-ILDs patients - divided in three subgroups IPF, CTD-ILDs and other f-ILDs - and 45 healthy subjects were recruited. Serum adiponectin concentration were measured by enzyme-linked immunosorbent assay (ELISA). Pulmonary function tests and clinical data were systematically collected. The results showed that patients with f-ILDs have reduced circulating levels of serum adiponectin (12.5 [10.8-15.4] versus 19.3 [17.3-20.8] p < 0.001). No significant difference in adiponectin levels were observed in the different f-ILDs subgroups (p = 0.619). Adiponectin levels were not associated with progression of f-ILDs (p = 0.745). High molecular weight adiponectin isoform was highly reduced in patients with f-ILDs. In patients with CTD-ILDs - but not in other subgroups - adiponectin levels were associated with pulmonary function and GAP index. These resuls support a potential role of adiponectin as diagnostic and prognostic biomarker of f-ILDs.

PMID:40420027 | DOI:10.1186/s12890-025-03706-w

Cell Mol Life Sci. 2025 May 27;82(1):214. doi: 10.1007/s00018-025-05729-2.

ABSTRACT

Long non-coding RNAs (lncRNAs) play critical roles in the process of lung tissue injury and repair which abnormal repair leads to disease including fibrosis, yet the physiopathology remains elusive. Here, we identified the lncRNA SYISL as a key regulator that is markedly upregulated in idiopathic pulmonary fibrosis (IPF) patients and bleomycin (BLM)-induced murine fibrotic lungs. Inhibition of SYISL significantly attenuates TGF-β1-driven fibroblast myofibroblast transition (FMT), a process confers to tissue injury repair and regeneration. Which demonstrates SYISL interaction with miR-23a function as a potent suppressor of fibrotic activation. Mechanistically, SYISL acts as a competing endogenous RNA (ceRNA) that directly binds miR-23a, thereby derepressing TRIO and F-actin binding protein (TRIOBP) via targeting its 3' untranslated region (UTR). Knockdown of TRIOBP amplifies the anti-fibrotic effects of miR-23a mimics while abolishing the pro-fibrotic activity of miR-23a inhibitors, establishing TRIOBP as a downstream effector of the SYISL/miR-23a axis. In vivo, intratracheal delivery of SYISL-targeting shRNA via adeno-associated virus (AAV) robustly reduces collagen deposition, hydroxyproline content, and expression of fibrotic markers in BLM-induced mice. Our findings elucidate a lncRNA-driven regulatory circuit in which SYISL promotes pulmonary fibrosis by sequestering miR-23a to elevate TRIOBP expression, nominating this axis as a novel therapeutic target for IPF.

PMID:40419807 | DOI:10.1007/s00018-025-05729-2

Cell Signal. 2025 May 24:111886. doi: 10.1016/j.cellsig.2025.111886. Online ahead of print.

ABSTRACT

TRIM7, a member of the E3 ubiquitin ligase family, has garnered significant attentions in different research fields since its discovery. This enzyme plays indispensable roles in various pathophysiological processes through ubiquitination-mediated degradation of diverse protein substrates. This review systematically summarizes the current knowledge on the protein structure and biological functions of TRIM7. Structurally, TRIM7 features a conserved RBCC motif (RING, B-box, and coiled-coil domains) coupled with a variable C-terminal region that dictates the substrate specificity. In infectious contexts, TRIM7 is required for the pathogen-specific regulation, and exerts paradoxical effects by either promoting host defense or facilitating viral pathogenesis depending on pathogen type. Within oncology, TRIM7 manifests tumor-suppressive properties through regulating metastasis, apoptosis, and tumor immunology. In addition, it might serve as a reliable biomarker for monitoring the progression of idiopathic pulmonary fibrosis and also inhibits the progression of atherosclerosis. In summary, TRIM7 plays critical roles in different pathophysiological processes, and it might be a predictive and therapeutic target in certain human diseases.

PMID:40419231 | DOI:10.1016/j.cellsig.2025.111886

Proteome Sci. 2025 May 26;23(1):5. doi: 10.1186/s12953-025-00241-8.

ABSTRACT

BACKGROUND: Metabolomics, a burgeoning field within systems biology, focuses on the comprehensive study of small molecules present in biological systems. Mass spectrometry (MS) has emerged as a powerful tool for metabolomic analysis due to its high sensitivity, resolution, and ability to characterize a wide range of metabolites thus offering deep insights into the metabolic profiles of living systems.

AIM OF REVIEW: This review provides an overview of the methodologies, workflows, strategies, data analysis techniques, and applications associated with mass spectrometry-based metabolomics.

KEY SCIENTIFIC CONCEPTS OF REVIEW: We discuss workflows, key strategies, experimental procedures, data analysis techniques, and diverse applications of metabolomics in various research domains. Nuances of sample preparation, metabolite extraction, separation using chromatographic techniques, mass spectrometry analysis, and data processing are elaborated. Moreover, standards, quality controls, metabolite annotation, software for statistical and pathway analysis are also covered. In conclusion, this review aims to facilitate the understanding and adoption of mass spectrometry-based metabolomics by newcomers and researchers alike by providing a foundational understanding and insights into the current state and future directions of this dynamic field.

PMID:40420110 | DOI:10.1186/s12953-025-00241-8