Search Results (836)

The effective management of municipal road infrastructure requires up-to-date, standardized and reliable condition information to support sustainable maintenance. While visual road-condition assessment methods based on established standards are widely applied to municipal roads, they remain largely manual, time-consuming, costly and subjective. This study presents an end-to-end workflow for the automated visual inspection and condition assessment of municipal road infrastructure using high-resolution, 3D street-level imagery acquired by professional mobile mapping systems. The proposed approach integrates an efficient preprocessing pipeline for precise road-surface extraction with deep learning models trained for the specific task and an advanced postprocessing method for robust results aggregation. For this purpose, a large dataset covering approximately 352 km of municipal roads across eight municipalities was created by combining street-level imagery with expert-annotated road-condition index (RCI) values. Two neural network variants were implemented: a regression model predicting standardized RCI values and a binary classifier distinguishing between roads requiring maintenance and those in good condition. To ensure decision-oriented outputs at the infrastructure-asset level, frame-based predictions are aggregated into homogeneous road segments using outlier detection and change-point analysis along the road axis. The regression model achieved a mean absolute error of 0.48 RCI values at frame level and 0.40 RCI values at road-segment level, outperforming conventional inter-expert variability, while the binary classification model reached an F1-score of 0.85. These findings demonstrate that AI-based visual road-condition assessment using professional mobile mapping data can provide accurate, standardized and scalable condition information for municipal road infrastructure. The proposed workflow supports maintenance prioritization and infrastructure management decisions without requiring explicit detection of individual pavement defects, offering a practical pathway toward automated, cost-effective road-condition monitoring. Full article

Sperm morphology is one of the most critical indicators of male fertility. This paper presents a deep learning-based approach to classify sperm cells into 18 morphological classes, including one normal and 17 abnormal types. Two state-of-the-art convolutional neural networks, EfficientNetV2-S and ResNet50V2, are employed and fine-tuned using a class-weighted loss function together with extensive data augmentation to improve generalization under class imbalance. Automatic mixed precision training is adopted to reduce memory consumption and accelerate the training process. An ensemble strategy is subsequently constructed by linearly fusing the logits of both architectures, where the fusion weight is optimized to maximize recall, precision, and overall F1-score. Experimental results show that the proposed ensemble achieves an overall accuracy of 70.94%, consistently outperforming the individual models. Sperm cells with pronounced structural abnormalities, such as PinHead and DoubleTail, are classified with high accuracy, whereas less visually distinctive defects result in comparatively lower performance. These findings demonstrate the potential of CNN-based ensemble models to provide consistent and reliable automated sperm morphology classification. Full article

Background/Objectives: Skin and soft tissue defects of the head and neck are common challenges in plastic surgery and require reconstruction strategies tailored to defect size and depth. This study aimed to evaluate the clinical application and outcomes of the hemi-keystone flap (KF) technique and its modifications for head and neck reconstruction. Methods: A retrospective cohort study was conducted on 50 patients (36 males, 14 females; aged 9–92 years) who underwent hemi-KF reconstruction between September 2020 and March 2024. Data were collected on defect characteristics, flap design, surgical time, complications, scar outcomes, and follow-up duration. Scar outcomes were assessed using the Patient and Observer Scar Assessment Scale (POSAS). Results: The mean defect and flap sizes were 4.68 ± 4.14 cm² and 11.79 ± 16.69 cm², respectively. Single original hemi-KFs were used in 60% of cases, and double hemi-KFs in 32%. The mean flap-surgery duration was 29.04 ± 14.56 min. Partial wound dehiscence occurred in 6% of cases. The mean follow-up period was 6.34 ± 5.43 months. The mean POSAS scores were 15.30 ± 3.59 (patient) and 17.12 ± 3.70 (observer), indicating favorable scar outcomes and patient satisfaction. Conclusions: The hemi-KF technique and its modifications are reliable and versatile options for head and neck reconstruction, offering favorable functional and aesthetic outcomes. Full article

Background: Focal chondral and osteochondral knee defects have limited intrinsic healing capacity and may progress toward post-traumatic osteoarthritis. Early post-operative inflammatory signaling may influence clinical recovery after cartilage repair. This prospective, single-center observational cohort study aimed to characterize short-term post-operative inflammatory biomarker profiles in synovial fluid and serum after AMIC and to assess associations with patient-reported outcomes over 12 months. Methods: Fifteen patients undergoing autologous matrix-induced chondrogenesis (AMIC) for focal knee chondral/osteochondral defects were prospectively enrolled. International Knee Documentation Committee (IKDC) and Lysholm scores were recorded pre-operatively and at 6 and 12 months. Synovial fluid and serum were collected intraoperatively, at 6 and 12 weeks post-operatively. Interleukin (IL)-1β, IL-1 receptor antagonist (IL-1RA), and IL-6 were quantified using multiplex flow luminescence immunoassay, and the total synovial fluid protein level was measured. Non-parametric repeated-measures testing and Spearman’s rank correlation were applied (p < 0.05). Results: IKDC and Lysholm scores improved from (30.6 ± 9.4) to (58.8 ± 15.0) and from (57.5 ± 18.6) to (78.2 ± 14.7), respectively, exceeding established minimal clinically important difference (MCID) thresholds. Synovial fluid IL-1β and IL-1RA increased significantly over time ((p = 0.01357) and (p = 0.03953), respectively); IL-1β remained elevated, whereas IL-1RA tended to decline after 6 weeks. IL-6 levels remained low throughout. Total synovial fluid protein increased significantly (p = 0.00043). No significant correlations were observed between corresponding biomarker levels in synovial fluid and serum. Higher IL-6 and a higher IL-1β/IL-1RA ratio were associated with poorer clinical improvement (ρ = −0.80, p < 0.05 and ρ = −0.580, p < 0.05, respectively). Conclusions: AMIC was associated with a sustained intra-articular inflammatory response despite favorable 12-month outcomes. Exploratory analyses suggest that inflammatory dysregulation—particularly involving IL-6 and IL-1β/IL-1RA balance—may be linked to less favourable clinical recovery. Synovial fluid measurements provided more relevant information on local joint biology than serum sampling. Full article

Reliable fault detection along transmission corridors is essential for preventing small defects from developing into long outages and costly emergency operations. This study aims to improve the field reliability of an open vocabulary vision language backbone without retraining the large model in an end-to-end manner. The work focuses on four operational fault classes in multi-region corridor imagery collected during routine inspections and uses a Florence-2 vision language model as the base recognizer. On top of this backbone, three domain-specific components are introduced. A subclass-aware fusion scheme keeps probability mass within the active parent concept so that insulator icing and conductor icing produce stable, action-oriented decisions. A Power-Line Focus Then Crop normalization uses an attention-guided corridor window together with isotropic resizing so that thin conductors and small fittings remain visible in the processed image. A corridor geo prior reduces scores as the distance from the mapped centerline increases and in this way suppresses detections that lie outside the corridor. All methods are evaluated under a shared preprocessing and scoring pipeline in training-free and parameter-efficient tuning modes. Experiments on unseen regions show higher accuracy for skinny and low-contrast faults, fewer false alarms outside the right-of-way, and improved score calibration in the confidence range used for triage, while keeping throughput and memory usage suitable for unmanned aerial vehicles and substation edge devices. Full article

Background/Objectives: Locally advanced midface malignant tumors require extensive resection, resulting in complex defects involving bone and multiple soft tissue structures. Reconstructing these substantial defects presents a significant challenge to restore both function and aesthetics. This study aims to compare the functional and aesthetic outcomes of chimeric free flaps versus single free flaps in midface microvascular reconstructions. Methods: This retrospective analysis included fifty consecutive patients with Type III Cordeiro defects who underwent midface reconstruction with free tissue transfer between 2020 and 2024. The cohort included fourteen patients who received prefabricated chimeric flaps and thirty-six patients who received single free flaps. Outcomes were assessed six months postoperatively using a modified University of Washington Quality of Life Questionnaire (UW-QOL), analyzing domains including speech, chewing, sensation, appearance, pain, and social activity. Statistical analysis was performed using the Mann–Whitney U test. Results: In the chimeric flap group, no major flap necrosis or complications were observed. In unadjusted comparisons, the chimeric flap group showed higher transformed UW-QOL scores in several domains. Statistically significant between-group differences were observed for opening and speech (p = 0.004), change in appearance (p = 0.022), sensation (p = 0.011), and social activity (p = 0.006). Aesthetic outcomes, assessed via patient rating of appearance, were also significantly higher in unadjusted comparisons with the chimeric flap approach. Furthermore, in Type IIIa defects, titanium mesh successfully provided reliable orbital support. Conclusions: Chimeric free flaps represent a feasible reconstructive option in selected cases of complex maxillary and midface reconstruction. Their main advantages—providing the proper amount of specific, well-vascularized tissue and offering greater mobility of components— may be associated with more favorable functional, aesthetic, and social outcomes in unadjusted comparisons compared to reconstruction using single free flaps. Full article

In the manufacturing of high-reliability components, sinusoidal wobble laser welding has gained preference due to its excellent performance. However, surface defect inspection for such welds is challenged by large variations in defect scales, the coexistence of multiple defects, and scarce samples, which collectively limit existing detection methods. To address these issues, this paper proposes a lightweight detection framework that integrates a generative adversarial network with an improved YOLO architecture. First, a frequency-domain-enhanced StyleGAN2-AFMS model is constructed to effectively augment high-quality defect samples. Second, a YOLO11n-WAFE detector is designed, which incorporates an ADownECA downsampling module to enhance the capability of capturing subtle defects and an Edge-Aware Semantic–Detail Fusion module to improve discriminative robustness under multi-defect conditions. To validate the approach, an industrial-level Sinusoidal Wobble Laser Weld Defect Dataset is built. Experiments reveal that the proposed framework boosts mAP@0.5 to 94.2% (an 8% improvement over the baseline) and mAP@0.5:0.95 to 77.4%, with an F1-score of 89.5%, while maintaining lightweight (2.15 M parameters) and fast (656 FPS) characteristics. This study provides a high-precision and efficient solution for few-shot industrial defect inspection. Full article

Background: Early diagnosis of familial hypercholesterolemia (FH) is crucial to improve long-term outcomes. FH diagnosis relies on elevated low-density lipoprotein cholesterol (LDL-C) levels, familial clinical characteristics, and identification of pathogenic variants in FH-related genes. Secondary factors, such as overweight and obesity, are known to influence lipid profiles in the general population. More recently, polygenic risk scores based on single-nucleotide polymorphisms (SNPs) have been proposed as additional determinants of LDL-C levels. Methods: We enrolled 214 pediatric subjects with LDL-C levels ≥95th percentile (after 6 months of dietary intervention) and with at least one parent with LDL-C levels ≥ 95th percentile. All participants underwent biochemical and auxological assessment and genetic testing for FH. In a subgroup of 60 subjects, LDL-C polygenic scores based on 6- and 12-SNPs were calculated. Results: Pathogenic variants confirming heterozygous FH were identified in 190 subjects (variant-positive, V+); 17 were variant-negative (V−), yielding a mutation detection rate of 91.8%. An additional seven patients carrying variants of uncertain significance were excluded from the primary analysis. LDL-C was modestly higher in V+ than V− subjects using both Friedewald (212 vs. 188 mg/dL; p = 0.035) and Martin–Hopkins formulas (208 vs. 187 mg/dL; p = 0.041), while the other main clinical and laboratory parameters were similar. In V+, LDL-C was higher in subjects with null variants, compared to those with defective variants. Body mass index (BMI SDS) was inversely correlated with HDL-C (p < 0.001), and obesity (BMI z-score > 2 SDS) was associated with lower HDL-C and higher LDL-C, non-HDL-C, and ApoB. With regard to the polygenic scores, 12- and 6-SNP scores showed overlap between V+ and V−, and published cut-offs did not discriminate lipid severity in our population; however, in V+ subjects, the 12-SNP score acted as a phenotype modifier, being independently associated with higher LDL-C and non-HDL-C levels after adjustment for age, sex, and BMI SDS. Conclusions: In children selected by LDL-C ≥ 95th percentile, together with autosomal dominant familial hypercholesterolemia, genetic confirmation of FH is achieved in the vast majority of cases. Variant type (null vs. defective), BMI, and polygenic background contribute to phenotypic heterogeneity, supporting the need to address other factors alongside genetic diagnosis. Further validation is needed before polygenic scores can be implemented in routine clinical practice. Full article

Linear array ultrasonic devices such as the MIRA A1040 are highly effective at detecting subsurface defects in concrete; however, interpretation of their data is time-consuming, subjective, and requires specialized expertise. This paper proposes a quantitative signal-processing framework that computes objective subsurface-quality Multi-Metric Scores derived from ultrasonic tomography B-scans. The framework integrates the Signal-to-Background Ratio, Energy Concentration Ratio, and Spatial Dispersion into a composite 0–100 scale. Laboratory testing demonstrated clear discrimination between control samples (scores 79–100) and specimens with intentionally placed voids (8–38) or honeycombing defects (6–35). Field validation confirmed similar separation using an acceptance threshold of 70. The proposed scoring methodology offers a practical, automated approach for real-time quality assessment of concrete pavements under realistic field construction conditions. Full article

Campanacci grade III giant cell tumors of the distal radius frequently require en bloc resection to achieve adequate oncologic control. Reconstruction of the resulting defect remains challenging, particularly with respect to preservation of distal radioulnar joint stability and forearm rotation. Although proximal fibular autograft reconstruction is well established, ligamentous stabilization of the distal radioulnar joint is rarely incorporated in oncologic settings. This technical note describes an integrated reconstructive strategy combining proximal fibular autograft with distal oblique bundle reconstruction, illustrated by a representative clinical case. The technique involves segmental en bloc resection of the distal radius followed by reconstruction using an ipsilateral, nonvascularized proximal fibular autograft including the fibular head. Distal radioulnar joint stability is addressed through reconstruction of the distal oblique bundle using an autologous palmaris longus tendon graft. Surgical indications, operative steps, donor site stabilization, and perioperative management are detailed. Functional evolution was assessed using the Musculoskeletal Tumor Society scoring system and range-of-motion measurements. Histopathological examination confirmed negative oncologic margins. Early postoperative events included donor-site common peroneal nerve dysfunction and radiocarpal instability requiring temporary Kirschner wire stabilization. At nine months, the Musculoskeletal Tumor Society score reached 80%, with forearm rotation preserved at 68.8% pronation and 81.3% supination of normal values. Combined osseous and ligamentous reconstruction following distal radius resection is technically feasible and may allow preservation of distal forearm mechanics while maintaining oncologic principles. Broader validation will require application in larger clinical series and longer follow-up. Full article

Laser metal deposition operates on the principle of layer-by-layer material addition, wherein each layer is formed by overlapping individual single tracks. Consequently, clads formed serve as the fundamental building blocks for this technology. Their quality directly affects the overall build quality, particularly the geometric characteristics, which are also critical to process productivity. In the present work, geometric characteristics of TiC/Ti6Al4V single tracks fabricated via laser metal deposition are optimised. An artificial neural network model was developed to predict the clad width, height, and dilution using processing parameters, laser power, scan speed, and powder feed rate, as model inputs. The Particle Swarm Optimisation algorithm was employed for hyperparameter selection. The hyperparameter-optimised model achieved a mean squared error of 0.00183 and an R² score of 0.979 during training, and a mean squared error of 0.00709 and an R² score of 0.887 during testing. Although the small discrepancy between training and testing metrics suggests slight overfitting, likely due to the size of the dataset, the model achieved a mean absolute percentage error of less than 10% during testing. Subsequently, process plots generated by the model predictions were used to identify suitable parameters, and a processing map was developed to highlight the window that achieves suitable dilution (14–24%), defect-free sound bonding, and thick and dense clads. Full article

Partial discharge (PD) signals in gas-insulated switchgear (GIS) exhibit complex characteristics, and single-modal feature recognition methods face limitations in achieving satisfactory diagnostic accuracy due to incomplete fault information representation. This paper proposes a multi-modal fault diagnosis framework that effectively integrates complementary information from different sensing modalities to improve defect identification performance. First, PRPD time-domain statistical features from HFCT measurements and frequency-domain features from UHF signals are extracted to construct a comprehensive hybrid feature set. Z-score normalization is applied to eliminate scale differences between heterogeneous features. Principal component analysis (PCA) is then employed for dimensionality reduction, preserving essential discriminative information while removing redundancy. Finally, a ResNet-MLP classifier with skip connections is designed to enhance nonlinear feature extraction and alleviate gradient vanishing problems in deep network training. Experimental validation on four typical defect types—protrusion defect, floating discharge, metal particle discharge, and surface discharge on insulator—demonstrates that the proposed method achieves 99.38% classification accuracy on the test set, with consistently high precision, recall, and F1-score across all categories. The proposed approach significantly outperforms standard MLP without residual connections, achieving 98.94% ± 0.49% accuracy compared to 95.47% ± 3.72% over 20 independent runs, demonstrating superior diagnostic accuracy and generalization capability for GIS insulation fault diagnosis. Full article

Background/Objectives: Non-carious cervical lesions (NCCLs) are common defects in adults that can lead to dentin hypersensitivity and aesthetic concerns, for which composite resin restorations currently represent the gold standard of care. However, evidence regarding the long-term clinical superiority of high-filled injectable composites and Er,Cr:YSGG laser-based cavity preparation remains limited. The present study aimed to compare the 1-year clinical performance of two different surface preparation protocols (Er,Cr:YSGG laser vs. conventional bur preparation with phosphoric acid etching) and two composite resin types (high-filled injectable vs. conventional paste-type) in the restoration of NCCLs. Methods: In this prospective, split-mouth, randomized controlled clinical trial, a total of 168 NCCLs in 27 patients were restored. Lesions were randomly allocated to four groups according to the combination of surface preparation (Er,Cr:YSGG laser or phosphoric acid etching) and high-filled injectable composite (G-ænial Universal Injectable) or paste-type composite (G-ænial Anterior). The same universal adhesive system was used in all cases. Clinical evaluations were performed by a blinded examiner at 1 week, 6 months, and 12 months, using the FDI World Dental Federation criteria. Results: At the 1-year follow-up, 25 patients and 150 restorations were available for evaluation, corresponding to a recall rate of 98.22%. High clinical acceptability was observed in all groups with respect to aesthetic, functional, and biological parameters. Retention was 100% in the acid-etched paste-type composite group and ranged from 94.7% to 97.4% in the remaining groups, with no statistically significant differences among groups (p > 0.05). A transient increase in postoperative sensitivity was detected in the laser groups at the 1-week evaluation (p = 0.026); however, sensitivity scores declined to zero in all groups at 6 months and 1 year. Conclusions: High-filled injectable composites demonstrated 1-year clinical performance comparable to that of conventional paste-type composites in the restoration of NCCLs. Er,Cr: YSGG laser-based cavity conditioning produced outcomes similar to conventional phosphoric acid etching with respect to retention, marginal adaptation, and biological compatibility. The early increase in laser-related postoperative sensitivity was transient and did not compromise long-term clinical success. Taken together, the ease of application and favorable clinical performance of injectable composites indicate that these materials constitute a reliable alternative for the restoration of non-carious cervical lesions. Full article

The S-100 standard for Electronic Chart Display and Information Systems (ECDIS) uses Lua scripts to render electronic charts, yet lacks security specifications for script execution. This paper evaluates automated Static Application Security Testing (SAST) tools versus expert manual review for S-100-compliant software. Four SAST tools were applied alongside an expert review of OpenS100, a reference implementation for next-generation ECDIS. While automated tools identified numerous defects, they failed to detect 83% (19/23) of expert-identified vulnerabilities, including an unrestricted Lua interpreter flaw with a Common Vulnerability Scoring System (CVSS) score of 9.3. This vulnerability enables Remote Code Execution (RCE) via malicious portrayal catalogues, verified through Proof of Concept (PoC) development. The analysis demonstrates that SAST tools are constrained by limited maritime domain knowledge and challenges in analyzing cross-language semantic risks at the C++–Lua interface. The findings establish that identified vulnerabilities stem from specification gaps in the S-100 standard rather than isolated coding errors. These results indicate that functional safety certifications require supplementation to address design-level security risks. The evidence supports that the International Hydrographic Organization (IHO) incorporate security controls, such as script sandboxing and library restrictions, into the S-100 framework before the 2029 mandatory adoption deadline. Full article

Semiconductor defect inspection is frequently hindered by data scarcity and the resulting class imbalance in supervised learning. This study proposes a CycleGAN-based data augmentation pipeline designed to synthesize realistic defective CD-SEM images from abundant normal patterns, incorporating a quantitative quality control mechanism. Using an ADI CD-SEM dataset, we conducted a sensitivity analysis by cropping original 1024 × 1024 micrographs into 512 × 512 and 256 × 256 inputs. Our results indicate that increasing the effective defect-area ratio is critical for improving generative stability and defect visibility. To ensure data integrity, we applied a screening protocol based on the Structural Similarity Index (SSIM) and a median absolute deviation noise metric to exclude low-fidelity outputs. When integrated into the training of XceptionNet classifiers, this filtered augmentation strategy yielded substantial performance gains on a held-out test set, specifically improving the Recall and F1 score while maintaining a near-ceiling AUC. These results demonstrate that controlled CycleGAN augmentation, coupled with objective quality filtering, effectively mitigates class imbalance constraints and significantly enhances the robustness of automated defect detection. Full article