Browse Articles
Discover research articles across all indexed journals
Multi-omics driven computational framework for cancer molecular subtype classification
Abstract Cancer molecular subtype classification is an essential component of precision oncology which provides insights into cancer prognosis and guides targeted therapy. Despite the growing applications of AI for cancer molecular subtype classification, challenges persist due to non-standardized dataset configurations, diverse omics modalities, and inconsistent evaluation measures. These issues limit the comparability, reproducibility, and generalizability of AI classifiers across different cancers and hinder the development of robust and accurate AI-driven tools. This study performs comparative analyses of 35 unique AI classifiers across 153 datasets, covering 8 omics modalities and 20 different cancers. Particularly, it investigates 6 different research questions, and based on comprehensive performance analyses of the 35 AI classifiers it elucidates the research questions with the following answers: (i) out of 17 different configurations for 5 out of the 8 tested omics modalities, RPPA (RPPA), Gistic2-all-data-by-genes (CNV), HM27 (Meth), and HiSeqV2-exon (Exon) configurations consistently yield better performance; (ii) in terms of 8 omics modalities, RNASeq, miRNA, CNV, and Exon generally achieve higher macro-accuracy (MACC) compared to Meth., Array, SNP and RPPA; (iii) SNP and RPPA modalities are prone to biases due to technical noise; (iv) traditional machine learning (ML) models (SVM, XGB, HGB) perform best on small and low-dimensional datasets, while deep learning (DL) models (ResNet18, CNN, NN, MLP) excel on large and high-dimensional datasets; (v) SVM achieves the highest mean MACC across all classifiers, with NN, ResNet18, DEEPGENE, and MLP also demonstrate strong performance; and (vi) DL classifiers show superior MACC as compared to ML classifiers in 12 out of 20 cancers. The findings offer key insights to guide the development of standardized, robust, and efficient AI-driven pipelines for cancer molecular subtype classification. This study enhances reproducibility and facilitates better comparison across AI methods, ultimately advancing precision oncology.
SALT: Introducing a framework for hierarchical segmentations in medical imaging using label trees
Abstract Traditional segmentation networks treat anatomical structures as isolated elements, often neglecting their hierarchical relationships. This study introduces Softmax for Arbitrary Label Trees (SALT), a novel method that leverages these hierarchical connections to improve segmentation efficiency and interpretability. SALT is a novel activation function that extends the softmax to arbitrary hierarchical label trees by modeling conditional probabilities along parent–child relations in imaging data. This enables anatomical hierarchies in CT imaging to be represented naturally, allowing segmentations to propagate from broader regions to detailed structures. Using the SAROS dataset from The Cancer Imaging Archive (TCIA), which comprises 900 body segmentations from 883 patients and was enhanced by TotalSegmentator to include 113 anatomical labels, the model was trained on 600 scans, with validation and testing on 150. Dice scores across SAROS, CT-ORG, FLARE22, LCTSC, LUNA16, and WORD datasets measured performance, with 95% confidence intervals (CI) from 1000 bootstrapping rounds. SALT achieved top performance on the LUNA16 and SAROS datasets, with Dice scores of 0.93 (95% CI: 0.919–0.938) and 0.929 (95% CI: 0.924–0.933). Reliable accuracy was also observed in CT-ORG (0.891, 95% CI: 0.869–0.906), FLARE22 (0.849, 95% CI: 0.844–0.854), LCTSC (0.908, 95% CI: 0.902–0.914), and WORD (0.844, 95% CI: 0.839–0.85). SALT can segment a 1000-slice CT in 35 s. By leveraging hierarchical body structures, SALT enables rapid whole-body segmentation, processing CT scans in 35 s on average. This capability supports its integration into clinical workflows, enhancing efficiency in automated full-body segmentation and contributing to improved diagnostic workflows and patient care.
Firearm classification from acoustic signals using combined mel spectrogram, MFCC, LFCC, and CRNN networks
Correction: Genome-wide identification of the cytochrome P450 superfamily in Trichoplusia ni and in-silico expression of resistance against HDAC inhibitors
Quantifying variability of mitochondrial markers in m3243A > G myopathy
Abstract Myopathy is a prevalent and disabling feature of mitochondrial disease, in which skeletal muscle accumulates fibres with mitochondrial dysfunction in a variable mosaic pattern. This intra-individual spatial heterogeneity, a key consideration in longitudinal assessments, remains largely uncharacterised, hindering mechanistic studies and clinical trials by obscuring or confounding findings. We quantified this variability in m.3243 A > G-related myopathy, a leading cause of adult mitochondrial disease. Post-mortem biopsies from quadriceps femoris and tibialis anterior muscles of four patients were analysed for single-fibre deficiency in oxidative phosphorylation (OXPHOS) complex I and IV, while homogenate mitochondrial DNA (mtDNA) copy number and m.3243 A > G heteroplasmy were respectively determined by quantitative PCR and pyrosequencing. Bootstrapped combinatorial analyses established thresholds for minimum meaningful change above the 97.5th percentile, while accounting for anatomical biopsy distancing. Spatial variability in the proportion of OXPHOS-deficient fibres increased with distancing; within the same muscle, this threshold was 13.8% for NDUFB8 and 9.8% for MT-CO1. Variability in mtDNA copy number modestly increased with distance, while m.3243 A > G heteroplasmy remained largely stable, with within-muscle thresholds of 1,136 copies per nucleus and 8.2%, respectively. These findings provide assay-specific thresholds and offer mechanistic and translational insights for trial design, patient monitoring, and reliable detection of disease progression or therapeutic response.
Impact of adhesive curing mode and dentin sealing on bond strength of CAD/CAM resin composite
Abstract The aim of this study was to investigate influence of curing mode of universal adhesives and dentin sealing approach on microtensile bond strength (MTBS) of CAD/CAM composite to dentin. Occlusal surfaces of 36 human molars were ground to expose flat dentin and randomly assigned to 6 groups according to: (1) Adhesive curing mode [light-cured/LC (One coat 7 Universal, COLTENE); dual-cure/DC (One coat 7 Universal/Dual-cure Activator, COLTENE); and self-cure/SC (Palfique Universal Bond, Tokuyama); and (2) Dentin sealing approach (delayed sealing/DDS and immediate sealing/IDS). Following 1-week provisionalization, CAD/CAM composite blocks (Brilliant Crios, COLTENE), 4 mm 2 , were cemented over conditioned dentin surfaces. After 24 h, bonded assemblies were thermo-cycled for 5000 cycles. Specimens were tested for MTBS. Failure mode was analyzed under stereomicroscope. Data were statistically analyzed using ANOVA. DDS showed significantly higher MTBS values than IDS when using LC and DC adhesives. While, IDS produced significantly higher MTBS values than DDS when using SC adhesive. Predominant failure mode was adhesive in all groups, except for SC adhesive in IDS group, mixed failure was the predominant mode. Light- and dual-cured universal adhesives improved bond strength in delayed dentin sealing approach. Self-cure universal adhesive produced better bond strength when applied to immediately sealed dentin.
Associations of afternoon naps with progression of advanced cardiovascular-kidney-metabolic syndrome among Chinese adults aged 45 years and above
A method for characterizing and analyzing the structural behavior of concrete dams in cold regions
Abstract Aiming at the gross error and data missing in the monitoring sequence of concrete dam, the variational mode decomposition method and the gated recurrent unit depth learning algorithm are respectively used to extract the effective information of the monitoring sequence. On the basis of the research on the characteristics of the traditional concrete dam structural behavior characterization model, the paper explores the expression mode of the effect of cold wave, freeze-thaw, wintering layer and other influencing factors. In order to reflect the correlation between the monitoring measurement values, the space coordinate variable is introduced to establish the monitoring measurement change characterization model, so as to realize the characterization and analysis of the structural behavior changes of concrete dams in cold regions and the quantitative analysis of various influencing factors. Based on the research in this article, we can fully understand the operation status of the dam, identify hidden dangers, and carry out relevant risk investigation and reinforcement. It can reduce the risk of dam failure to a certain extent.
The effect of hepatic steatosis index on prediabetes: A large-scale retrospective cohort study
Pilot clinical comparison of three occlusal splint fabrication techniques: A preliminary study
Health impact assessment of decentralization of Emergency Medical Services: a case study in Chonburi Province, Thailand
Integrating multi-omics and clinical features to model survival in epithelial ovarian cancer subtypes
Abstract Epithelial ovarian cancer (EOC) exhibits significant heterogeneity in clinical outcomes, influenced by histology, age, stage, and molecular characteristics. This study aimed to develop and validate a comprehensive model integrating demographic, clinical, and molecular data from The Cancer Genome Atlas (TCGA) to predict two-year survival outcomes in EOC. The cohort included 2,427 patients with Endometrioid Adenocarcinoma (EA)s and Serous Cystadenocarcinoma (SC) , of whom 1,011 had gene data. Machine learning models, including Logistic Regression, Gradient Boosting Classifier (GBC), Support Vector Machines (SVM), and Random Forest, were trained and evaluated for predictive performance. SVM provided the optimal balance of mortality-class detection and overall performance. While GBC achieved the highest ROC-AUC (0.81), SVM demonstrated superior recall for mortality cases (0.70 vs. 0.61), which was prioritized given our clinical objective. Shapley Additive Explanations (SHAP) analyses revealed that WT1, HOXA11, TPM4, TMPRSS2, MUC16, SDHD, and MYC were the most influential predictors of mortality, along with age at diagnosis. Differential gene expression and enrichment analyses identified distinct age- and stage-associated molecular profiles, with genes involved in cell cycle regulation, tumor microenvironment, and growth factor signaling showing significant upregulation. Mutational analyses revealed histology-specific patterns, with TP53, PIK3CA, and ZFHX3 highly mutated in SC, while PTEN and ARID1A were more prevalent in EA. Several mutations, including TP53, FAT3, and FAT4 in EA, and CSMD3 in SC, were associated with poorer survival. Integrating multivariate predictive modeling with biological interpretation provides a comprehensive framework for personalized risk stratification and treatment decision-making in EOC. The identified prognostic biomarkers, such as TPM4, SDHD, MUC16, and BCL6, represent potential targets for future studies and therapeutic interventions.
Integrative analysis of pancreatic microbiota and metabolome in patients with pancreatic ductal adenocarcinoma
Non-invasive anemia detection from conjunctiva and sclera images using vision transformer with attention map explainability
Abstract Iron-deficiency anemia, a prevalent global health issue, traditionally requires invasive procedures for accurate diagnosis, such as a blood sample for measuring hemoglobin (Hgb) concentration. Nevertheless, this marker can be visually assessed by observing external anatomical elements, such as the eye’s conjunctiva and sclera. These regions often appear paler in anemic individuals, providing a visual sign of potential anemia. In this work, a non-invasive approach for anemia detection utilizing sclera-conjunctival images is presented. Using the Vision Transformer (ViT) model with a transfer learning approach, robust classification of anemia/no anemia is achieved. This methodology not only focuses on classification accuracy but also incorporates an explainability technique to provide visual insights into the decision-making process of the model. Experimental results demonstrated high accuracy, where an overall accuracy of 98.47% is achieved. The ViT model’s performance is compared against established machine learning and deep learning algorithms to evaluate its effectiveness in anemia detection. The analysis of the results indicates that the ViT model, with its ability to focus on relevant image features when analyzing the explainability results, offers a promising alternative for anemia detection, potentially reducing the need for invasive diagnostic procedures.
Mechanical properties of rock cutting by disc cutters and feasibility analysis of mechanical mining in Jinchuan No. 3 Mine with hard rock
Abstract Disc cutters are essential rock-cutting tools for Tunnel Boring Machines (TBMs), primarily used in hard rock excavation. However, TBMs are not suitable for mining actives due to limitations in size and flexibility. This study first investigates the mechanical properties of rock cutting by disc cutters, and then explores the feasibility of mechanical mining with disc cutter based hard rock mining machines. The ores in the Jinchuan No. 3 Mine represent to typical hard rockmass, with rock strength ranging from about 125 to 180 MPa. The mechanical properties of hard rock cutting are investigated by linear cutting machine (LCM) tests and numerical simulations, showing good consistency between experimental and simulation results. The laboratory results reveal maximum normal forces of 40 kN and 60 kN at penetration depths of 2 mm and 4 mm, respectively, with specific energy (SE) of 7.33 kWh/m 3 and 8.42 kWh/m 3 . The simulation results indicate maximum normal forces of 40 kN and 55 kN. Moreover, simulated crack propagation during rock cutting supports the tensile crack-dominant model, with crack characteristics closely matching existing theoretical analysis and experimental observations. During rock cutting, multiple semi-conical shaped cracks are generated, with their sizes initially decreasing before stabilizing. Simulation of rock cutting with double disc cutters identifies the optimal cutter spacing. Accordingly, a cutter arrangement approach for the wheel-type cutter head of hard rock mining machines is proposed. Finally, the feasibility of mechanical mining in the Jinchuan No. 3 Mine is discussed through estimating mining efficiency and proposing an innovative mining method.
Intelligent information management enables quality-by-design in pharmaceutical production
Point-of-care, Point-of-concern? A Commentary on What Ails Point-of-care Ultrasound Education
Next-generation UOWC enabling high-speed and secure RGB image transmission using IRSM-OCDMA with PSO-based image enhancement
Abstract Underwater Optical Wireless Communication systems face severe signal attenuation, scattering, and turbulence, which significantly degrade image transmission quality and limit the communication range. To address these challenges, this paper proposes a secure and high-capacity RGB image transmission framework based on Optical Code Division Multiple Access (OCDMA) using Identity Row Shift Matrix (IRSM) codes. The IRSM-OCDMA scheme enhances data confidentiality by assigning unique orthogonal codes to each user while supporting simultaneous multiuser transmission with an aggregate rate of up to 30 Gbps. System performance is analyzed across five water types: Pure Seawater (PS), Clear Ocean, Coastal Ocean, Harbour I, and Harbour II (HR II), covering a broad range of attenuation coefficients. Image quality is quantitatively evaluated using standard metrics including Root Mean Square Error, Signal-to-Noise Ratio, Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Correlation Coefficient. Two distinct post-processing methods are applied: median filtering for impulsive noise reduction and a Particle Swarm Optimization-based correction algorithm that adaptively restores image features under underwater channel conditions. Simulation results show a maximum transmission distance of 27 m in PS and 4 m in turbid HR II water, demonstrating the effectiveness of the proposed framework. The combination of IRSM coding with adaptive post-processing offers a robust solution for secure, high-quality image transmission in Internet of Underwater Things applications.