Search Results (2,865)

Retinal vessel segmentation in fundus images is critical for diagnosing microvascular and ophthalmologic diseases. However, the task remains challenging due to significant vessel width variation and low vessel-to-background contrast. To address these limitations, we propose WDM-UNet, a novel spatial-wavelet dual-domain fusion architecture that integrates spatial and wavelet-domain representations to simultaneously enhance the local detail and global context. The encoder combines a Deformable Convolution Encoder (DCE), which adaptively models complex vascular structures through dynamic receptive fields, and a Wavelet Convolution Encoder (WCE), which captures the semantic and structural contexts through low-frequency components and hierarchical wavelet convolution. These features are further refined by a Gated Fusion Transformer (GFT), which employs gated attention to enhance multi-scale feature integration. In the decoder, depthwise separable convolutions are used to reduce the computational overhead without compromising the representational capacity. To preserve fine structural details and facilitate contextual information flow across layers, the model incorporates skip connections with a hierarchical fusion strategy, enabling the effective integration of shallow and deep features. We evaluated WDM-UNet in three public datasets: DRIVE, STARE, and CHASE_DB1. The quantitative evaluations demonstrate that WDM-UNet consistently outperforms state-of-the-art methods, achieving 96.92% accuracy, 83.61% sensitivity, and an 82.87% F1-score in the DRIVE dataset, with superior performance across all the benchmark datasets in both segmentation accuracy and robustness, particularly in complex vascular scenarios. Full article

Computer vision techniques such as three-dimensional digital image correlation (3D-DIC) and three-dimensional point tracking (3D-PT) have demonstrated broad applicability for monitoring the conditions of large-scale engineering systems by reconstructing and tracking dynamic point clouds corresponding to the surface of a structure. Accurate stereophotogrammetry measurements require the stereo cameras to be calibrated to determine their intrinsic and extrinsic parameters by capturing multiple images of a calibration object. This image-based approach becomes cumbersome and time-consuming as the size of the tested object increases. To streamline the calibration and make it scale-insensitive, a multi-sensor system embedding inertial measurement units and a laser sensor is developed to compute the extrinsic parameters of the stereo cameras. In this research, the accuracy of the proposed sensor-based calibration method in performing stereophotogrammetry is validated experimentally and compared with traditional approaches. Tests conducted at various scales reveal that the proposed sensor-based calibration enables reconstructing both static and dynamic point clouds, measuring displacements with an accuracy higher than 95% compared to image-based traditional calibration, while being up to an order of magnitude faster and easier to deploy. The novel approach has broad applications for making static, dynamic, and deformation measurements to transform how large-scale structural health monitoring can be performed. Full article

Introduction: Finger injuries are common in pediatric patients and typically heal well with conservative management. However, rare fracture patterns involving significant displacement and physeal injury, such as the one described in this case, require specialized surgical intervention to ensure proper healing and prevent long-term complications. Case Presentation: A 12-year-old left-hand-dominant female presented with pain, swelling, and deformity at the distal interphalangeal (DIP) joint following hyperextension of the left fifth digit. Initial radiographs revealed a volar displaced intra-articular fracture with physis involvement, confirmed by computed tomography (CT) imaging. Conservative management with closed reduction and splinting failed to achieve adequate alignment. Surgical intervention was performed via a dorsal approach, utilizing ORIF with K-wire fixation to restore joint congruity and ensure anatomic alignment. Outcomes: Postoperative follow-up demonstrated satisfactory healing, maintained reduction, and resolution of pain with no complications. The patient regained functional use of the digit with minimal stiffness, and the growth plate remained uninvolved during the recovery period. Discussion: This case underscores the importance of advanced imaging, early referral, and tailored surgical intervention for rare mallet fractures involving volar displacement and physeal injury. ORIF provided reliable stabilization and optimal outcomes in this complex case. Conclusions: Volar displaced Salter–Harris III fractures of the DIP joint are rare and challenging injuries in pediatric patients. This case highlights the role of ORIF in achieving successful outcomes and emphasizes the importance of precise reduction and stabilization to prevent long-term complications. Full article

The growing use of remote-sensing technologies has placed greater demands on object-detection algorithms, which still face challenges. This study proposes a hierarchical adaptive feature aggregation network (HAF-YOLO) to improve detection precision in remote-sensing images. It addresses issues such as small object size, complex backgrounds, scale variation, and dense object distributions by incorporating three core modules: dynamic-cooperative multimodal fusion architecture (DyCoMF-Arch), multiscale wavelet-enhanced aggregation network (MWA-Net), and spatial-deformable dynamic enhancement module (SDDE-Module). DyCoMF-Arch builds a hierarchical feature pyramid using multistage spatial compression and expansion, with dynamic weight allocation to extract salient features. MWA-Net applies wavelet-transform-based convolution to decompose features, preserving high-frequency detail and enhancing representation of small-scale objects. SDDE-Module integrates spatial coordinate encoding and multidirectional convolution to reduce localization interference and overcome fixed sampling limitations for geometric deformations. Experiments on the NWPU VHR-10 and DIOR datasets show that HAF-YOLO achieved mAP50 scores of 85.0% and 78.1%, improving on YOLOv8 by 4.8% and 3.1%, respectively. HAF-YOLO also maintained a low computational cost of 11.8 GFLOPs, outperforming other YOLO models. Ablation studies validated the effectiveness of each module and their combined optimization. This study presents a novel approach for remote-sensing object detection, with theoretical and practical value. Full article

Temperature dependence of the deformation behavior and the residual stress in 304 stainless steel beams with single-sided Al₂O₃ coatings of varying thicknesses are analyzed using the image relative method. The results demonstrate that, due to the mismatch of thermal expansion coefficient between the coating and substrate, residual stresses were produced, which caused the bending deformation of the single-side coated specimens. Moreover, coating thickness significantly influences the deformation behavior of specimens. Within the elastic deformation regime, the single-side coated specimens would exhibit alternating bending and flattening deformations in response to the fluctuations of temperature. The higher ratio of the coating thickness to the substrate thickness is, the smaller bending curvature of specimens becomes, and the lower residual compressive stresses in the coating are. For the specimens undergoing elastic deformation, residual stresses can be effectively calculated through the Stoney’s formula. However, as the thickness of coating is close to that of substrate (the corresponding specimens would be regarded as the laminated composites), plastic deformation occurs. And the residual stresses in those specimens vary along the direction of the thickness and the length. In addition, the residual stress decreased with increasing temperature because of the stress relaxation. Full article

Experimental and simulation analysis was conducted on the effects of 532 nm nanosecond laser-induced thermal damage on the front-side illuminated CMOS detector. The study examined CMOS detector output images at different stages of damage, including point damage, line damage, and complete failure, and correlated these with microscopic structural changes observed through optical and scanning electron microscopy. A finite element model was used to study the thermal–mechanical coupling effect during laser irradiation. The results indicated that at a laser energy density of 78.9 mJ/cm², localized melting occurs within photosensitive units in the epitaxial layer, manifesting as an irreversible white bright spot appearing in the detector output image (point damage). When the energy density is further increased to 241.9 mJ/cm², metal routings across multiple pixel units melt, resulting in horizontal and vertical black lines in the output image (line damage). Upon reaching 2005.4 mJ/cm², the entire sensor area failed to output any valid image due to thermal stress-induced delamination of the silicon dioxide insulation layer, with cracks propagating to the metal routing and epitaxial layers, ultimately causing structural deformation and device failure (complete failure). Full article

Enhancing the wear resistance of structural steels used in demanding industrial applications is critical for extending components’ lifespan and ensuring mechanical reliability. In this study, we investigated the influence of flux-cored arc welding (FCAW) hardfacing on the tensile behavior of S355MC steel. Protective Fe-Cr-C alloy layers were deposited in one and two successive passes using automated FCAW, followed by tensile testing of specimens oriented at varying angles relative to the weld bead direction. The methodology integrated 3D scanning and digital image correlation to accurately capture geometric and deformation parameters. The experimental results revealed a consistent reduction in tensile strength and ductility in all the welded configurations compared to the base material. The application of the second weld layer further intensified this effect, while specimen orientation influenced the degree of mechanical degradation. Microstructural analysis confirmed carbide refinement and good adhesion, but also identified welding-induced defects and residual stresses as factors that contributed to performance loss. The findings highlight a clear trade-off between improved surface wear resistance and compromised structural properties, underscoring the importance of process optimization. Strategic selection of welding parameters and bead orientation is essential to balance functional durability with mechanical integrity in industrial applications. Full article

Background: Breast and hematological cancer treatments, especially with anthracyclines, have been shown to be associated with an increased risk of cardiotoxicity (CTX). An accurate prediction of cardiotoxicity risk and early detection of myocardial injury may allow for effective cardioprotection to be instituted and tailored to reverse cardiac dysfunction and prevent the discontinuation of essential cancer treatments. Objectives: The PRoactive Evaluation of Function to Evade Cardio Toxicity (PREFECT) study sought to evaluate the ability of fast-strain-encoded (F-SENC) cardiac magnetic resonance imaging (CMR) and 2D echocardiography (2D Echo) to stratify patients at risk of CTX prior to initiating cancer treatment, detect early signs of cardiac dysfunction, including subclinical CTX (sub-CTX) and CTX, and monitor for recovery (REC) during cardioprotective therapy. Methods: Fifty-nine patients with breast cancer or lymphoma were prospectively monitored for CTX with F-SENC CMR and 2D Echo over at least 1 year for evidence of cardiac dysfunction during anthracycline based chemotherapy. F-SENC CMR also monitored myocardial deformation in 37 left ventricular (LV) segments to obtain a MyoHealth risk score based on both longitudinal and circumferential strain. Sub-CTX and CTX were classified based on pre-specified cardiotoxicity definitions. Results: CTX was observed in 9/59 (15%) and sub-CTX in 24/59 (41%) patients undergoing chemotherapy. F-SENC CMR parameters at baseline predicted CTX with a lower LVEF (57 ± 5% vs. 61 ± 5% for all, p = 0.05), as well as a lower MyoHealth (70 ± 9 vs. 79 ± 11 for all, p = 0.004) and a worse global circumferential strain (GCS) (−18 ± 1 vs. −20 ± 1 for all, p < 0.001). Pre-chemotherapy MyoHealth had a higher accuracy in predicting the development of CTX compared to CMR LVEF and 2D Echo LVEF (AUC = 0.85, 0.69, and 0.57, respectively). The 2D Echo parameters on baseline imaging did not stratify CTX risk. F-SENC CMR obtained good or excellent images in 320/322 (99.4%) scans. During cancer treatment, MyoHealth had a high accuracy of detecting sub-CTX or CTX (AUC = 0.950), and the highest log likelihood ratio (indicating a higher probability of detecting CTX) followed by F-SENC GLS and F-SENC GCS. CMR LVEF and CMR LV stroke volume index (LVSVI) also significantly worsened in patients developing CTX during cancer treatment. Conclusions: F-SENC CMR provided a reliable and accurate assessment of myocardial function during anthracycline-based chemotherapy, and demonstrated accurate early detection of CTX. In addition, MyoHealth allows for the robust identification of patients at risk for CTX prior to treatment with higher accuracy than LVEF. Full article

Our understanding of foreland basin subsurface structures relies heavily on seismic reflection data. The seismic profile across the eastern Rioni foreland basin in western Georgia is critical for characterizing its deformation structural style. We applied fault-related folding and thrust wedge theories to interpret the seismic profile and construction structural cross-section, which reveals that compressional structures are controlled by multiple detachment levels. Both thin-skinned and thick-skinned structures are identified. The seismic profile and structural cross-section reveal the presence of normal faults, reverse faults, thrust faults, duplexes, triangle zone, and crustal-scale duplexes. The deep-level detachment within the basement is responsible for the development of the crustal-scale duplexes. These structures appear to have formed through the reactivation of pre-existing normal faults during compressive deformation. Based on our interpretation, the imaged duplex system likely represents the western subsurface continuation of the Dzirula Massif. Full article

Accurate detection of maize tassels plays a crucial role in yield estimation of maize in precision agriculture. Recently, UAV and deep learning technologies have been widely introduced in various applications of field monitoring. However, complex field backgrounds pose multiple challenges against the precision detection of maize tassels, including maize tassel multi-scale variations caused by varietal differences and growth stage variations, intra-class occlusion, and background interference. To achieve accurate maize tassel detection in UAV images under complex field backgrounds, this study proposes an MSMT-RTDETR detection model. The Faster-RPE Block is first designed to enhance multi-scale feature extraction while reducing model Params and FLOPs. To improve detection performance for multi-scale targets in complex field backgrounds, a Dynamic Cross-Scale Feature Fusion Module (Dy-CCFM) is constructed by upgrading the CCFM through dynamic sampling strategies and multi-branch architecture. Furthermore, the MPCC3 module is built via re-parameterization methods, and further strengthens cross-channel information extraction capability and model stability to deal with intra-class occlusion. Experimental results on the MTDC-UAV dataset demonstrate that the MSMT-RTDETR significantly outperforms the baseline in detecting maize tassels under complex field backgrounds, where a precision of 84.2% was achieved. Compared with Deformable DETR and YOLOv10m, improvements of 2.8% and 2.0% were achieved, respectively, in the mAP₅₀ for UAV images. This study proposes an innovative solution for accurate maize tassel detection, establishing a reliable technical foundation for maize yield estimation. Full article

Mycosis is caused by, among other factors, filamentous fungi, ubiquitous molds belonging to Aspergillus spp. which are often opportunistic pathogens. Over 100 species of Aspergillus have been described. The most common species responsible for diseases in humans and animals are Aspergillus fumigatus and Aspergillus niger, with Aspergillus flavus and Aspergillus clavatus being somewhat rarer. Aspergillus causes a range of diseases, from localized colonization and hypersensitivity reactions, through chronic necrotizing infections, to rapidly progressing angioinvasion and dissemination, leading to death. Testicular mycosis is extremely rarely described in both humans and animals. No studies in the literature report a simultaneous occurrence of testicular tumors and fungal infection of the organ, so the aim of this paper was to describe, for the first time, a case of two independent testicular tumors coexisting with testicular mycosis. A histopathological examination was performed on the left testicle of a male dog, specifically a mixed-breed dog resembling a husky weighing 22 kg and with an age of 8 years. Bilateral orchidectomy was performed for medical reasons due to the altered outline of the left testicle, leading to scrotal deformation. The dog did not show any clinical signs of illness, and the testicles were not painful. The right testicle, according to the operating veterinarian, showed no macroscopic changes, so histopathological verification was not performed. Microscopic imaging of the changes clearly indicated the coexistence of a tumor process involving Leydig cells (Leydigoma, interstitial cell tumor, ICT), Sertoli cells (Sertolioma), and fungal infection of the testis. The case suggests the possibility of the coexistence of tumor processes, which may have impaired local immune response of the tissue, with an infectious, in this case fungal, inflammatory process. Based on the literature, this paper is the first report on the occurrence of two independent histotype testicular tumors and their associated mycosis. Full article

Orthognathic surgery (OS) is a complex procedure commonly used to treat dentofacial deformities (DFDs). These conditions, related to jaw position or size and often involving malocclusion, affect approximately 15% of the population. Due to the complexity of OS, accurate planning is essential. Digital assessment using computer-aided design (CAD) and computer-aided manufacturing (CAM) tools enhances surgical predictability. However, limitations in soft tissue simulation often require surgeon input to optimize aesthetic results and minimize surgical impact. This study aimed to evaluate the accuracy of virtual surgery planning (VSP) by analyzing the relationship between planning deviations and surgical satisfaction. A single-center, retrospective study was conducted on 16 patients who underwent OS at San Pedro University Hospital of La Rioja. VSP was based on CT scans using Dolphin Imaging software (v12.0, Patterson Dental, St. Paul, MN, USA) and surgeries were guided by VSP-designed occlusal splints. Outcomes were assessed using the Orthognathic Quality of Life (OQOL) questionnaire and deviations were measured through pre- and postoperative imaging. The results showed high satisfaction scores and good overall outcomes, despite moderate deviations from the virtual plan in many cases, particularly among Class II patients. A total of 63% of patients required VSP modifications due to poor soft tissue fitting, with 72% of these being Class II DFDs. Most deviations involved less maxillary advancement than planned, while maintaining optimal occlusion. This suggests that VSP may overestimate advancement needs, especially in Class II cases. No significant differences in satisfaction were observed between patients with low (<2 mm) and high (>2 mm) deviations. These findings support the use of VSP as a valuable planning tool for OS. However, surgeon experience remains essential, especially in managing soft tissue behavior. Improvements in soft tissue prediction are needed to enhance accuracy, particularly for Class II DFDs. Full article

Canvas paintings are prone to biodeterioration due to their complex chemical composition, which can support fungal growth even under controlled conditions. This study evaluated the susceptibility of common synthetic restoration materials—Lascaux glues (303 HV, 498 HV), Acrylharz P550, BEVA 371, Laropal A81, and Regalrez 1094—to degradation by fourteen xerotolerant/xerophilic fungal strains. All tested Aspergillus and Penicillium species extensively colonized, especially artificially aged materials. FTIR-PAS analysis revealed chemical changes in carbonyl and C–H bonds in Laropal A81 and Regalrez 1094 colonized by Aspergillus spp. Scanning electron microscopy (SEM) imaging showed thinning of Lascaux glues and deformation of Regalrez 1094. Transcriptomic profiling of A. puulaauensis grown on Lascaux 498 HV and Regalrez 1094 identified altered expression of genes coding for esterases and oxidases, enzymes involved in synthetic polymer degradation. Esterase activity assays using 4-nitrophenol-based substrates confirmed significant enzymatic activity correlating with the presence of ester bonds. These findings highlight the vulnerability of synthetic restoration materials, specifically Laropal A81, Regalrez 1094, and Lascaux glues, to extremophilic fungi thriving in environments with low water activity. The results emphasize the urgent need for specific knowledge on fungi and their metabolic pathways to use/develop more durable conservation materials and strategies to protect cultural heritage objects from biodeterioration. Full article

The management of adult spinal deformity (ASD) has evolved dramatically over the past century, transitioning from external bracing and in situ fusion to complex, technology-driven surgical interventions. This review traces the historical development of spinal deformity correction and highlights contemporary enabling technologies that are redefining the surgical landscape. Advances in stereoradiographic imaging now allow for precise, low-dose three-dimensional assessment of spinopelvic parameters and segmental bone density, facilitating individualized surgical planning. Robotic assistance and intraoperative navigation improve the accuracy and safety of instrumentation, while patient-specific rods and interbody implants enhance biomechanical conformity and alignment precision. Machine learning and predictive modeling tools have emerged as valuable adjuncts for risk stratification, surgical planning, and outcome forecasting. Minimally invasive deformity correction strategies, including anterior column realignment and circumferential minimally invasive surgery (cMIS), have demonstrated equivalent clinical and radiographic outcomes to traditional open surgery with reduced perioperative morbidity in select patients. Despite these advancements, complications such as proximal junctional kyphosis and failure remain prevalent. Adjunctive strategies—including ligamentous tethering, modified proximal fixation, and vertebral cement augmentation—offer promising preventive potential. Collectively, these innovations signal a paradigm shift toward precision spine surgery, characterized by data-informed decision-making, individualized construct design, and improved patient-centered outcomes in spinal deformity care. Full article

Ensuring the structural safety of steel trusses in escalators is critical for the reliable operation of vertical transportation systems. While manual inspection remains widely used, its dependence on human judgment leads to extended cycle times and variable defect-recognition rates, making it less reliable for identifying subtle surface imperfections. To address these limitations, a novel context-aware, multi-scale deep learning framework based on the YOLOv5 architecture is proposed, which is specifically designed for automated structural defect detection in escalator steel trusses. Firstly, a method called GIES is proposed to synthesize pseudo-multi-channel representations from single-channel grayscale images, which enhances the network’s channel-wise representation and mitigates issues arising from image noise and defocused blur. To further improve detection performance, a context enhancement pipeline is developed, consisting of a local feature module (LFM) for capturing fine-grained surface details and a global context module (GCM) for modeling large-scale structural deformations. In addition, a multi-scale feature fusion module (MSFM) is employed to effectively integrate spatial features across various resolutions, enabling the detection of defects with diverse sizes and complexities. Comprehensive testing on the NEU-DET and GC10-DET datasets reveals that the proposed method achieves 79.8% mAP on NEU-DET and 68.1% mAP on GC10-DET, outperforming the baseline YOLOv5s by 8.0% and 2.7%, respectively. Although challenges remain in identifying extremely fine defects such as crazing, the proposed approach offers improved accuracy while maintaining real-time inference speed. These results indicate the potential of the method for intelligent visual inspection in structural health monitoring and industrial safety applications. Full article