A Novel Model for Instance Segmentation and Quantification of Bridge Surface Cracks-The YOLOv8-AFPN-MPD-IoU.

Surface cracks are alluded to as one of the early signs of potential damage to infrastructures. In the same vein, their detection is an imperative task to preserve the structural health and safety of bridges. Human-based visual inspection is acknowledged as the most prevalent means of assessing infrastructures' performance conditions. Nonetheless, it is unreliable, tedious, hazardous, and labor-intensive. This state of affairs calls for the development of a novel YOLOv8-AFPN-MPD-IoU model for instance segmentation and quantification of bridge surface cracks. Firstly, YOLOv8s-Seg is selected as the backbone network to carry out instance segmentation. In addition, an asymptotic feature pyramid network (AFPN) is incorporated to ameliorate feature fusion and overall performance. Thirdly, the minimum point distance (MPD) is introduced as a loss function as a way to better explore the geometric features of surface cracks. Finally, the middle aisle transformation is amalgamated with Euclidean distance to compute the length and width of segmented cracks. Analytical comparisons reveal that this developed deep learning network surpasses several contemporary models, including YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and Mask-RCNN. The YOLOv8s + AFPN + MPDIoU model attains a precision rate of 90.7%, a recall of 70.4%, an F1-score of 79.27%, mAP50 of 75.3%, and mAP75 of 74.80%. In contrast to alternative models, our proposed approach exhibits enhancements across performance metrics, with the F1-score, mAP50, and mAP75 increasing by a minimum of 0.46%, 1.3%, and 1.4%, respectively. The margin of error in the measurement model calculations is maintained at or below 5%. Therefore, the developed model can serve as a useful tool for the accurate characterization and quantification of different types of bridge surface cracks.

Nucleation, Development and Healing of Micro-Cracks in Shape Memory Polyurethane Subjected to Subsequent Tension Cycles.

Thermoresponsive shape memory polymers (SMPs) have garnered increasing interest for their exceptional ability to retain a temporary shape and recover the original configuration through temperature changes, making them promising in various applications. The SMP shape change and recovery that happen due to a combination of mechanical loading and appropriate temperatures are related to its particular microstructure. The deformation process leads to the formation and growth of micro-cracks in the SMP structure, whereas the subsequent heating over its glass transition temperature Tg leads to the recovery of its original shape and properties. These processes also affect the SMP microstructure. In addition to the observed macroscopic shape recovery, the healing of micro-crazes and micro-cracks that have nucleated and developed during the loading occurs. Therefore, our study delves into the microscopic aspect, specifically addressing the healing of micro-cracks in the cyclic loading process. The proposed research concerns a thermoplastic polyurethane shape memory polymer (PU-SMP) MM4520 with a Tg of 45 °C. The objective of the study is to investigate the effect of the number of tensile loading-unloading cycles and thermal shape recovery on the evolution of the PU-SMP microstructure. To this end, comprehensive research starting from structural characterization of the initial state and at various stages of the PU-SMP mechanical loading was conducted. Dynamic mechanical analysis (DMA), differential scanning calorimetry (DSC), wide-angle X-ray scattering (WAXS) and scanning electron microscopy (SEM) were used. Moreover, the shape memory behavior in the thermomechanical loading program was investigated. The obtained average shape fixity value was 99%, while the shape recovery was 92%, which confirmed good shape memory properties of the PU-SMP. Our findings reveal that even during a single loading-unloading tension cycle, crazes and cracks nucleate on the surface of the PU-SMP specimen, whereas the subsequent temperature-induced shape recovery process carried out at the temperature above Tg enables the healing of micro-cracks. Interestingly, the surface of the specimen after three and five loading-unloading cycles did not exhibit crazes and cracks, although some traces of cracks were visible. The traces disappeared after exposing the material to heating at Tg + 20 °C (65 °C) for 30 min. The crack closure phenomenon during deformation, even without heating over Tg, occurred within three and five subsequent cycles of loading-unloading. Notably, in the case of eight loading-unloading cycles, cracks appeared on the surface of the PU-SMP and were healed only after thermal recovery at the particular temperature over Tg. Upon reaching a critical number of cycles, the proper amount of energy required for crack propagation was attained, resulting in wide-open cracks on the material's surface. It is worth noting that WAXS analysis did not indicate strong signs of typical highly ordered structures in the PU-SMP specimens in their initial state and after the loading history; however, some orientation after the cyclic deformation was observed.

A Fabric-Based Strain Sensor with a Microbridge Structure and the Supercapacitor-Powered Integrated Sensing System.

Developing fabric-based strain sensors with high sensitivity and stability is in high demand for wearable electronics. Herein, carbon nanotubes (CNTs) and polypyrrole (PPy) are coated on a thermoplastic polyurethane (TPU) fabric as strain sensors. A microbridge structure, in which CNT bridges the stretching-induced cracks, has been designed for the TPU-CNT-PPy strain sensor. The microbridge structure can significantly enhance the electrical resilience, ensuring the improved sensitivity and stability of strain sensors. As a result, our TPU-CNT-PPy strain sensors deliver high sensitivity (GF = 231.5) with a broad working range (150%) and fast response and recovery time (166/195 ms). In addition, our TPU-CNT-PPy could also be used as flexible electrodes of the microsupercapacitors (MSCs) as a power supplier for the integrated sensing system. The TPU-CNT-PPy-based MSCs exhibit a high specific capacitance (460.3 mF cm-2 at 0.5 mA cm-2) and excellent cycling stability (96.69% capacitance retention for 10,000 charge/discharge cycles). Finally, we demonstrated an integrated sensing system using TPU-CNT-PPy as both MSCs and strain sensors, where the current signals of the sensors could be well detected via Bluetooth. This study offers a microbridge strategy to fabricate strain sensors with high sensitivity and stability and develops an integrated sensing system for the actual applications of wearable electronics.

A robust self-supervised approach for fine-grained crack detection in concrete structures.

This work addresses a critical issue: the deterioration of concrete structures due to fine-grained cracks, which compromises their strength and longevity. To tackle this problem, experts have turned to computer vision (CV) based automated strategies, incorporating object detection and image segmentation techniques. Recent efforts have integrated complex techniques such as deep convolutional neural networks (DCNNs) and transformers for this task. However, these techniques encounter challenges in localizing fine-grained cracks. This paper presents a self-supervised 'you only look once' (SS-YOLO) approach that utilizes a YOLOv8 model. The novel methodology amalgamates different attention approaches and pseudo-labeling techniques, effectively addressing challenges in fine-grained crack detection and segmentation in concrete structures. It utilizes convolution block attention (CBAM) and Gaussian adaptive weight distribution multi-head self-attention (GAWD-MHSA) modules to accurately identify and segment fine-grained cracks in concrete buildings. Additionally, the assimilation of curriculum learning-based self-supervised pseudo-labeling (CL-SSPL) enhances the model's ability when applied to limited-size data. The efficacy and viability of the proposed approach are demonstrated through experimentation, results, and ablation analysis. Experimental results indicate a mean average precision (mAP) of at least 90.01%, an F1 score of 87%, and an intersection over union threshold greater than 85%. It is evident from the results that the proposed method yielded at least 2.62% and 4.40% improvement in mAP and F1 values, respectively, when tested on three diverse datasets. Moreover, the inference time taken per image is 2 ms less than that of the compared methods.

Dynamic Thermal Response of Multiple Interface Cracks between a Half-Plane and a Coating Layer under General Transient Temperature Loading.

This paper explores the thermal behavior of multiple interface cracks situated between a half-plane and a thermal coating layer when subjected to transient thermal loading. The temperature distribution is analyzed using the hyperbolic heat conduction theory. In this model, cracks are represented as arrays of thermal dislocations, with densities calculated via Fourier and Laplace transformations. The methodology involves determining the temperature gradient within the uncracked region, and these calculations contribute to formulating a singular integral equation specific to the crack problem. This equation is subsequently utilized to ascertain the dislocation densities at the crack surface, which facilitates the estimation of temperature gradient intensity factors for the interface cracks experiencing transient thermal loading. This paper further explores how the relaxation time, loading parameters, and crack dimensions impact the temperature gradient intensity factors. The results can be used in fracture analysis of structures operating at high temperatures and can also assist in the selection and design of coating materials for specific applications, to minimize the damage caused by temperature loading.

Computer Vision and Augmented Reality for Human-Centered Fatigue Crack Inspection.

A significant percentage of bridges in the United States are serving beyond their 50-year design life, and many of them are in poor condition, making them vulnerable to fatigue cracks that can result in catastrophic failure. However, current fatigue crack inspection practice based on human vision is time-consuming, labor intensive, and prone to error. We present a novel human-centered bridge inspection methodology to enhance the efficiency and accuracy of fatigue crack detection by employing advanced technologies including computer vision and augmented reality (AR). In particular, a computer vision-based algorithm is developed to enable near-real-time fatigue crack detection by analyzing structural surface motion in a short video recorded by a moving camera of the AR headset. The approach monitors structural surfaces by tracking feature points and measuring variations in distances between feature point pairs to recognize the motion pattern associated with the crack opening and closing. Measuring distance changes between feature points, as opposed to their displacement changes before this improvement, eliminates the need of camera motion compensation and enables reliable and computationally efficient fatigue crack detection using the nonstationary AR headset. In addition, an AR environment is created and integrated with the computer vision algorithm. The crack detection results are transmitted to the AR headset worn by the bridge inspector, where they are converted into holograms and anchored on the bridge surface in the 3D real-world environment. The AR environment also provides virtual menus to support human-in-the-loop decision-making to determine optimal crack detection parameters. This human-centered approach with improved visualization and human-machine collaboration aids the inspector in making well-informed decisions in the field in a near-real-time fashion. The proposed crack detection method is comprehensively assessed using two laboratory test setups for both in-plane and out-of-plane fatigue cracks. Finally, using the integrated AR environment, a human-centered bridge inspection is conducted to demonstrate the efficacy and potential of the proposed methodology.

Is motor-driven insertion of orthodontic miniscrews more advantageous than manual insertion? A micro-CT evaluation of bone miniscrew contact surface area and cortical microcracks in rabbits.

AIM: This in vitro study aimed to evaluate and compare the bone-miniscrew contact surface area (BMC) and the cortical bone microcracks (CM) resulting from manual (hand-driven) and automated (motor-driven) orthodontic miniscrew (OM) insertion methods. METHODS: Thirty-three OM were inserted in the femurs of nine New Zealand rabbits using manual (n = 16) and automated (n = 17) insertions. After euthanizing the rabbits, bone blocks, each including one OM, were sawed. Micro-CT scanning was performed, and data analysis included reconstruction, binarization and quantification of morphometric parameters of BMC and the number and length of CM. Means and standard deviations for complete BMC, complete BMC proportion, cortical BMC, cortical BMC proportion, and length and number of CM were calculated. Mixed model analysis was used to adjust for more than one sample/CM per animal. A paired t-test was used to compare the number of CM between the two groups. RESULTS: Compared to the automated insertion, manually inserted miniscrews had significantly lower complete BMC (7.54 ± 1.80 mm2 vs. 11.99 ± 3.64 mm2), cortical BMC (5.91 ± 1.48 mm2 vs. 8.48 ± 1.90 mm2) and cortical BMC proportion (79.44 ± 5.84% vs. 87.94 ± 3.66%). However, it was not statistically significant in complete BMC proportion (p = .052). The automated insertion also resulted in a significantly lower mean number of CM than the manual method (p = .012). However, the length of the cracks was shorter in the manual group but with no significant difference (p = 0.256). CONCLUSION: Motor-driven OM insertion results in superior BMC and reduction in the number of CM, which may lead to better miniscrew stability.

Research on the dynamic tensile characteristics and surface crack evolution of coal under impact loading.

The tensile properties of coal under dynamic loading are important mechanical characteristics of coal and are highly important for controlling coal rock stability under impact loading conditions, selecting blasting engineering parameters, and studying the mechanism of rockburst disasters. To investigate the dynamic tensile failure process of coal subjected to impact loading, this study used high-speed photography and digital image correlation technology to capture the dynamic tensile failure of coal under impact loading. The dynamic tensile evolution was quantitatively analyzed from the beginning of coal sample being loaded to failure. The captured images of the coal were processed, and the fractal dimension was used to quantitatively describe the evolution of the coal surface cracks under impact loading. The following conclusions were drawn from the experimental results: (1) An empirical formula was established to describe the dynamic tensile strength characteristics of coal under different loading rates. (2) Under impact loading, the maximum strain of a Brazilian disc coal sample first appeared at the contact end between the sample and the incident rod. (3) Under impact loading, a Brazilian disc coal sample cracked from the center of the sample outward, and the crack subsequently extended toward both ends. The fractal dimension of the crack exhibited a power function relationship with time, and the variation range of the fractal dimension of the crack was 1.05-1.39.

Effective small crack detection based on tunnel crack characteristics and an anchor-free convolutional neural network.

Tunnel cracks are thin and narrow linear targets, and their pixel proportions in images are usually very low, less than 6%; therefore, a method is needed to better detect small crack targets. In this study, a crack detection method based on crack characteristics and an anchor-free framework is investigated. First, the characteristics of cracks are analyzed to obtain the real crack texture, interference noise texture, and targets appearing near each crack as the context information for the model to filter and remove noise. We discuss the crack detection performance of anchor-based and anchor-free algorithms. Then, an optimized anchor-free algorithm is proposed in this paper for crack detection. Based on the advantages of YOLOX-x, we add a semantic enhancement module to better use contextual information. The experimental results show that the anchor-free algorithm performs slightly better than other algorithms in crack detection situations. In addition, the proposed method displays better detection performance for slender and inconspicuous cracks, with an average precision of 0.858.

Concrete Highway Crack Detection Based on Visible Light and Infrared Silicate Spectrum Image Fusion.

Cracks provide the earliest and most immediate visual response to structural deterioration of asphalt pavements. Most of the current methods for crack detection are based on visible light sensors and convolutional neural networks. However, such an approach obviously limits the detection to daytime and good lighting conditions. Therefore, this paper proposes a crack detection technique cross-modal feature alignment of YOLOV5 based on visible and infrared images. The infrared spectrum characteristics of silicate concrete can be an important supplement. The adaptive illumination-aware weight generation module is introduced to compute illumination probability to guide the training of the fusion network. In order to alleviate the problem of weak alignment of the multi-scale feature map, the FA-BIFPN feature pyramid module is proposed. The parallel structure of a dual backbone network takes 40% less time to train than a single backbone network. As determined through validation on FLIR, LLVIP, and VEDAI bimodal datasets, the fused images have more stable performance compared to the visible images. In addition, the detector proposed in this paper surpasses the current advanced YOLOV5 unimodal detector and CFT cross-modal fusion module. In the publicly available bimodal road crack dataset, our method is able to detect cracks of 5 pixels with 98.3% accuracy under weak illumination.

Experimental study on opto-acoustic nonlinear frequency-mixing technique with separated basic temperature.

Different from the traditional frequency-mixing technique which employs a contacting transducer, the laser-induced acoustic nonlinear frequency-mixing detection technique utilizes a laser source to instigate crack motion and generate acoustic waves. Thus, apart from the temperature oscillation induced by the pump laser, the "basic temperature" originating from the probe laser can also influence the crack. This additional variable complicates the contact state of the crack, yielding a more diverse range of nonlinear acoustic signal attributes. In light of this, our study enhances the conventional opto-acoustic nonlinear frequency mixing experimental setup by integrating an independent heating laser beam. This modification isolates the impact of the "basic temperature" on crack width while also dialing down the probe laser power to mitigate its thermal effects. To amplify the sensitivity of crack detection, we deliberated on the optimal laser source parameters for this setup. Consequently, our revamped system, paired with fine-tuned parameters, captures nonlinear acoustic signals with an enriched feature set. This investigation can provide support for the non-contact opto-acoustic nonlinear frequency mixing technique in the detection and evaluation of micro-cracks.

Self-Healing of Cracks in Cementitious Materials as a Method of Improving the Durability of Pre-Stressed Concrete Railway Sleepers.

The article presents research results regarding the possibility of modifying pre-stressed concrete railway sleepers to improve their durability. The cracks that appear in these elements are one of the reasons for shortening the period of safe use. They do not have a significant impact on the load-bearing capacity of these elements, but on their durability. The resulting scratches become an easy way for the external environment to migrate inside the element, including the reinforcement area. Despite efforts to eliminate the possibility of cracking, this phenomenon still occurs in railway sleepers. In order to reduce the negative effects of cracking the cement matrix, a technology for modifying a prefabricated concrete element with resin-filled tubes towards its autonomous self-healing was developed and tested. The tests were divided into three stages, including laboratory tests carried out on cement mortar beams, semi-technical tests carried out on reinforced concrete beams, and industrial tests carried out on pre-stressed concrete and prefabricated railway sleepers. All research conducted on a laboratory and semi-technical scale, preceding the target stage, was intended to ultimately enable the development of tube application technology on an industrial scale while verifying the effectiveness of self-healing at the laboratory level. The use of self-healing cementitious materials potentially reduces the negative effects of cracking railway sleepers, as shown by observations conducted during the research.

Experimental Study on Dynamic Characteristics of Damaged Post-Tensioning Concrete Sleepers Using Impact Hammer.

Concrete sleepers in operation are commonly damaged by various internal and external factors, such as poor materials, manufacturing defects, poor construction, environmental factors, and repeated loads and driving characteristics of trains; these factors affect the vibration response, mode shape, and natural frequency of damaged concrete sleepers. However, current standards in South Korea require only a subjective visual inspection of concrete sleepers to determine the damage degree and necessity of repair or replacement. In this study, an impact hammer test was performed on concrete sleepers installed on the operating lines of urban railroads to assess the field applicability of the modal test method, with the results indicating that the natural frequency due to concrete sleeper damage was lower than that of the undamaged state. Furthermore, the discrepancy between the simulated and measured natural frequencies of the undamaged concrete sleeper was approximately 1.87%, validating the numerical analysis result. The natural frequency of the damaged concrete sleepers was lower than that of the undamaged concrete sleeper, and cracks in both the concrete sleeper core and the rail seat had the lowest natural frequency among all the damage categories. Therefore, the damage degrees of concrete sleepers can be quantitatively estimated using measured natural-frequency values.

Microstructure Evolution and Fretting Wear Mechanisms of Steels Undergoing Oscillatory Sliding Contact in Dry Atmosphere.

Variations in the microstructure and the dominant fretting wear mechanisms of carbon steel alloy in oscillatory sliding contact against stainless steel in a dry atmosphere were evaluated by various mechanical testing and microanalytical methods. These included scanning electron microscopy and energy dispersive spectrometry with corresponding elemental maps of the wear tracks, in conjunction with cross-sectional transmission electron microscopy of samples prepared by focused ion beam machining to assess subsurface and through-thickness changes in microstructure, all as a function of applied load and sliding time. Heavily dislocated layered microstructures were observed below the wear tracks to vary with both the load and sliding time. During the accumulation of fretting cycles, the subsurface microstructure evolved into stable dislocation cells with cell walls aligned parallel to the surface and the sliding direction. The thickness of the damaged subsurface region increased with the load, consistent with the depth distribution of the maximum shear stress. The primary surface oxide evolved as Fe2O3 and Fe3O4 with increasing sliding time, leading to the formation of a uniform oxide scale at the sliding surface. It is possible that the development of the dislocation cell structure in the subsurface also enhanced oxidation by pipe diffusion along dislocation cores. The results of this study reveal complex phase changes affecting the wear resistance of steels undergoing fretting wear, which involve a synergy between oxidative wear, crack initiation, and crack growth along dislocation cell walls due to the high strains accumulating under high loads and/or prolonged surface sliding.

A Highly Sensitive Strain Sensor with Wide Linear Sensing Range Prepared on a Hybrid-Structured CNT/Ecoflex Film via Local Regulation of Strain Distribution.

With the development of information technology, high-performance wearable strain sensors with high sensitivity and stretchability have played a significant role in motion detection. However, many high-sensitivity and outstanding-stretchability strain sensors possess a limited linear sensing range, which limits the enhancement of the flexible strain sensors' performance. Herein, we develop a hybrid-structured carbon nanotube (CNT)/Ecoflex strain sensor with laser-engraved grooves along with punched circular holes in a composite CNT/Ecoflex film by vacuum filtration and permeation. By optimizing the distribution of grooves and circular holes, the strain in the sensing layer can be locally regulated, which alters the morphology of cracks under strain and allows the hybrid-structured CNT/Ecoflex strain sensor to simultaneously exhibit high sensitivity (GF = 43.8) as well as a wide linear sensing range (200%). On the basis of excellent performance, the hybrid-structured CNT/Ecoflex strain sensor is capable of detecting movements in various parts of the human body, including movements of larynx and joint bending.

Strain Engineering: Perfecting Freestanding Perovskite Oxide Fabrication.

Freestanding oxide membranes provide a promising path for integrating devices on silicon and flexible platforms. To ensure optimal device performance, these membranes must be of high crystal quality, stoichiometric, and their morphology free from cracks and wrinkles. Often, layers transferred on substrates show wrinkles and cracks due to a lattice relaxation from an epitaxial mismatch. Doping the sacrificial layer of Sr3 Al2 O6 (SAO) with Ca or Ba offers a promising solution to overcome these challenges, yet its effects remain critically underexplored. A systematic study of doping Ca into SAO is presented, optimizing the pulsed laser deposition (PLD) conditions, and adjusting the supporting polymer type and thickness, demonstrating that strain engineering can effectively eliminate these imperfections. Using SrTiO3 as a case study, it is found that Ca1.5 Sr1.5 Al2 O6 offers a near-perfect match and a defect-free freestanding membrane. This approach, using the water-soluble Bax /Cax Sr3-x Al2 O6 family, paves the way for producing high-quality, large freestanding membranes for functional oxide devices.

Finite Element Analysis and Fatigue Test of INTEGRA Dental Implant System.

The study involved numerical FEA (finite element analysis) of dental implants. Based on this, fatigue tests were conducted according to the PN-EN 14801 standard required for the certification of dental products. Thanks to the research methodology developed by the authors, it was possible to conduct a thorough analysis of the impact of external and internal factors such as material, geometry, loading, and assembly of the dental system on the achieved value of fatigue strength limit in the examined object. For this purpose, FEM studies were based on identifying potential sites of fatigue crack initiation in reference to the results of the test conducted on a real model. The actions described in the study helped in the final evaluation of the dental system design process named by the manufacturer as INTEGRA OPTIMA 3.35. The objective of the research was to identify potential sites for fatigue crack initiation in a selected dental system built on the INTEGRA OPTIMA 3.35 set. The material used in the research was titanium grade 4. A map of reduced von Mises stresses was used to search for potential fatigue crack areas. The research [loading] was conducted on two mutually perpendicular planes positioned in such a way that the edge intersecting the planes coincided with the axis of the system. The research indicated that the connecting screw showed the least sensitivity (stress change) to the change in the loading plane, while the value of preload has a significant impact on the achieved fatigue strength of the system. In contrast, the endosteal implant (root) and the prosthetic connector showed the greatest sensitivity to the change in the loading plane. The method of mounting [securing] the endosteal implant using a holder, despite meeting the standards, may contribute to generating excessive stress concentration in the threaded part. Observation of the prosthetic connector in the Optima 3.35 system, cyclically loaded with a force of F ≈ 300 N in the area of the upper hexagonal peg, revealed a fatigue fracture. The observed change in stress peak in the dental connector for two different force application surfaces shows that the positioning of the dental system (setting of the socket in relation to the force action plane) is significantly decisive in estimating the limited fatigue strength.

Central Bouquet Hemorrhages in Pathologic Myopia: Clinical Characteristics and Prognostic Relevance.

PURPOSE: To compare the clinical implications of central bouquet hemorrhages (CBHs) to primarily subretinal hemorrhages, both occurring in the setting of pathologic myopia with lacquer crack formation. DESIGN: Multicenter retrospective cohort study. PARTICIPANTS: Twenty-five eyes (11 primarily subretinal hemorrhages and 14 CBH) were monitored over a median of 35 (interquartile range [IQR], 9.50-54) months. MAIN OUTCOMES MEASURES: Comprehensive ophthalmic examinations and OCT were reviewed. The study employed linear mixed-effects models to compare the impact of CBH versus primarily subretinal hemorrhages on baseline visual acuity (VA), rate of VA improvement, and final VA, adjusting for the follow-up period. Times of hemorrhages reabsorbtion and rate of ellipsoid zone (EZ) layer disruption on OCT were recorded. RESULTS: Eyes with CBH exhibited significantly worse baseline VA (0.93 ± 0.45 logarithm of the minimum angle of resolution [logMAR]; 20/160 Snellen vs. 0.36 ± 0.26 logMAR [20/50 Snellen], P < 0.001), a slower rate of VA improvement (P = 0.04), and a trend toward worse final VA (0.48 ± 0.47 logMAR [20/60 Snellen] vs. 0.16 ± 0.16 logMAR [20/30 Snellen], P = 0.06) compared with eyes with primarily subretinal hemorrhages. The CBH group experienced longer median reabsorption times (10 [IQR, 4.6-23.3] months vs. 2.3 [IQR, 2-3.2] months), and a higher prevalence of EZ layer disruption (86% vs. 0%), than the group with primarily subretinal hemorrhages. Central bouquet hemorrhage reabsorption was followed by the appearance of vertical hyperreflective lines in the central fovea in 67% of eyes, persisting for up to 6 years of follow-up. CONCLUSIONS: Central bouquet hemorrhage signifies a distinct condition in pathologic myopia, characterized by worse visual outcomes, prolonged structural impact, and possible irreversible damage, compared with primarily subretinal hemorrhages. Central bouquet hemorrhage regression should be taken into account in the differential diagnosis of vertical hyperreflective lesions in the central fovea on OCT in eyes with pathologic myopia. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

A Deep Learning Approach for Surface Crack Classification and Segmentation in Unmanned Aerial Vehicle Assisted Infrastructure Inspections.

Surface crack detection is an integral part of infrastructure health surveys. This work presents a transformative shift towards rapid and reliable data collection capabilities, dramatically reducing the time spent on inspecting infrastructures. Two unmanned aerial vehicles (UAVs) were deployed, enabling the capturing of images simultaneously for efficient coverage of the structure. The suggested drone hardware is especially suitable for the inspection of infrastructure with confined spaces that UAVs with a broader footprint are incapable of accessing due to a lack of safe access or positioning data. The collected image data were analyzed using a binary classification convolutional neural network (CNN), effectively filtering out images containing cracks. A comparison of state-of-the-art CNN architectures against a novel CNN layout "CrackClassCNN" was investigated to obtain the optimal layout for classification. A Segment Anything Model (SAM) was employed to segment defect areas, and its performance was benchmarked against manually annotated images. The suggested "CrackClassCNN" achieved an accuracy rate of 95.02%, and the SAM segmentation process yielded a mean Intersection over Union (IoU) score of 0.778 and an F1 score of 0.735. It was concluded that the selected UAV platform, the communication network, and the suggested processing techniques were highly effective in surface crack detection.

Study of thermal effects induced by the high-frequency probing laser in nonlinear opto-acoustic frequency-mixing technique.

Photo-thermal modulation-based nonlinear opto-acoustic frequency-mixing technique is an effective method for detecting micro-cracks. When using this technique for micro-crack detection, the selection of laser source parameters is particularly crucial. Compared to traditional piezo-transducer-based mixing techniques, the characteristic of using a laser as the detection source is the presence of thermal effects. The thermal effect caused by laser irradiation on the sample surface can not only generate acoustic waves but also affect the crack state, thus influencing nonlinear signals. In this paper, an experimental setup using photo-thermal modulation-based nonlinear opto-acoustic frequency-mixing technique has been set up to investigate the thermal effects of the probe laser source. In addition, a corresponding physical model has been established to discuss the physical mechanisms revealed by the experimental results. This study provides a basis for selecting appropriate probe source parameters and scanning positions of laser sources when detecting micro-cracks using the photo-thermal modulation-based nonlinear opto-acoustic frequency-mixing technique.