Search Results (173)

Background/Objectives: Anthracycline-induced cardiotoxicity remains a major challenge in cancer treatment, and researchers are showing interest in artificial intelligence (AI) to improve the prediction and detection of cancer therapy-related cardiac dysfunction (CTRCD). Current surveillance strategies rely mainly on left ventricular ejection fraction and, more recently, global longitudinal strain. Methods: The present study was designed to evaluate cardiac performance in a rat model of doxorubicin-induced cardiotoxicity and empagliflozin-mediated cardioprotection using a machine learning-based analytical framework. Eighteen adult male Sprague–Dawley rats were assigned to five experimental groups. We aimed to quantify ventricular wall dynamics and contractility using an advanced image-processing and object-detection model that has not been previously used to distinguish normal from impaired cardiac kinetics. During real-time recording, simultaneous electrocardiogram monitoring was performed, enabling direct correlation between deep learning-based ventricular wall motion metrics and cardiac electrical activity. The cardioprotective effects of empagliflozin were further validated by immunofluorescence staining (cTnI, vimentin, α-SMA, and Cx43) of rat cardiomyocytes and paraffin-embedded cardiac tissue, demonstrating attenuation of cellular injury and structural remodeling. Results: The integrated analysis of cardiac kinetic patterns derived via machine learning distinguishes not only extreme cardiotoxicity, but also tracks a graded pattern consistent with ECG-derived severity and treatment-related functional preservation. These findings indicate that the algorithm captures the gradient of empagliflozin’s cardioprotective effect within this internally validated preclinical setting. Additionally, immunofluorescence results validated the benefits of SGLT2 inhibition on myocardial integrity. Conclusions: The novelty of the present work lies at the intersection of advanced cardiac kinetic analysis using AI, preclinical modeling, and SGLT2-mediated cardioprotection in cardio-oncology. Full article

This paper presents a prototype for an assistive navigation system that integrates three-dimensional audio spatialization with computer vision to improve the mobility of visually impaired individuals. The system uses stereoscopic depth perception and real-time point cloud reconstruction alongside a modified YOLO convolutional neural network for object detection and auralization techniques with head-related impulse response functions. Twenty participants (ten who were visually impaired and ten who were blindfolded) navigated controlled obstacle scenarios while wearing a chest-mounted camera and specialized headphones. The prototype achieved 95.00% precision in object classification across eleven obstacle categories and a 33.19% recall, indicating conservative detection behavior. The processing efficiency was 0.042489 s per image, which exceeds real-time requirements. User evaluation revealed an average collision rate of 0.5 per scenario and a mean completion time of 48 s. Statistical analysis showed no significant difference in collision rates between participant groups ($p=0.172$), though visually impaired participants demonstrated faster completion times ($p=0.003$). Integrating segmented, convolution-based audio processing with stereoscopic depth estimation enabled users to perceive obstacle locations through spatial sound cues, establishing a foundation for advancing assistive navigation technologies without extensive training. Full article

Micro-scale counter-rotating wind turbines (CRWTs) offer enhanced potential for wake energy recovery. This study proposes an integrated cascade–coupling design framework for high-solidity CRWTs, in which rear rotor geometry and rotor coupling are co-designed based on stereoscopic particle image velocimetry measurements of the front rotor wake. Experiments are conducted at a tip-speed ratio of $\lambda =1.0$, solidity $\sigma =1.25$, spacing ratios of $d=0.6R_T$, $1.0R_T$, and $3.0R_T$, and a tip radius of $R_T=70$ mm. At the physical limit spacing of $d=0.6R_T$, the integrated design increases the system power coefficient by 24.1% while limiting front rotor power reduction to 17.2%, compared to a 10.3% system gain and 34.5% front rotor suppression for the baseline mirrored configuration. Wake measurements confirm near-complete absorption of rotational kinetic energy from the front rotor wake without exacerbating upstream interference. These results demonstrate that cascade-based energy extraction and coupling-based interference mitigation can operate synergistically, enabling compact, high-performance micro-scale CRWTs suitable for space-constrained and urban energy applications. Full article

Free space detection in assisted driving applications is essential to provide information to vehicles about traversable surfaces and potential obstacles to be avoided. The current trend in free space detection favors the use of deep learning techniques. However, Deep Neural Networks require extensive training that considers as many scenarios as possible, which makes it difficult to create a model that can be generalized to all types of surfaces. Additionally, their lack of explainability contrasts with the growing interest in geometrically grounded and safety-oriented design principles for autonomous vehicle systems. To address these limitations, we propose a geometric approach that incorporates coplanarity conditions and normal vector estimation, removing the dependence on datasets for different types of surfaces. Additionally, the stereoscopic images are clustered in superpixels. The use of images clustered in superpixels allows us to obtain shorter processing times, in addition to taking advantage of the spatial and color information provided by the superpixels to increase the robustness of the three-dimensional reconstruction of the scene. Experimental results show that the proposed superpixel-based approach achieves competitive performance compared to unsegmented dense stereo methods, while significantly reducing algorithmic complexity. These results demonstrate the viability of integrating superpixel clustering into stereo-based free space estimation frameworks. Full article

Background: In maxillofacial reconstruction, even small inaccuracies can compromise aesthetics, function, and safety. Surgeons currently rely on preoperative imaging; however, recent advances in intraoperative imaging now provide three-dimensional, real-time guidance, possibly enhancing surgical outcomes. This review evaluates the current application of intraoperative imaging in maxillary and mandibular surgery including its impact on accuracy, efficiency, and outcomes. Methods: Two separate systematic reviews (PROSPERO CRD420251125497, CRD420251124600), analyzing maxillary and mandibular repair were conducted through Cochrane, Medline, Embase, and Web of Science. Both reviews adhered to the PRISMA guidelines. Inclusion criteria encompassed intraoperative digital imaging or navigation in maxillary or mandibular surgery. Studies without human subjects, intraoperative imaging, or the surgery of interest were excluded. Bias was assessed with NIH Quality Assessment. Results: A combined total of 795 publications were screened, with 35 studies ultimately included in this review, encompassing 1643 patients. Techniques included intraoperative computed tomography (CT) (n = 12, 34.3%), stereotactic navigation (n = 16, 45.7%), augmented reality (n = 2, 5.7%), ultrasound, fluoroscopy, infrared stereoscopic and electromagnetic (n = 1, 2.9%, each). The most common indication for surgery was fracture repair. Reporting was heterogeneous, with variable metrics and reporting for accuracy, complications, and revisions. Overall, cone-beam CT (CBCT) and stereotactic navigation both demonstrated significant restoration of normal symmetry, and stereotactic navigation enabled accuracy of <2 mm. CBCT added the shortest amount of time intraoperatively, ranging from 1 to 20 min. Reporting on long-term outcomes was heterogeneous. Conclusions: A variety of intraoperative imaging and navigation techniques are being applied in maxillofacial surgery. However, inconsistent reporting metrics, small study size, and study feasibility-focused study design limit meaningful comparison across technologies. Rigorous prospective studies with standardized outcome measures are needed to further define their clinical value and guide adoption. Full article

We present a stereoscopic analysis of coronal streamer deflection induced by a CME-driven shock, utilizing multi-viewpoint coronagraph observations from STEREO-Ahead, STEREO-Behind, and SOHO. Driven by the continuous impact of the shock, the streamer deflection propagates outward, exhibiting distinct morphological variations across the three different lines of sight. Our analysis reveals that speeds derived directly from two-dimensional (2D) images differ significantly from those obtained via three-dimensional (3D) reconstruction. Specifically, the 2D projected speeds measured from STEREO-Ahead, STEREO-Behind, and SOHO are 445, 476, and 336 km s⁻¹, respectively. Furthermore, while 2D measurements suggest a constant propagation speed, the 3D reconstruction reveals a pronounced deceleration of approximately −36 m s⁻². Significant discrepancies are also noted in the deflection amplitude between the 2D and 3D results. Since the propagating streamer deflection effectively traces the shock’s movement, we propose that measuring the deflection speed offers a robust alternative for deriving actual shock velocities in the outer corona, where direct white-light detection remains challenging. Full article

Currently, most wave observation equipment is used for fixed-point measurements, and there is a relative scarcity of ship-borne real-time wave measurement devices, which limits comprehensive and three-dimensional monitoring of wave characteristics. This paper introduces the Wave Acquisition Stereo System (WASS) and describes the design and construction of a ship-borne stereoscopic vision experimental apparatus. Sea trials were conducted to evaluate the system’s ship-borne wave-measurement performance and to quantify the effect of deployment parameters on accuracy. The results indicate that the device reliably retrieves wave parameters; compared with concurrent buoy observations, the error in significant wave height did not exceed 0.14 m. Research confirms that deployment parameters have a significant impact on measurement outcomes: sampling frequency directly affects the accuracy of wave-parameter estimation; a higher sampling rate (10 Hz) improves the reliability of the calculated results. The baseline-to-height ratio has an optimal range (0.1–0.3), and values outside this interval reduce measurement accuracy. Under a fixed geometric configuration, the observation field exhibits a band-shaped low-error zone aligned with the baseline direction. Full article

No-reference stereoscopic image quality assessment (NR-SIQA) remains a fundamental challenge due to the complex biological mechanisms of binocular rivalry and fusion, particularly under asymmetric distortions. In this paper, we propose a novel framework termed Multi-Stage Complementary Ensemble (MSCE). The core innovation lies in the Adaptive Selective Propagation (ASP) strategy embedded within a hierarchical Transformer architecture to dynamically regulates the fusion of binocular features. Specifically, by simulating the human visual system’s transition from binocular rivalry to fusion, the ASP strategy applies nonlinear gain control to selectively reinforce features from the governing view based on binocular discrepancies. Furthermore, the proposed Hierarchical Complementary Fusion (HCF) module effectively captures and integrates low-level texture integrity, mid-level structural degradation, and high-level semantic consistency, leveraging ensemble learning principles, within a unified quality-aware manifold. Experimental results on four benchmark datasets demonstrate that the MSCE framework achieves state-of-the-art performance, particularly in terms of prediction consistency under complex asymmetric distortions. Full article

Background/Objectives: Despite significant advances in imaging technology, real-time intra-fraction monitoring of moving targets remains a challenge in markerless radiotherapy. This retrospective study investigates the use of ExacTrac Dynamic by Brainlab as an intra-fraction monitoring tool for stereotactic body radiotherapy (SBRT) in both early-stage NSCLC and oligometastatic disease. Methods: A total of 63 X-ray pairs from 21 patients were analyzed to evaluate tumor visualization with and without a surrogate approach. Statistical analysis was conducted to determine whether failures could be attributed to tumor size or localization using the Mann–Whitney U-test and Fisher’s exact test. The accuracy of the X-ray/digitally reconstructed radiograph (DRR) surrogate-based fusion was assessed by calculating and comparing the corresponding 3D vectors according to the linear mixed effects model, with a random slope effect for size of surrogate and a random intercept per patient. Results: Surrogates enhanced tumor visualization on X-ray/DRR fusions from 14.3% to 75.5%. Tumor size and lung affected (left or right) did not predict visualization success. Tumor location, however, tended to influence visibility, with lesions in the upper lobes being more readily visualized (88%) than those in the lower lobes (48.1%), although no statistical significance was reported (p > 0.05). Regarding geometric accuracy, 76% of the analyzed data points deviated less than 5 mm in the 3D vector measurements, the mean values were around 4 mm (±3 mm), and the medians were within 3 mm across all conditions. No statistically significant differences (p > 0.05) were found based on the surrogate size or the triggering time of the X-ray during the breathing cycle. Conclusions: Surrogate-based DRRs, referred to as Correlation Objects, demonstrate consistent geometric accuracy across multiple surrogate sizes and X-ray acquisitions, supporting the clinical translation of markerless lung targeting workflows for lung SBRT. Full article

The enamel of teeth affected by Molar–Incisor Hypomineralization (MIH) has been reported to have a higher protein content. Though a glass hybrid is recommended for restoring teeth with MIH in children, there is a lack of in vitro research on the influence of deproteinization on its marginal integrity. Therefore, this study aimed to evaluate whether enamel pretreatment with 5.25% NaOCl reduces the size of the marginal crevice of such restorations. Out of eight extracted teeth with severe MIH, restored using a glass hybrid (Equia Forte HT/GC), half underwent deproteinization. A stereoscopic and a scanning electron microscope (SEM) were used for sections analysis. The median value of the marginal crevice measured using stereoscopic microscopy (n = 17) was significantly lower for the deproteinized (6.78 μm) than for the standard-prepared specimens (12.61 μm), p = 0.008. On SEM images, the median marginal crevice (n = 10) was 69.40 μm versus 156.77 μm for the deproteinized and standard groups, respectively. The differences, however, were not statistically significant. This study only partially confirmed the hypothesis that pretreatment with NaOCl reduces marginal crevices between the Equia Forte HT material and hypomineralized hard tissues. Further studies on the effect of deproteinization on the marginal adaptation of glass hybrid materials are needed. Full article

This study presents an experimental methodology for characterizing the crack-tip region using high-resolution Digital Image Correlation (DIC). The approach utilizes a stereoscopic microscope setup combined with 3D-DIC analysis to enable precise measurements within the small-scale region surrounding the crack tip. Two nonlinear parameters are evaluated: the plastic component of the crack-tip opening displacement (CTOD_p) and the cyclic plastic zone size. The investigation was conducted on disk-shaped compact tension specimens made of AISI 1020 steel under constant-ΔK fatigue testing. The results demonstrate a strong correlation between these nonlinear parameters and fatigue crack propagation, which was maintained stable, validating the proposed methodology. Furthermore, the relevance of crack-tip plasticity in fatigue crack propagation is verified under the tested conditions, highlighting its utility for fatigue life assessment under complex loading scenarios. Full article

Understanding the microstructure–property relationship in aluminum extrusions is crucial to leverage their potential in automotive lightweighting. The sensitivity of the processing history to the microstructure and through-thickness variations poses a major challenge since it leads to strong directionality in plasticity and fracture. Reliable characterization of the mechanical response under relevant stress states is crucial for the development of modeling strategies and performance ranking in alloy design. To this end, tensile and 3-point bend tests were performed for an aluminum extrusion produced on a laboratory-scale extrusion press at Rio Tinto Aluminium. Direct measurements of surface strains during bending using stereoscopic digital image correlation revealed that a larger bend angle in the VDA238-100 test does not necessarily imply a higher fracture strain. The T4 sample tested in the extrusion direction sustained a bend angle of 104° compared to 68° in T6 for the same nominal bend severity (ratio of sheet thickness to punch radius), despite comparable major fracture strains of 0.60 and 0.58, respectively. It is proposed that the work-hardening behavior governs the strain distribution on the outer bend surface. The higher hardening rate in the T4 condition helped distribute deformation in the bend zone more uniformly. This delayed fracture to larger bend angles since strain is accumulated at a lower rate. To assess whether the effect of the hardening behavior is manifest at a microstructural lengthscale, microcomputed tomography (μ-CT) scans were conducted on interrupted bend samples. The distribution and severity of damage in the form of cracks on the outer bend surface were distinct to the temper and thus the hardening rate. Full article

Unmanned aerial vehicle (UAV) hyperspectral remote sensing imaging systems have demonstrated significant potential for water quality monitoring. However, accurately obtaining water-leaving reflectance from UAV imagery remains challenging due to complex atmospheric radiation transmission above water bodies. This study proposes a method for water-leaving reflectance inversion based on air–ground collaborative correction. A fully connected neural network model was developed using TensorFlow Keras to establish a non-linear mapping between UAV hyperspectral reflectance and the measured near-water and water-leaving reflectance from ground-based spectral. This approach addresses the limitations of traditional linear correction methods by enabling spatiotemporal synchronization correction of UAV remote sensing images with ground observations, thereby minimizing atmospheric interference and sensor differences on signal transmission. The retrieved water-leaving reflectance closely matched measured data within the 450–900 nm band, with the average spectral angle mapping reduced from 0.5433 to 0.1070 compared to existing techniques. Moreover, the water quality parameter inversion models for turbidity, color, total nitrogen, and total phosphorus achieved high determination coefficients (R² = 0.94, 0.93, 0.88, and 0.85, respectively). The spatial distribution maps of water quality parameters were consistent with in situ measurements. Overall, this UAV hyperspectral remote sensing method, enhanced by air–ground collaborative correction, offers a reliable approach for UAV hyperspectral water quality remote sensing and promotes the advancement of stereoscopic water environment monitoring. Full article

In low-light environments, light field (LF) images are often affected by various degradation factors, which impair the performance of subsequent visual tasks such as depth estimation. To address these challenges, although numerous light-field low-light enhancement methods have been proposed, they generally overlook the importance of frequency-domain information in modeling light field features, thereby limiting their noise suppression capabilities. Moreover, these enhancement methods mainly rely on pixel- or semantic-level cues without explicitly incorporating disparity information for structural modeling, thereby overlooking the stereoscopic spatial structure of light field images and limiting enhancement performance across different depth levels. To address these issues, we propose a light field low-light enhancement method named DDPNet. The method integrates a depth-guided mechanism to jointly restore light field images in both the spatial and frequency domains, employing a multi-stage progressive strategy to achieve synergistic improvements in illumination and depth. Specifically, we introduce a Dual-Domain Feature Extraction (DDFE) module, which incorporates spatial-frequency analysis to efficiently extract both global and local light field features. In addition, we propose a Depth-Aware Enhancement (DAE) module, which utilizes depth maps to guide the enhancement process, effectively restoring edge structures and luminance information. Extensive experimental results demonstrate that DDPNet significantly outperforms existing methods. Full article

Visual virtuality can be seen as involving the processing and perception of pictorial images. The production of such representations has a longer history than speculations about their perception. Pictorial images of objects and scenes lack two dimensions present in their subject matter—depth and motion. Instruments to investigate stereoscopic depth and apparent motion were invented in the early 1830s. Wheatstone devised stereoscopes and conducted experiments with them; Plateau and Stampfer independently crafted devices for presenting sequences of slightly different patterns that created the impression of motion. Wheatstone later proposed how moving and stereoscopic images could be combined. Thereafter, interpretations of virtual depth and motion perception became more concerned with central processing rather than being based on geometrical optics. Full article