Gait Posture. 2025 May;118:168-177. doi: 10.1016/j.gaitpost.2025.02.001. Epub 2025 Feb 13.

ABSTRACT

INTRODUCTION: Fully-instrumented gait analysis (FGA) enables objective and scientific characterization of human motion parameters. It is unclear to what extent FGA is used in the care of patients with rare bone diseases (RBDs). Our purpose was to provide a scoping review to describe and categorize the spectrum of existing literature about FGA in patients with RBD, to report the key findings and the impact on the clinical management. Additionally, we aimed to explore the feasibility of establishing a minimum common standard for evaluating the quality of motion analysis studies.

METHODS: Within the activities of ERN BOND (European Reference Network for Rare Bone Diseases), a systematic literature search was performed in the following databases: Ovid Medline, Cochrane Database of Systematic Reviews, CENTRAL Register of controlled trials, Embase, Global Health and Epistemonikos. Abstracts and full-text articles were screened by two independent reviewers. The PRISMA ScR protocol was followed, and quality assessment of all studies was done based on the 27-item Downs and Black Scale.

RESULTS: The abstracts of 1053 studies were screened, and 64 full-text studies were assessed for eligibility and 24 studies could be included. We found reduced walking speed and step lengths being one of the most common features. Furthermore, characteristic patterns for several of the RBDs, as reduced ankle push-off power, increased lateral trunk lean and increased flexion pattern in the sagittal plane, are all contributing to an increased energy expenditure during gait. Several studies found a mismatch between static radiological findings and dynamic gait parameters.

CONCLUSIONS: Existing research indicates that FGA should be considered an important tool to better understand gait alterations and the effect of lower limb deformities on gait in these patients. Together with radiologic assessment FGA data might be used for clinical decision making and as outcome parameters in future observational and interventional studies.

PMID:39978051 | DOI:10.1016/j.gaitpost.2025.02.001

Res Sq [Preprint]. 2025 Jan 30:rs.3.rs-5811417. doi: 10.21203/rs.3.rs-5811417/v1.

ABSTRACT

Incontinentia pigmenti (IP) is caused by loss-of-function variants in IKBKG, with molecular genetic diagnosis complicated by a pseudogene. We describe seven individuals from three families with IP but negative clinical testing in whom long-read sequencing identified causal variants. Concurrent methylation analysis explained disease severity in one individual who died from neurologic complications, identified a mosaic variant in an individual with an atypical presentation, and confirmed skewed X-chromosome inactivation in an XXY individual.

PMID:39975911 | PMC:PMC11838753 | DOI:10.21203/rs.3.rs-5811417/v1

bioRxiv [Preprint]. 2025 Feb 9:2025.01.30.635777. doi: 10.1101/2025.01.30.635777.

ABSTRACT

Duchenne muscular dystrophy (DMD) patients suffer from skeletal and cardiopulmonary weakness, and interestingly up to one third are diagnosed on the autism spectrum. Dystrophin is an essential protein for regulating the transmission of intracellular force to the extracellular matrix within the skeletal muscle, but also plays key roles in neurobehavior and cognitive function. The mouse dystrophin gene (also abbreviated Dmd) is X-linked and has several isoforms with tissue-specific expression, including the large Dp427m muscle transcript found in heart and skeletal muscle, and the Dp427c transcript that encodes the brain-specific dystrophin cerebellar protein. Understanding the functional requirements and pathways that are affected by dystrophin loss will impact dystrophin replacement gene therapy and exon-skipping correction strategies. We generated conditional Dystrophin knockout mice by targeting exon 52 of the mouse Dystrophin (Dmd flox52) locus. We generated dystrophin constitutive and inducible myofiber knockout (Dmd mKO) mice to evaluate the tissue-specific function of the large skeletal muscle dystrophin isoform. Constitutive embryonic deletion of the Dystrophin gene exclusively in skeletal myofibers resulted in a severe skeletal muscle myopathy, dystrophic histopathology, and functional deficits compared to the mdx mouse. Transcriptomic analysis of skeletal myofibers of the Dmd mKO mice revealed the dysregulation of key extracellular matrix and cytokine signaling pathways. Separately, we generated Purkinje neuron cerebellar dystrophin knockout (Dmd:Pcp2 KO) mice that displayed neurobehavioral deficits in social approach, social memory, and spatial navigation and working memory. These studies reveal the essential requirement for dystrophin expression in both the skeletal muscle and brain for normal physiological and neurobehavioral function.

PMID:39975305 | PMC:PMC11838426 | DOI:10.1101/2025.01.30.635777

Biomed Pharmacother. 2025 Feb 19;184:117931. doi: 10.1016/j.biopha.2025.117931. Online ahead of print.

ABSTRACT

Triple-negative breast cancer (TNBC), a highly invasive type of cancer, is difficult to treat due to insufficient specific targets and low survival rates. Current therapy often encounters drug resistance or relapse; thus, repurposing existing drugs could revolutionize cancer treatment. This study examined the anticancer effects of the antipsychotics Cariprazine (CAR), Olanzapine (OLZ), and Clozapine (CLZ), and the immunomodulatory potential of CAR, in vitro and in vivo in TNBC models. In vitro, CAR, OLZ, and CLZ significantly inhibited the proliferation of TNBC cells. This inhibition occurred via the induction of mitochondrial apoptosis, G0/G1 cell cycle arrest, and the suppression of autophagy, as evidenced by the down-regulation of Bcl-2, p62, and pAKT; the upregulation of Bax and active caspase 3; the decrease of ΔΨM; and the promotion of cytochrome c release. In addition, CAR inhibited MDA-MB-231 cells migration. In vivo, CAR inhibited tumor growth in the 4T1 xenograft model without causing adverse effects and resulted in the mRNA upregulation caspase 9, p53, p21, and Beclin-1. In addition, CAR influenced the immune response by promoting the production of proinflammatory cytokines TNF-α, IFN-γ, IL-17, and IL-1β and increasing the percentage of TNF-α+, IL-17+, IL-1β+, and IFN-γ+ CD3+ splenocytes. In conclusion, compared with other antipsychotics, 5-FU, and cisplatin, CAR exerted the most potent anticancer activity in TNBC in vitro and in vivo. This efficacy may be attributed to its ability to regulate apoptosis and autophagy, promote G0/G1 cell cycle arrest, and modulate antitumor immune response, suggesting its therapeutic potential in breast cancer.

PMID:39978031 | DOI:10.1016/j.biopha.2025.117931

Pharmacogenomics J. 2025 Feb 20;25(2):3. doi: 10.1038/s41397-024-00360-z.

ABSTRACT

Prediction of treatment response by genetic biomarkers has potential for clinical use and contributes to the understanding of pathophysiology and drug mechanism of action. The purpose of this study is to detect genetic biomarkers possibly associated with response to lurasidone, during the first four weeks of treatment. One-hundred and seventy-one acutely psychotic patients from two placebo-controlled clinical trials of lurasidone were included. Genetic associations with changes in Positive and Negative Syndrome Scale total score at weeks one, two, and four were examined. Genotyping was done with the Affymetrix 6.0 microarray and associations were computed using PLINK regression model. Although genome-wide significance was not reached with a limited sample size, signals of potential interest for further studies were with genes important for neurogenesis. Possible week one marker, rs6459950 (p = 7.05 × 10-7), was close to the sonic hedgehog gene (SHH), involved in neuronal differentiation and neurogenesis. Possible week two marker, rs7435958, was a SNP of GABRB1, encoding the GABAA Receptor β1. Notably, possible week four signals included a SNP within PTCH1, a specific receptor for the SHH, the possible week one marker. Pathway analysis supported the possibility that neurogenesis might be involved in early antipsychotic response. Tissue enrichment analysis suggested that potential signals were enriched in anterior cingulate cortex, reported to be relevant in antipsychotic action. This is the first study to examine genes possibly associated with very early response to lurasidone. Further replication studies in larger sample size should be required.

PMID:39979276 | DOI:10.1038/s41397-024-00360-z

J Cyst Fibros. 2025 Feb 19:S1569-1993(25)00059-1. doi: 10.1016/j.jcf.2025.02.008. Online ahead of print.

ABSTRACT

INTRODUCTION: Cystic fibrosis (CF) is caused by mutation of the CFTR gene, encoding an epithelial anion channel. Here we evaluated the effect of the modulator combination elexacaftor-tezacaftor-ivacaftor (ETI) on the function of four rare, poorly characterized CFTR variants: L383S, I507del, L1065P and R1066H.

METHODS: Intestinal organoids were obtained from subjects carrying the CFTR variants L383S, I507del, L1065P or R1066H in trans of a minimal function allele (class I mutation). Organoids and epithelial monolayers were used to assess the effect of ETI on CFTR protein abundance and CFTR-mediated chloride, bicarbonate, and fluid transport.

RESULTS: In L383S-CFTR expressing cells, normal levels of fully glycosylated CFTR protein (C-band) were detected. In contrast, in I507del, L1065P or R1066H organoids, only partially glycosylated CFTR (B-band) was detected. Chloride/bicarbonate transport was severely impaired in epithelial monolayers prepared from these latter three variants, while anion transport of the L383S variant was affected to a moderate extent. ETI, but not ivacaftor alone, significantly enhanced CFTR-mediated chloride and bicarbonate transport in L1065P and R1066H monolayers, and stimulated fluid transport. A corresponding increase in the abundance of C-band protein was observed in both variants. ETI also modestly improved L383S-CFTR function, with a marginal effect on I507del-CFTR.

CONCLUSIONS: The I507del, L1065P and R1066H variants display severely impaired function. ETI treatment markedly enhanced L1065P- and R1066HCFTR function, whereas its effect on L383S- CFTR was less pronounced. Consequently, ETI may ameliorate disease symptoms in individuals carrying the L1065P or R1066H variant. More tentative, it may also benefit those carrying the L383S variant.

PMID:39979195 | DOI:10.1016/j.jcf.2025.02.008

J Cyst Fibros. 2025 Feb 19:S1569-1993(25)00064-5. doi: 10.1016/j.jcf.2025.02.014. Online ahead of print.

NO ABSTRACT

PMID:39979194 | DOI:10.1016/j.jcf.2025.02.014

Asian J Endosc Surg. 2025 Jan-Dec;18(1):e70036. doi: 10.1111/ases.70036.

ABSTRACT

Cholelithiasis is increasing in the pediatric population, and there are currently no guidelines for the management of asymptomatic patients with both cholelithiasis and a predisposing condition. This study seeks to highlight situations where prophylactic cholecystectomy may be desirable. We retrospectively reviewed the medical records of children who underwent elective laparoscopic cholecystectomy between October 2011 and September 2022. Thirty-two patients were included in the study. Five different groups of patients were identified based on associated pathologies. Twenty-six patients were symptomatic (81.25%), and six were asymptomatic (18.75%). All patients underwent a laparoscopic cholecystectomy. Hematologic and cystic fibrosis patients with asymptomatic cholelithiasis had a shorter length of hospital stay than patients with the same condition who progressed from asymptomatic to symptomatic gallstone disease. Consequently, patients with associated diseases (particularly hematologic diseases and cystic fibrosis) may benefit from early laparoscopic cholecystectomy, which could reduce the probability of surgical difficulties and shorten the length of hospital stay.

PMID:39978935 | DOI:10.1111/ases.70036

Am J Transplant. 2025 Feb 18:S1600-6135(25)00092-9. doi: 10.1016/j.ajt.2025.02.009. Online ahead of print.

ABSTRACT

Lung transplant candidates who are highly sensitized against human leucocyte antigen have a lower likelihood of graft allocation and a higher risk of dying while on the waiting list. C1-esterase inhibitor, an inhibitor of the classical and lectin pathways of complement activation, has been used successfully to prevent and treat acute antibody-mediated rejection in kidney and heart transplantation. Here, we report three cases of C1-esterase inhibitors used perioperatively in highly sensitized lung transplant candidates, with successful bilateral lung transplants despite severe primary graft dysfunction and/or hyperacute antibody-mediated rejection.

PMID:39978596 | DOI:10.1016/j.ajt.2025.02.009

Pulm Pharmacol Ther. 2025 Feb 18:102345. doi: 10.1016/j.pupt.2025.102345. Online ahead of print.

ABSTRACT

BACKGROUND: Elexacaftor-tezacaftor-ivacaftor (ETI) therapy has shown improvement in lung function, BMI and reduction in pulmonary exacerbations but the impact of genotype and severity of lung disease on heterogeneity of ETI efficacy in real life is not known.

METHODS: This is a prospective observational study. Clinical data at baseline and at one-year of therapy were compared for the total cohort and for two subgroups; genotype [homozygous vs. heterozygous for F508del], and severity of lung disease at ETI initiation (ppFEV1 <80% vs. ≥80%).

RESULTS: Among the total cohort of 115 pwCF, median age of 23 (17, 32) years, 66 (58%) were homozygous, 76 (66%) had ppFEV1 <80%. Significant increases in mean ppFEV1 and mean BMI and decrease in MRSA and Pa culture positivity on sputum/throat swab were observed at one year of ETI therapy in the total cohort, and in groups based on either genotype or disease severity (p<0.05 in all). Comparing one-year prior to one-year on ETI therapy, significant improvements were noted in pulmonary exacerbations, hospital admissions, antibiotic courses, number of pwCF receiving daily chest therapy, dornase alfa and hypertonic saline in the total cohort and in all four subgroups (p<0.05 for all). Though improvements were not dependent on genotype, we noted larger mean differences in ppFEV1, BMI, pulmonary exacerbations and antibiotic use in the group with more severe lung disease (ppFEV1 <80%) after one year of ETI therapy.

CONCLUSION: ETI therapy improved clinical outcomes in pwCF which were impacted by severity of underlying lung disease.

PMID:39978537 | DOI:10.1016/j.pupt.2025.102345

Genome Biol. 2025 Feb 20;26(1):34. doi: 10.1186/s13059-025-03503-y.

ABSTRACT

Spatially resolved transcriptomics (SRT) data provide critical insights into gene expression patterns within tissue contexts, necessitating effective methods for identifying spatial domains. We introduce stDyer, an end-to-end deep learning framework for spatial domain clustering in SRT data. stDyer combines Gaussian Mixture Variational AutoEncoder with graph attention networks to learn embeddings and perform clustering. Its dynamic graphs adaptively link units based on Gaussian Mixture assignments, improving clustering and producing smoother domain boundaries. stDyer's mini-batch strategy and multi-GPU support facilitate scalability to large datasets. Benchmarking against state-of-the-art tools, stDyer demonstrates superior performance in spatial domain clustering, multi-slice analysis, and large-scale dataset handling.

PMID:39980033 | DOI:10.1186/s13059-025-03503-y

BMC Med Educ. 2025 Feb 20;25(1):273. doi: 10.1186/s12909-024-06552-2.

ABSTRACT

BACKGROUND: The integration of artificial intelligence (AI) into medical education is poised to revolutionize teaching, learning, and clinical practice. However, successful implementation of AI-based tools in medical curricula faces several challenges, particularly in resource-limited settings like Pakistan, where technological and institutional barriers remain significant. This study aimed to evaluate knowledge, attitudes, and practices of medical students and faculty regarding AI in medical education, and explore the perceptions and key barriers regarding strategies for effective AI integration.

METHODS: A concurrent mixed-methods study was conducted over six months (July 2023 to January 2024) at a tertiary care medical college in Pakistan. The quantitative component utilized a cross-sectional design, with 236 participants (153 medical students and 83 faculty members) completing an online survey. Mean composite scores for knowledge, attitudes, and practices were analyzed using non-parametric tests. The qualitative component consisted of three focus group discussions with students and six in-depth interviews with faculty. Thematic analysis was performed to explore participants' perspectives on AI integration.

RESULTS: Majority of participants demonstrated a positive attitude towards AI integration. Faculty had significantly higher mean attitude scores compared to students (3.95 ± 0.63 vs. 3.81 ± 0.75, p = 0.040). However, no statistically significant differences in knowledge (faculty: 3.53 ± 0.66, students: 3.55 ± 0.73, p = 0.870) or practices (faculty: 3.19 ± 0.87, students: 3.23 ± 0.89, p = 0.891) were found. Older students reported greater self-perceived knowledge (p = 0.010) and more positive attitudes (p = 0.016) towards AI, while male students exhibited higher knowledge scores than females (p = 0.025). Qualitative findings revealed key themes, including AI's potential to enhance learning and research, concerns about over-reliance on AI, ethical issues surrounding privacy and confidentiality, and the need for institutional support. Faculty emphasized the importance of training to equip educators with the necessary skills to effectively integrate AI into their teaching.

CONCLUSIONS: This study highlights both the enthusiasm for AI integration and the significant barriers that must be addressed to successfully implement AI in medical education. Addressing technological constraints, providing faculty training, and developing ethical guidelines are critical steps toward fostering the responsible use of AI in medical curricula. These findings underscore the need for context-specific strategies, particularly in resource-limited settings, to ensure that medical students and educators are well-prepared for the future of healthcare.

PMID:39979912 | DOI:10.1186/s12909-024-06552-2

BMC Cancer. 2025 Feb 20;25(1):310. doi: 10.1186/s12885-025-13688-x.

ABSTRACT

BACKGROUND: Bladder cancer (BLCA) exists a profound molecular diversity, with basal and luminal subtypes having different prognostic and therapeutic outcomes. Traditional methods for molecular subtyping are often time-consuming and resource-intensive. This study aims to develop machine learning models using deep learning features from hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) to predict basal and luminal subtypes in BLCA.

METHODS: RNA sequencing data and clinical outcomes were downloaded from seven public BLCA databases, including TCGA, GEO datasets, and the IMvigor210C cohort, to assess the prognostic value of BLCA molecular subtypes. WSIs from TCGA were used to construct and validate the machine learning models, while WSIs from Shanghai Tenth People's Hospital (STPH) and The Affiliated Guangdong Second Provincial General Hospital of Jinan University (GD2H) were used as external validations. Deep learning models were trained to obtained tumor patches within WSIs. WSI level deep learning features were extracted from tumor patches based on the RetCCL model. Support vector machine (SVM), random forest (RF), and logistic regression (LR) were developed using these features to classify basal and luminal subtypes.

RESULTS: Kaplan-Meier survival and prognostic meta-analyses showed that basal BLCA patients had significantly worse overall survival compared to luminal BLCA patients (hazard ratio = 1.47, 95% confidence interval: 1.25-1.73, P < 0.001). The LR model based on tumor patch features selected by Resnet50 model demonstrated superior performance, achieving an area under the curve (AUC) of 0.88 in the internal validation set, and 0.81 and 0.64 in the external validation sets from STPH and GD2H, respectively. This model outperformed both junior and senior pathologists in the differentiation of basal and luminal subtypes (AUC: 0.85, accuracy: 74%, sensitivity: 66%, specificity: 82%).

CONCLUSIONS: This study showed the efficacy of machine learning models in predicting the basal and luminal subtypes of BLCA based on the extraction of deep learning features from tumor patches in H&E-stained WSIs. The performance of the LR model suggests that the integration of AI tools into the diagnostic process could significantly enhance the accuracy of molecular subtyping, thereby potentially informing personalized treatment strategies for BLCA patients.

PMID:39979837 | DOI:10.1186/s12885-025-13688-x

J Imaging Inform Med. 2025 Feb 20. doi: 10.1007/s10278-025-01448-z. Online ahead of print.

ABSTRACT

Medical image segmentation is challenging due to the need for expert annotations and the variability of these manually created labels. Previous methods tackling label variability focus on 2D segmentation and single modalities, but reliable 3D multi-modal approaches are necessary for clinical applications such as in oncology. In this paper, we propose a framework for generating reliable and unbiased labels with minimal radiologist input for supervised 3D segmentation, reducing radiologists' efforts and variability in manual labeling. Our framework generates AI-assisted labels through a two-step process involving 3D multi-modal unsupervised segmentation based on feature clustering and semi-supervised refinement. These labels are then compared against traditional expert-generated labels in a downstream task consisting of 3D multi-modal bone tumor segmentation. Two 3D-Unet models are trained, one with manually created expert labels and the other with AI-assisted labels. Following this, a blind evaluation is performed on the segmentations of these two models to assess the reliability of training labels. The framework effectively generated accurate segmentation labels with minimal expert input, achieving state-of-the-art performance. The model trained with AI-assisted labels outperformed the baseline model in 61.67% of blind evaluations, indicating the enhancement of segmentation quality and demonstrating the potential of AI-assisted labeling to reduce radiologists' workload and improve label reliability for 3D multi-modal bone tumor segmentation. The code is available at https://github.com/acurtovilalta/3D_LabelGeneration .

PMID:39979760 | DOI:10.1007/s10278-025-01448-z

J Imaging Inform Med. 2025 Feb 20. doi: 10.1007/s10278-024-01380-8. Online ahead of print.

ABSTRACT

Clinical parameters measured from gated single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) have value in predicting cardiac resynchronization therapy (CRT) patient outcomes, but still show limitations. The purpose of this study is to combine clinical variables, features from electrocardiogram (ECG), and parameters from assessment of cardiac function with polar maps from gated SPECT MPI through deep learning (DL) to predict CRT response. A total of 218 patients who underwent rest-gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6-month follow-up. A DL model was constructed by combining a pre-trained VGG16 model and a multilayer perceptron. Two modalities of data were input to the model: polar map images from SPECT MPI and tabular data from clinical features, ECG parameters, and SPECT-MPI-derived parameters. Gradient-weighted class activation mapping (Grad-CAM) was applied to the VGG16 model to provide explainability for the polar maps. For comparison, four machine learning (ML) models were trained using only the tabular features. Modeling was performed on 218 patients who underwent CRT implantation with a response rate of 55.5% (n = 121). The DL model demonstrated average AUC (0.83), accuracy (0.73), sensitivity (0.76), and specificity (0.69) surpassing ML models and guideline criteria. Guideline recommendations achieved accuracy (0.53), sensitivity (0.75), and specificity (0.26). The DL model trended towards improvement over the ML models, showcasing the additional predictive benefit of utilizing SPECT MPI polar maps. Incorporating additional patient data directly in the form of medical imagery can improve CRT response prediction.

PMID:39979759 | DOI:10.1007/s10278-024-01380-8

Mol Imaging Biol. 2025 Feb 20. doi: 10.1007/s11307-025-01990-w. Online ahead of print.

ABSTRACT

PURPOSE: The goal of this study is to create a novel framework for identifying MSI status in colorectal cancer using advanced radiomics and deep learning strategies, aiming to enhance clinical decision-making and improve patient outcomes in oncology.

PROCEDURES: The study utilizes histopathological slide images from the NCT-CRC-HE-100 K and PAIP 2020 databases. Key procedures include self-attentive adversarial stain normalization for data standardization, tumor delineation via a Slimmable Transformer, and radiomics feature extraction using a hybrid quantum-classical neural network.

RESULTS: The proposed system reaches 99% accuracy when identifying colorectal cancer MSI status. It shows the model is good at telling the difference between MSI and MSS tumors and can be used in real medical care for cancer.

CONCLUSIONS: Our research shows that the new system improves colorectal cancer MSI status determination better than previous methods. Our optimized processing technology works better than other methods to divide and analyze tissue features making the system good for improving patient care decisions.

PMID:39979579 | DOI:10.1007/s11307-025-01990-w

Endocrine. 2025 Feb 20. doi: 10.1007/s12020-025-04196-w. Online ahead of print.

ABSTRACT

PURPOSE: This study explores a self-learning method as an auxiliary approach in residency training for distinguishing between benign and malignant thyroid nodules.

METHODS: Conducted from March to December 2022, internal medicine residents underwent three repeated learning sessions with a "learning set" comprising 3000 thyroid nodule images. Diagnostic performances for internal medicine residents were assessed before the study, after every learning session, and for radiology residents before and after one-on-one education, using a "test set," comprising 120 thyroid nodule images. Finally, all residents repeated the same test using artificial intelligence computer-assisted diagnosis (AI-CAD).

RESULTS: Twenty-one internal medicine and eight radiology residents participated. Initially, internal medicine residents had a lower area under the receiver operating characteristic curve (AUROC) than radiology residents (0.578 vs. 0.701, P < 0.001), improving post-learning (0.578 to 0.709, P < 0.001) to a comparable level with radiology residents (0.709 vs. 0.735, P = 0.17). Further improvement occurred with AI-CAD for both group (0.709 to 0.755, P < 0.001; 0.735 to 0.768, P = 0.03).

CONCLUSION: The proposed iterative self-learning method using a large volume of ultrasonographic images can assist beginners, such as residents, in thyroid imaging to differentiate benign and malignant thyroid nodules. Additionally, AI-CAD can improve the diagnostic performance across varied levels of experience in thyroid imaging.

PMID:39979566 | DOI:10.1007/s12020-025-04196-w

Sci Rep. 2025 Feb 20;15(1):6245. doi: 10.1038/s41598-025-90514-1.

NO ABSTRACT

PMID:39979555 | DOI:10.1038/s41598-025-90514-1

Cardiovasc Eng Technol. 2025 Feb 20. doi: 10.1007/s13239-025-00775-0. Online ahead of print.

ABSTRACT

The prevalence of coronary artery disease (CAD) has become the major cause of death across the world in recent years. The accurate segmentation of coronary artery is important in clinical diagnosis and treatment of coronary artery disease (CAD) such as stenosis detection and plaque analysis. Deep learning techniques have been shown to assist medical experts in diagnosing diseases using biomedical imaging. There are many methods which employ 2D DL models for medical image segmentation. The 2D Pyramid Scene Parsing Neural Network (PSPNet) has potential in this domain but not explored for the segmentation of coronary arteries from 3D Coronary Computed Tomography Angiography (CCTA) images. The contribution of present research work is to propose the modification of 2D PSPNet into 3D PSPNet for segmenting the coronary arteries from 3D CCTA images. The innovative factor is to evaluate the network performance by employing Global processing and Patch based processing methods. The experimental results achieved a Dice Similarity Coefficient (DSC) of 0.76 for Global process method and 0.73 for Patch based method using a subset of 200 images from the ImageCAS dataset.

PMID:39979546 | DOI:10.1007/s13239-025-00775-0

Sci Rep. 2025 Feb 20;15(1):6194. doi: 10.1038/s41598-025-90648-2.

ABSTRACT

Confined columns, such as round-ended concrete-filled steel tubular (CFST) columns, are integral to modern infrastructure due to their high load-bearing capacity and structural efficiency. The primary objective of this study is to develop accurate, data-driven approaches for predicting the axial load-carrying capacity (Pcc​) of these columns and to benchmark their performance against existing analytical solutions. Using an extensive dataset of 200 CFST stub column tests, this research evaluates three machine learning (ML) models - LightGBM, XGBoost, and CatBoost - and three deep learning (DL) models - Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). Key input features include concrete strength, column length, cross-sectional dimensions, steel tube thickness, and yield strength, which were analysed to uncover underlying relationships. The results indicate that CatBoost delivers the highest predictive accuracy, achieving an RMSE of 396.50 kN and an R2 of 0.932, surpassing XGBoost (RMSE: 449.57 kN, R2: 0.906) and LightGBM (RMSE: 449.57 kN, R2: 0.916). Deep learning models were less effective, with the DNN attaining an RMSE of 496.19 kN and R2 of 0.958, while the LSTM underperformed substantially (RMSE: 2010.46 kN, R2: 0.891). SHapley Additive exPlanations (SHAP) identified cross-sectional width as the most critical feature, contributing positively to capacity, and column length as a significant negative influencer. A user-friendly, Python-based interface was also developed, enabling real-time predictions for practical engineering applications. Comparison with 10 analytical models demonstrates that these traditional methods, though deterministic, struggle to capture the nonlinear interactions inherent in CFST columns, thus yielding lower accuracy and higher variability. In contrast, the data-driven models presented here offer robust, adaptable, and interpretable solutions, underscoring their potential to transform design and analysis practices for CFST columns, ultimately fostering safer and more efficient structural systems.

PMID:39979519 | DOI:10.1038/s41598-025-90648-2