Image-based Methodology Research Articles

Development of an Image-Based Methodology to Measure Heave Height in Hamburg Wheel Tracker–Tested Asphalt Specimens

Development of an Image-Based Methodology to Measure Heave Height in Hamburg Wheel Tracker–Tested Asphalt Specimens

Image based analytical approaches for study of particulate matter (PM) in air

Particulate matter (PM) stands as a predominant pollutant in developing countries, demanding effective source identification and remediation strategies. This review centers on the scanning electron microscopy (SEM) image-based methodology for PM analysis, particularly emphasizing the passive technique of utilizing plant leaves for PM capture. The SEM-image-based approach serves as a powerful tool for unraveling the morphological characteristics of PM, crucial for source identification. Additionally, SEM, when equipped with energy dispersive spectroscopy (EDS), enables chemical and mineralogical characterization, providing insights into the origin of PM. The first part of the review describes the plant as the best bio-sampler for PM. In this context, removal of PM from the environment through plant-based interventions is described. Subsequently, the application of SEM for size-based analysis using ImageJ and morphological analysis for source identification of PM is detailed. Following this, the PM chemical and mineralogical composition for source identification are described based on EDS analysis. Image-based techniques play a pivotal role in selecting the most effective plant species for PM removal from the air. The review comprehensively outlines the morphological, chemical, and mineralogical attributes utilized for PM source identification and their subsequent remediation by plants. Finally, the benefits of SEM-image-based techniques for PM analysis are elucidated. This review offers a holistic understanding of the SEM-EDS and plant-based approach, presenting a promising avenue for addressing PM pollution and enhancing environmental quality.

Data-driven crack image-based seismic failure mode identification for damaged RC columns

The seismic failure mode identification of reinforced concrete columns is crucial for post-earthquake stability and safety assessment of the damaged concrete buildings. In this paper, a multi-feature crack image-based methodology is proposed for non-destructive non-contact failure mode prediction in reinforced concrete columns damaged in an earthquake. A databank of 455 surface crack patterns from quasi-static experiments on 111 reinforced concrete columns with a variety of structural and geometric properties is collected by the authors aimed at the development and validation of the methodology. For the intricacy retrieval of the surface crack maps, multi-feature fractal-based procedures are taken into consideration. Various machine learning algorithms are employed to train the seismic failure mode predictive models using the characteristics of the damaged RC columns. Ten scenarios are defined based on the image-extracted indices, and structural and geometric characteristics of rectangular reinforced concrete columns. Hyperparameter tuning of the machine learning algorithms using GridsearchCV function has optimized the performance of the models. A k-fold cross-validation procedure is also executed to examine the robustness of the results. Results reveal that the predictive model in which the image-extracted indices and structural parameters are jointly used as input features of supervised learning provides 98% accuracy for the testing dataset with Extreme gradient boost algorithm. In addition, among the scenarios that only image-derived parameters are considered as input features, an accuracy of 83% is obtained with Extreme gradient boost algorithm for the testing dataset.

Revolutionizing cardiovascular risk prediction: A novel image-based approach using fundus analysis and deep learning

Worldwide, CVDs continue to stand as a prominent contributor to mortality. Detecting and assessing CVD risk early is paramount for effective prevention and management. Medical imaging has gained prominence as a tool for evaluating CVD risk factors. In this study, a novel Inception v3 with a VGG16 is proposed to forecast cardiovascular risk rates via readily available and non-invasive fundus images. This approach harnesses advanced image analysis techniques encompassing contrast enhancement and noise reduction. The blood vessel segmentation and Optic disc detection of the pertinent features are extracted from the fundus images. In this context, the Inception v3 architecture is initially employed to capture intricate hierarchical patterns within the images. Alternatively, explore the utilization of the VGG16 architecture. By integrating these features with clinical data, the model is then trained to predict cardiovascular risk rates. Empirical findings underscore the method's remarkable accuracy in risk rate prediction. This non-invasive, image-based methodology holds transformative potential for reshaping early diagnosis and risk management approaches for cardiovascular diseases. Ultimately, this innovation stands to enhance patient care and outcomes.

Image-based research methods for mapping tourist behaviour: smart photos

ABSTRACT Conventional research methods for understanding tourists’ behaviours need to be more practical and accurate when tracking tourists’ movements within a destination. In recent years, technological development has offered advanced technical approaches for data collection and analysis. Taking account of the tourist experience in post-industrial landscapes, this study introduces an image-based methodology to explore tourists’ movements at industrial heritage sites. Preliminary results are presented, using Liverpool’s Royal Albert Dock as an example of detecting tourists’ movement through use of a drone. The findings demonstrate that the selected method – Smart Photo – effectively maps tourists’ behaviour and movements, and that this provides researchers with a simple, fast, and accurate data collection and analysis tool.

Uncertainty Quantification in the In Vivo Image-Based Estimation of Local Elastic Properties of Vascular Walls.

Patient-specific computational models are a powerful tool for planning cardiovascular interventions. However, the in vivo patient-specific mechanical properties of vessels represent a major source of uncertainty. In this study, we investigated the effect of uncertainty in the elastic module (E) on a Fluid-Structure Interaction (FSI) model of a patient-specific aorta. The image-based χ-method was used to compute the initial E value of the vascular wall. The uncertainty quantification was carried out using the generalized Polynomial Chaos (gPC) expansion technique. The stochastic analysis was based on four deterministic simulations considering four quadrature points. A deviation of about ±20% on the estimation of the E value was assumed. The influence of the uncertain E parameter was evaluated along the cardiac cycle on area and flow variations extracted from five cross-sections of the aortic FSI model. Results of stochastic analysis showed the impact of E in the ascending aorta while an insignificant effect was observed in the descending tract. This study demonstrated the importance of the image-based methodology for inferring E, highlighting the feasibility of retrieving useful additional data and enhancing the reliability of in silico models in clinical practice.

Scapular morphology of great apes and humans: A three-dimensional computed tomography-based comparative study.

The primate scapula has been studied widely since its shape has been shown to correlate with how the forelimb is used in daily activities. In this study, we expand on the existing literature and use an image-based methodology that was originally developed for orthopaedic practice to quantify and compare the three-dimensional (3D) morphology of the scapula across humans and great apes. We expect that this image-based approach will allow us to identify differences between great apes and humans that can be related to differences in mobility and loading regime of the shoulder. We hypothesize that gorillas and chimpanzees will have a similar scapular morphology, geared towards stability and weight-bearing in knuckle-walking, whilst the scapular morphology of orangutans is expected to be more similar to that of humans given their high glenohumeral mobility associated with their suspensory lifestyle. We made 3D reconstructions of computed tomography scans of 69 scapulae from four hominid genera (Pongo, Gorilla, Pan and Homo). On these 3D bone meshes, the inferior glenoid plane was determined, and subsequently, a set of bony landmarks on the scapular body, coracoid, and acromion were defined. These landmarks allowed us to measure a set of functionally relevant angles which represent acromial overhang, subacromial space and coracoacromial space. The angles that were measured are: the delto-fulcral triangle (DFT), comprising the alpha, beta, and delta angle, the acromion-glenoid angle (AGA), the coracoid-glenoid centre-posterior acromial angle (CGA), the anterior tilt (TA CGA) and the posterior tilt of the CGA (PT CGA). Three observers placed the landmarks on the 3D bone meshes, allowing us to calculate the inter-observer error. The main differences in the DFT were found between humans and the great apes, with small differences between the great apes. The DFT of humans was significantly lower compared to that of the great apes, with the smallest alpha (32.7°), smallest delta (45.7°) and highest beta angle (101.6°) of all genera. The DFT of chimpanzees was significantly higher compared to that of humans (p < 0.01), with a larger alpha (37.6°) and delta angle (54.5°) and smaller beta angle (87.9°). The mean AGA of humans (59.1°) was significantly smaller (p < 0.001) than that of gorillas (68.8°). The mean CGA of humans (110.1°) was significantly higher (p < 0.001) than in orangutans (92.9°). Humans and gorillas showed mainly a posterior tilt of their coracoacromial complex whilst chimpanzees showed mainly an anterior tilt. The coracoacromial complex of the orangutans was not tilted anteriorly or posteriorly. With our image-based method, we were able to identify morphological features of the scapula that differed significantly between hominid genera. However, we did not find an overall dichotomy in scapular morphology geared towards high stability (Pan/Gorilla) or high mobility (Homo/Pongo). Further research is needed to investigate the functional implications of these differences in scapular morphology.

Development of an Image-Based Methodology for the Evaluation of Histopathological Features in Human Meningioma.

Meningioma is the most common intracranial tumor in adulthood. With a clear female predominance and a recurrence rate that reaches 20%, it is, despite being considered a benign tumor, a pathology that greatly compromises post-diagnosis quality of life. Its prone to recur or progress to a higher degree is difficult to predict in the absence of obvious histological criteria. This project aims to develop an automatic methodology to aid in the diagnosis of meningiomas that is objective and easily reproducible. The methodology is based on histopathological image analysis using artificial intelligence and machine learning algorithms. It includes a semi-automatic process of identification and cleaning of the scanned samples, an automatic detection of the nuclei of each image and, finally, the parameterization of the samples. The obtained data together with the clinical information will be analyzed using statistical methods in order to provide a methodology to support clinical diagnosis and decision-making in patient management. The result is the development of an effective methodology that generates a set of data associated with morphological parameters with different trends according to the pathological groups studied. A tool has been developed that allows an effective semiautomatic analysis of the images to evaluate these parameters in an objective and reproducible way, helping in clinical decision-making and facilitating to undertake projects with large sample series. Clinical Relevance- The main contribution of this project is in the field of neuropathology, for the diagnosis of meningiomas, the most common brain tumor. The present project provides an objective and quantifiable prognosis methodology for the meningiomas, offering a more precise monitoring of the treatment applied to the patient, resulting in a better prognosis and better quality of life.

Determining crack kinematics from imaged crack patterns

Determining the relationship between the cause of damage and the subsequent structural behavior of infrastructure systems requires an accurate characterization of the propagation of cracks, which represents the evolution of the damage state. When no information about the cause of damage is available, kinematic approaches can be used to describe the motion of crack contours. Current image-based approaches to derive crack kinematics use digital image correlation (DIC) on a set of sequential images as the crack propagates. However, DIC is invasive in that the structure surfaces must be painted with random speckle patterns, limiting its use primarily to controlled experiments. In this paper, we propose a novel image-based methodology for computing crack opening in Mode I or Mode II. As an input, this method takes a binary image from a semantic segmentation of an image of a crack pattern. This binary image is used to detect the opposite edges along the crack, which are then registered using an optimization algorithm based on the Euclidean transformation model and non-linear least squares. As a final output, this method produces displacement maps in the tangential and normal directions to the crack skeleton. To demonstrate its performance, we validate our methodology first with synthetic crack patterns and then with real crack patterns. Because this methodology for determining crack openings requires only simple data (just a binary crack pattern image), it is straightforward, robust, and adaptable, thus contributing to the development of structural image-based damage assessments. The computational codes and datasets are available to the public for future research and benchmarking on https://github.com/eesd-epfl/crack_kinematics and https://doi.org/10.5281/zenodo.6632071.

Spatiotemporal measurement of concentration-dependent diffusion coefficient

We introduce a method to measure the concentration-dependent diffusion coefficient from a sequence of images of molecules diffusing from a source toward a sink. Generally, approaches measuring the diffusion coefficient, such as fluorescence recovery after photobleaching (FRAP), assume that the diffusion coefficient is constant. Hence, these methods cannot capture the concentration dependence of the diffusion coefficient if present. Other approaches measure the concentration-dependent diffusion coefficient from an instantaneous concentration profile and lose the temporal information. These methods make unrealistic assumptions, are not robust, and lead to 100% error. We introduce an image analysis framework that utilizes spatial and temporal information in a sequence of concentration images and numerically solves the general form of Fick's second law using radial basis functions (RBF) to measure the concentration-dependent diffusion coefficient. We term this approach as concentration image diffusimetry (CID). Our method makes no assumptions about the sink and source size and the diffusion dependence on concentration. CID is superior to existing methods in estimating spatiotemporal changes and concentration-dependent diffusion. CID also provides a statistical uncertainty quantification on the measurements using a bootstrapping approach, improving the reliability of the diffusion measurement. We assessed CID's performance using synthetically generated images. Our analysis suggests that CID accurately measures the diffusion coefficient with less than 2% error for most cases. We validated CID with FRAP experimental images and showed that CID agrees with established FRAP algorithms for samples with a constant diffusion coefficient. Finally, we demonstrate the application of CID to experimental datasets of a concentration gradient-driven protein diffusion into a tissue replicate. In conclusion, this work presents an image-based methodology that uses the spatial and temporal changes of concentration fields to measure the concentration-dependent diffusion coefficient.

Structural feature investigation of wooden artifacts through imaging techniques: a step forward in the preservation of historical musical instruments

Abstract Bowed string instruments represent a peculiar class of artworks, in some cases of historical relevance, capable of producing sound. Concert activity and natural ageing could cause mechanical stress that may lead to defects and fractures. Here, we propose an image-based methodology suitable to investigate such structural features in wooden instruments. The combined use of X-ray radiography and infrared thermography enabled a better identification and documentation of defects, woodworm galleries and cracks, thus enhancing the commonly employed approach.

Evaluation of the Role of Reclaimed Asphalt Pavement Preheating on Cracking Behavior of Hot Mix Asphalt Recycled Mixtures by Digital Image Analysis

Abstract In the last few decades, the need for reducing the exploitation of finite sources has led to an increasing use of reclaimed asphalt pavement (RAP) for the construction, maintenance, and rehabilitation of road pavements. During hot mix asphalt (HMA) plant production, RAP can be added at ambient temperature or preheated into special drums. When designing an RAP mixture, it is essential to dose the correct amount of virgin binder according to the percentage of the reactivated aged one. RAP preheating plays a key role in this process, although no reliable methods are available for achieving an accurate estimation. This article presents an innovative digital image-based methodology, named overlapped digital image (OIA) analysis, to better understand the role of reactivated binder on the cracking behavior of HMA-RAP mixtures. A recycled mixture was produced in the laboratory by adding RAP both at room temperature (25°C) and after preheating (150°C) and subsequently tested according to the Superpave IDT at 10°C and 25°C. The tests were combined with the OIA analysis to identify how the strain patterns and the initiation and propagation of fractures developed, according to the reactivation of the aged asphalt binder. The results show important outcomes in terms of cracking behaviors highlighting the important role of RAP preheating for inducing aged binder reactivation.

Homogeneity of the selected food mixes

The article presents the results of homogeneity assessments for selected food mixes based on computer image analysis. The study was conducted on müsli and condiment mixes standardly available on the consumer market. A total of 40 different ready-for-use products were analysed. Collected samples from three package of each product were placed in a special chamber and then photographed. Photographs were then subjected to computer image analysis to acquire information on the percentage content of individual components. Homogeneity assessment was based on the contents of a selected component called tracer and the coefficient of variation (CV). Lower CV values (3.02–27.31%) and thus better homogeneity was observed for condiment mixes as compared to müsli mixes (3.57–59.15%). Fourteen of twenty condiment mixes had adequate (acceptable at CV ≤ 10%) mixing degree. For the müsli, only six of the tested mixes had appropriate homogeneity. The presented results are a preliminary to developing an image-based methodology for determining the uniformity of granular dry food mixes.

In situ Growth Rate Assessment of the Hexactinellid Sponge Asconema setubalense Using 3D Photogrammetric Reconstruction

We describe the first application of a non-invasive and novel approach to estimate the growth rate of Asconema setubalense (Porifera, Hexactinellida) through the use of 3D photogrammetric methodology. Structure-from-Motion techniques (SfM) were applied to videos acquired with the Politolana ROTV in the El Cachucho Marine Protected Area (MPA) (Cantabrian Sea) on three different dates (2014, 2017, and 2019) over six years. With these data, a multi-temporal study was conducted within the framework of MPA monitoring. A complete 3D reconstruction of the deep-sea floor was achieved with Pix4D Mapper Pro software for each date. Having 3D point clouds of the study area enabled a series of measurements that were impossible to obtain in 2D images. In 3D space, the sizes (height, diameter, cup-perimeter, and cup-surface area) of several A. setubalense specimens were measured each year. The annual growth rates recorded ranged from zero (“no growth”) for a large size specimen, to an average of 2.2 cm year–1 in cup-diameter, and 2.5 cm year–1 in height for developing specimens. Von Bertalanffy growth parameters were estimated. Taking into account the size indicators used in this study and based on the von Bertalanffy growth model, this sponge reaches 95% maximum size at 98 years of age. During the MPA monitoring program, a high number of specimens disappeared. This raised suspicions of a phenomenon affecting the survival of this species in the area. This type of image-based methodology does not cause damage or alterations to benthic communities and should be employed in vulnerable ecosystem studies and MPA monitoring.

Determination of specific surface area of irregular aggregate by random sectioning and its comparison with conventional methods

A two-dimensional (2D) image-based methodology was proposed to measure the specific surface area (SSA, specified as the surface area per unit volume) of irregular aggregate by random sectioning. Conventional methods including spherical assumption, Brunauer-Emmett-Teller (BET) and computed tomography (CT) tests were used and compared in this study. Results show that spherical assumption provides the lowest SSA among these methods since the feature of anisotropy in dimension is not considered. SSA by BET test has one order of magnitude higher value than others, which is attributed to the fact that BET method measures each position of particles that nitrogen molecule can be adsorbed on during the applied relative pressure, based on the ‘pixel’ of nitrogen molecule. The proposed random sectioning method presents very similar SSA result compared to CT method, indicating that it can be considered as a reliable method. To improve the estimation of SSA by random sectioning method, factors that may influence SSA result were analyzed. Results indicate that the number of samples should be high enough to reach a constant result and the thresholding algorithm should be adequate. Besides, a higher resolution of pixel provides a higher SSA value. The comparison among these methods demonstrate that it is necessary to determine the scale at which the features of the surface are supposed to be captured before selecting the optimal testing method.

A simplified and open-source approach for multiple-valued water surface measurements in 2D hydrodynamic experiments

Water elevation measurements in 2D hydrodynamic experiments are widely used for validating analytical and numerical models. Experimental research has shown that some phenomena can present multiple-valued water surfaces. However, conventional wave probe sensors do not provide measurements of these surfaces, which is required for appropriate model comparisons. This paper aims to propose a simplified and open-source image-based methodology to measure the spatio-temporal evolution of multiple-valued water surface elevations observed in two-dimensional hydrodynamic experiments, considering the problem of shipping water on a fixed structure as the topic of application. This approach examines the stages of image processing and analysis through morphological operations, which have been implemented in plugins for free use in the open-source ImageJ software. Measurements performed in two experimental study cases of shipping water on the deck of a fixed structure, due to single and multiple incident waves, were compared with measurements taken by conventional wave probe sensors and manual tracking to verify the performance of the methodology. The results obtained give the time series of elevation of multiple-valued water surfaces, which can be obtained at any desired position over the horizontal domain of the images, at low cost and high computational efficiency. The present approach has been made available for its free use and can be adapted to analyze the spatio-temporal flow evolution in a wide range of 2D hydrodynamic experiments.

3D RECONSTRUCTION AND MESH OPTIMIZATION OF UNDERWATER SPACES FOR VIRTUAL REALITY

Abstract. In this contribution, we propose a versatile image-based methodology for 3D reconstructing underwater scenes of high fidelity and integrating them into a virtual reality environment. Typically, underwater images suffer from colour degradation (blueish images) due to the propagation of light through water, which is a more absorbing medium than air, as well as the scattering of light on suspended particles. Other factors, such as artificial lights, also, diminish the quality of images and, thus, the quality of the image-based 3D reconstruction. Moreover, degraded images have a direct impact on the user perception of the virtual environment, due to geometric and visual degenerations. Here, it is argued that these can be mitigated by image pre-processing algorithms and specialized filters. The impact of different filtering techniques on images is evaluated, in order to eliminate colour degradation and mismatches in the image sequences. The methodology in this work consists of five sequential pre-processes; saturation enhancement, haze reduction, and Rayleigh distribution adaptation, to de-haze the images, global histogram matching to minimize differences among images of the dataset, and image sharpening to strengthen the edges of the scene. The 3D reconstruction of the models is based on open-source structure-from-motion software. The models are optimized for virtual reality through mesh simplification, physically based rendering texture maps baking, and level-of-details. The results of the proposed methodology are qualitatively evaluated on image datasets captured in the seabed of Santorini island in Greece, using a ROV platform.

PM2.5 concentration estimation using convolutional neural network and gradient boosting machine

Surface monitoring, vertical atmospheric column observation, and simulation using chemical transportation models are three dominant approaches for perception of fine particles with diameters less than 2.5 micrometers (PM2.5) concentration. Here we explored an image-based methodology with a deep learning approach and machine learning approach to extend the ability on PM2.5 perception. Using 6976 images combined with daily weather conditions and hourly time data in Shanghai (2016), trained by hourly surface monitoring concentrations, an end-to-end model consisting of convolutional neural network and gradient boosting machine (GBM) was constructed. The mean absolute error, the root-mean-square error and the R-squared for PM2.5 concentration estimation using our proposed method is 3.56, 10.02, and 0.85 respectively. The transferability analysis showed that networks trained in Shanghai, fine-tuned with only 10% of images in other locations, achieved performances similar to ones from trained on data from target locations themselves. The sensitivity of different regions in the image to PM2.5 concentration was also quantified through the analysis of feature importance in GBM. All the required inputs in this study are commonly available, which greatly improved the accessibility of PM2.5 concentration for placed and period with no surface observation. And this study makes an exploratory attempt on pollution monitoring using graph theory and deep learning approach.

Enhancement of Archaeological Proxies at Non-Homogenous Environments in Remotely Sensed Imagery

Optical remote sensing has been widely used for the identification of archaeological proxies. Such proxies, known as crop or soil marks, can be detected in multispectral images due to their spectral signatures and the distinct contrast that they provide in relation to the surrounding area. The current availability of high-resolution satellite datasets has enabled researchers to provide new methodologies and algorithms that can further enhance archaeological proxies supporting thus image-interpretation. However, a critical point that remains unsolved is the detection of crop and soil marks in non-homogenous environments. In these areas, interpretation is problematic even after the application of sophisticated image enhancement analysis techniques due to the mixed landscape and spectral confusion produced from the high-resolution datasets. To overcome this problem, we propose an image-based methodology in which the vegetation is suppressed following the “forced invariance” method and then we apply a linear orthogonal transformation to the suppressed spectral bands. The new Red–Green–Blue (RGB) image corresponds to a new three-band spectral space where the three axes are linked with the crop mark, vegetation, and soil components. The study evaluates the proposed approach in the archaeological site of “Nea Paphos” in Cyprus using a WorldView-2 multispectral image aiming to overcome the limitations of the mixed environments.

Effects of surgical targeting in laser interstitial thermal therapy for mesial temporal lobe epilepsy: A multicenter study of 234 patients.

Laser interstitial thermal therapy (LITT) for mesial temporal lobe epilepsy (mTLE) has reported seizure freedom rates between 36% and 78% with at least 1 year of follow-up. Unfortunately, the lack of robust methods capable of incorporating the inherent variability of patient anatomy, the variability of the ablated volumes, and clinical outcomes have limited three-dimensional quantitative analysis of surgical targeting and its impact on seizure outcomes. We therefore aimed to leverage a novel image-based methodology for normalizing surgical therapies across a large multicenter cohort to quantify the effects of surgical targeting on seizure outcomes in LITT for mTLE. This multicenter, retrospective cohort study included 234 patients from 11 centers who underwent LITT for mTLE. To investigate therapy location, all ablation cavities were manually traced on postoperative magnetic resonance imaging (MRI), which were subsequently nonlinearly normalized to a common atlas space. The association of clinical variables and ablation location to seizure outcome was calculated using multivariate regression and Bayesian models, respectively. Ablations including more anterior, medial, and inferior temporal lobe structures, which involved greater amygdalar volume, were more likely to be associated with Engel class I outcomes. At both 1 and 2 years after LITT, 58.0% achieved Engel I outcomes. A history of bilateral tonic-clonic seizures decreased chances of Engel I outcome. Radiographic hippocampal sclerosis was not associated with seizure outcome. LITT is a viable treatment for mTLE in patients who have been properly evaluated at a comprehensive epilepsy center. Consideration of surgical factors is imperative to the complete assessment of LITT. Based on our model, ablations must prioritize the amygdala and also include the hippocampal head, parahippocampal gyrus, and rhinal cortices to maximize chances of seizure freedom. Extending the ablation posteriorly has diminishing returns. Further work is necessary to refine this analysis and define the minimal zone of ablation necessary for seizure control.