Volume Datasets Research Articles

Sterile donor tomography for improvement of refractive results after keratoplasty

Purpose: Any corneal microsurgeon may have inadvertently transplanted a donor corneal tissue with (subclinical) keratoconus or prior keratorefractive surgery, which typically leads to postoperative refractive surprises and cannot always be detected in the eye bank with only slit lamp. Given the increased number of keratorefractive procedures performed in the last decades, eye banks will soon have to face this problem more intensively. Thus, the efficiency and reliability of anterior segment optical coherence tomography (AS‐OCT) as a non‐invasive and sterile screening method in the eye bank to detect corneal grafts with curvature and/or thickness abnormalities was assessed.Methods: 1315 donor corneal tissues mounted in sterile tissue cultivation flasks were imaged using an AS‐OCT. The corneal tissues were preserved in organ culture medium I and transferred into organ culture medium II (containing dextran T‐500 6%) for deswelling at least 24 h prior to measurement and keratoplasty. Depth raster scans were performed through the posterior surface of the corneal tissues within a 7 mm central zone to create 3D volume data. The volume data set was preprocessed to eliminate flask reflections artefacts and to define the region of interest (ROI). Subsequently, the adaptation of a sphero‐cylindrical surface model was carried out with raytracing. Thus, the radii of curvature for the front and back surfaces can be determined and a corneal thickness map is generated.Results: The mean steep/flat front surface radius was 7.46 ± 0.29 (5.07–9.29)/7.69 ± 0.24 (6.70–9.50) mm, the corresponding values for the back surface being 6.47 ± 0.32 (5.00–8.00)/6.80 ± 0.31 (5.81–8.00) mm and the mean central thickness was 610 ± 84 (379–1457) μm. Abnormalities (beyond ±2 or ± 3 SD) were found in 140 or 34 corneas (10.6% or 2.6%) for anterior surface curvature, 120 or 38 corneas (9.1% or 2.9%) for the posterior surface, and 55 or 16 corneas (4.2% or 1.2%) for thickness.Conclusions: The AS‐OCT provides an objective, sterile and semi‐automated screening method to identify corneal morphological and refractive alterations (e.g. keratoconus, status post PRK/LASIK) and further optimize corneal donor selection in the eye bank. Corneal donors with curvature or thickness abnormalities ±3 SD do not have to be discarded but can be used for posterior lamellar keratoplasty or tectonic keratoplasty.

An improved Prophet emergency traffic-flow prediction model

Emergencies are rare and random, but cause dramatic changes in traffic volumes whenever they occur. It is therefore very challenging to predict emergency traffic volumes accurately. The aim of this paper is to provide a practical methodology for predicting traffic volumes during emergencies; this is done using the Prophet model and by improving the event function of the model. The proposed approach isolates the event impacts through time series decomposition techniques; it allows the model to add points in time when traffic flow changes abruptly and to incorporate external factors useful to adapt to the specific background imposed by the emergency. The main data used in the paper were from the daily traffic volume data set published on the Luxembourg Open Data platform. These data were collected over a period from January 2017 to December 2021. The data set covers the period of impact of two emergencies. The proposed method and four comparator models were applied to the second emergency period. The results show that the proposed method can accurately predict unconventional changes caused by emergencies and, by way of a comparative analysis, that it has better prediction accuracy with real data than the other comparator models under the same attribute conditions.

BIOM-66. ESTABLISHMENT OF A PROGNOSTIC MODEL FOR GLIOBLASTOMA MULTIFORME MAGNETIC RESONANCE IMAGING BASED ON IMBALANCED CLASSES, CLASSIFICATION, AND KAPLAN-MEIER SURVIVAL CURVE LEARNING ALGORITHMS

Abstract Glioblastoma multiforme (GBM) is a rapidly invasive brain tumor with a high mortality rate. It is accompa-nied by peripheral edema. Physicians use magnetic resonance imaging (MRI) to diagnose each patient’s con-dition in clinical practice. The current use of machine learning to classify brain tumors has an accuracy of about 90% in most studies. Therefore, this study aimed to improve its prediction accuracy using machine learning models to predict GBM patient survival or non-survival. The study used MRI T1-related and T2-related sequences to obtain GBM tumor and edema area attributes. It then divided them into four da-tasets: maximum tumor area, maximum edema area, total tumor volume, and total edema volume. These four datasets were used as inputs for classification models based on support vector machines, decision tree algo-rithms, random forest algorithms, and multilayer perceptron (MLP) to predict patient survival. A confusion matrix was used to evaluate each model and determine the most suitable models for each dataset based on their accuracy. MLP was the most appropriate for predicting the overall edema volume dataset, with the highest accuracy in predicting GBM patient survival or non-survival at 96.97%. Hopefully, this study can assist physicians in assessing and diagnosing GBM patients’ survival status in the future. Keywords: Classification Models; Glioblastoma Multiforme; KaplanMeier Curve; Magnetic Resonance Imaging; Peritumoral Edema

Towards better traffic volume estimation: Jointly addressing the underdetermination and nonequilibrium problems with correlation-adaptive GNNs

Traffic volume is an indispensable ingredient to provide fine-grained information for traffic management and control. However, due to the limited deployment of traffic sensors, obtaining full-scale volume information is far from easy. Existing work on this topic focuses primarily on improving the overall estimation accuracy of a particular method and ignores the underlying challenges of volume estimation, thereby having inferior performance in some critical tasks. This paper studies two key problems with regard to traffic volume estimation: (1) underdetermined traffic flows caused by fully undetected paths that can allow arbitrary volume values without violating the conservation law, where using local side information is insufficient to tackle, and (2) nonequilibrium traffic flows arise when traffic flows vary in density over space and time due to congestion propagation delay, which produce time-shifted volume readings to varying degrees. Here we demonstrate a graph-based deep learning method that offers a data-driven, equation-free, and correlation-adaptive approach to address the above issues and perform accurate network-wide traffic volume estimation. Particularly, in order to quantify the dynamic and nonlinear speed-volume relationships for the estimation of underdetermined flows, a speed pattern-adaptive adjacency matrix based on graph attention is developed and integrated into the graph convolution process, to capture nonlocal correlations between volumes. To measure the impacts of nonequilibrium flows, a temporal masked and clipped attention combined with a gated temporal convolution layer is customized to capture time-asynchronous correlations between upstream and downstream sensors under varying impacts of congestion delay. We then evaluate our model on a real-world highway traffic volume dataset and compare it with several benchmark models. It is demonstrated that the proposed model achieves high estimation accuracy even under 20% sensor coverage rate and outperforms other baselines significantly, especially on underdetermined and nonequilibrium flow locations. Furthermore, comprehensive quantitative model analysis is also carried out to justify the model designs. The source code and datasets are publicly available at: .

Semi-Automatic Measurement of Fetal Cardiac Axis in Fetuses with Congenital Heart Disease (CHD) with Fetal Intelligent Navigation Echocardiography (FINE).

Congenital heart disease (CHD) is one of the most common organ-specific birth defects and a major cause of infant morbidity and mortality. Despite ultrasound screening guidelines, the detection rate of CHD is limited. Fetal intelligent navigation echocardiography (FINE) has been introduced to extract reference planes and cardiac axis from cardiac spatiotemporal image correlation (STIC) volume datasets. This study analyses the cardiac axis in fetuses affected by CHD/thoracic masses (n = 545) compared to healthy fetuses (n = 1543) generated by FINE. After marking seven anatomical structures, the FINE software generated semi-automatically nine echocardiography standard planes and calculated the cardiac axis. Our study reveals that depending on the type of CHD, the cardiac axis varies. In approximately 86% (471 of 542 volumes) of our pathological cases, an abnormal cardiac axis (normal median = 40-45°) was detectable. Significant differences between the fetal axis of the normal heart versus CHD were detected in HLHS, pulmonary atresia, TOF (p-value < 0.0001), RAA, situs ambiguus (p-value = 0.0001-0.001) and absent pulmonary valve syndrome, DORV, thoracic masses (p-value = 0.001-0.01). This analysis confirms that in fetuses with CHD, the cardiac axis can significantly deviate from the normal range. FINE appears to be a valuable tool to identify cardiac defects.

Determinants of bicycle crashes at urban signalized intersections

Problem: Bicycle volumes are increasing in many regions worldwide leading to higher relevance of an in-depth understanding of bicyclist safety mechanisms. Detailed studies on bicyclist safety that consider exposure and distinguish by intersection category and crash types are missing for urban signalized intersections, which are of particular relevance for bicyclist safety. Method: Based on a comprehensive dataset of motorist and bicyclist volumes and infrastructure characteristics for a sample of 269 signalized intersections in two German cities, we utilize a top-down approach to analyze firstly, bicycle crashes of all types and secondly, bicycle crashes by type including turning, right-of-way and loss-of-control. A combination of descriptive statistics and Accident Prediction Models (APM) are applied as analysis methods. Results: Bicycle volumes are relevant for all types of intersections and crashes, whereas the effect of motor vehicle volumes differ between these different applications. The separation of bicyclists from motor vehicles in time and space increases their safety but also leads to behavioral adaption and risk compensation. The likelihood of right-of-way crashes even increases with more separation in the signaling scheme. The main predictor for loss-of-control crashes in terms of infrastructure are tram tracks. Summary: This study provides insights on relevant determinants of bicycle crashes at urban signalized intersections at several levels of detail. Exposure variables as well as the physical separation of bicyclists from motor vehicles show consistent effects on bicycle crash numbers whereas the effects of signaling differ between crash types. Practical Applications: The different types of intersections and crashes follow each specific mechanism of bicyclist safety. The separation of bicyclists and motorists in time and space are paramount at intersections with high bicycle volumes. Risk compensation such as red light running becomes more important as intersections get smaller and motor vehicle volumes decrease.

Pix2PixSSR: Spatial super‐resolution synthesis and visualization for time‐varying volumetric data

AbstractUpscaling of the time‐varying volume data is significant, since it can be used in in situ visualization to help scientists fast analyse complex simulations relevant to time‐varying volume data. A novel deep learning method called Pix2Pix spatial super‐resolution (Pix2PixSSR), which can be used to generate spatial super‐resolution of the time‐varying volume data is proposed here. It consists of two main components: One is a variant UNet‐like generator that takes the low resolution volume sequence as input and generates the high resolution counterparts; one is a PatchGAN discriminator that takes both low and high resolution volume sequences as input and predicts their realness. To validate its advantages, we qualitatively and quantitatively compare it with the state‐of‐the‐art upscaling techniques. More specifically, two experiments are performed. The first experiment uses the same variable of a time‐varying volume dataset for training and inference, while the second experiment uses different variables for training and inference. The experimental results show that for most cases, the Pix2PixSSR can generate the most similar super‐resolution to the ground truth, compared to the state‐of‐the‐art techniques.

Prediction of gas drainage changes from nitrogen replacement: A study of a TCN deep learning model with integrated attention mechanism

Accurate prediction of pure gas volume changes in nitrogen injection replacement coal seams is of great significance to increase coalbed methane (CBM) production and prevent underground gas disasters in coal mines. However, the mechanism of coal seam gas flow during nitrogen injection replacement is complex, and it is extremely difficult to achieve quantitative prediction of the pure volume of gas in nitrogen injection replacement coal seams. In this study, we propose a new model for predicting the change of pure amount of gas in coal seam of nitrogen injection replacement in coal mines (Attention-TCN). Meanwhile, we believe that a stable and reliable predictive model should have the ability to capture the underlying patterns and relationships of regular and noisy datasets during the learning process, rather than memorizing training data. Therefore, in this paper, the Attention-TCN model is trained and tested using the results of nitrogen injection and replacement methane double diffusion test (regularity dataset) and the results of nitrogen injection and replacement experiment in coal mine underground engineering (noisy dataset), respectively. The difference between the Attention-TCN model and the baseline models of TCN, gated recurrent neural network (GRU) and long and short-term memory neural network (LSTM) was also compared. The validity of the model was demonstrated using ten-fold cross-validation results. The results show that the proposed Attention-TCN prediction model achieves good prediction performance on both regular and noisy datasets, with prediction R2 greater than 0.99, and is highly flexible and robust. The model is better able to extract the basic features and structures in different types of datasets, enabling it to perform well on unseen data. The ten-fold cross-validation results clearly show that the Attention-TCN model is more accurate and all outperforms the TCN, GRU and LSTM prediction models. In addition, the prediction results of all models for different mine underground nitrogen injection replacement coal seam pure gas volume datasets further validate that the Attention-TCN model has better ability to generalize to new datasets and is more effective and practical for predicting the variation of pure gas volume in underground nitrogen injection replacement coal seams in coal mines.

Characterizing Spatial Heterogeneity in Reservoir Evaporation within the Rio Grande Basin Using a Coupled Version of the Weather, Research, and Forecasting Model

Abstract Increasing evaporative demand from storage reservoirs is aggravating water scarcity issues across the American West. In the Rio Grande basin, open water evaporation estimates represent approximately one-fifth of all water losses from the basin. However, most estimates of reservoir evaporation rely on outdated methods, point measurements, or simplistic models. Warming temperatures and increasing atmospheric evaporative demand are stressing overallocated resources, increasing the need for improved evaporation estimates. In response to this need, we develop open water evaporation estimates at Elephant Butte Reservoir (EBR), New Mexico, using three evaporation models and field measurements. Few studies quantify spatial heterogeneity in evaporation rates across large reservoirs; we therefore focus our efforts on using the Weather Research and Forecasting Model coupled to an energy budget lake model, WRF-Lake, to simulate evaporation across EBR over the course of two years. We compare results from WRF-Lake, which simulates lake heat storage, to results from the Complementary Relationship Lake Evaporation (CRLE) model and the Global Lake Evaporation Volume dataset (GLEV). Results indicate that monthly and annual evaporation totals from WRF-Lake and GLEV are similar, while CRLE overestimates annual evaporation totals, with monthly peak evaporation offset compared to WRF-Lake and GLEV. While WRF-Lake and GLEV appear to capture monthly and annual evaporation totals, only WRF-Lake simulates differences in evaporation totals across the reservoir surface. Average annual evaporation at EBR was approximately 1487 mm, yet annual totals differed by up to 545 mm depending on location. This study improves understanding of open water evaporation and elucidates limitations of extrapolating point in situ or bulk evaporation estimates across large reservoirs. Significance Statement Changes in climate are amplifying the loss of stored water in reservoirs due to increases in evaporation. Water managers need to account for this water loss, but many current methods do not accurately reflect the temporal and spatial variability in evaporation across large, heterogeneous reservoirs. To address this gap, we use a numerical weather prediction model coupled to a lake model to simulate spatial heterogeneity in reservoir evaporation on a subdaily time step. Our results suggest that bulk evaporation models may be sufficient for estimating evaporation at smaller, more homogeneous reservoirs, but more complex formulations may be more appropriate for estimating evaporation rates at large, complex reservoirs and for better understanding the heat storage affects that influence temporal variability of evaporation.

Fast algorithm for 3D volume reconstruction from light field microscopy datasets.

Light field microscopy can capture 3D volume datasets in a snapshot, making it a valuable tool for high-speed 3D imaging of dynamic biological events. However, subsequent computational reconstruction of the raw data into a human-interpretable 3D+time image is very time-consuming, limiting the technique's utility as a routine imaging tool. Here we derive improved equations for 3D volume reconstruction from light field microscopy datasets, leading to dramatic speedups. We characterize our open-source Python implementation of these algorithms and demonstrate real-world reconstruction speedups of more than an order of magnitude compared with established approaches. The scale of this performance improvement opens up new possibilities for studying large timelapse datasets in light field microscopy.

Distribution and associated factors of crystalline lens volume in noncataract adolescents and adults and patients with cataract in a Chinese population.

To explore the distribution of lens volume (VOL) and its associated factors in noncataract adolescents and adults and patients with cataract in a Chinese population. Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China. Cross-sectional study. 1674 eyes from 1674 Chinese participants (690 adolescents and 363 adults without cataract, and 621 patients with cataract) aged from 7 to 90 years were included. Lens thickness (LT) and lens diameter (LD) were measured using swept-source anterior segment optical coherence tomography (SS-AS OCT) to calculate VOL. Axial length (AL) was measured by IOL-Master 700. Pearson correlation analysis and multivariate linear regression models were used to evaluate the potential associated factors of lens dimensions. The mean VOL was 167.74 ± 12.18 mm 3 in noncataract adolescents, 185.20 ± 14.95 mm 3 in noncataract adults, and 226.10 ± 49.25 mm 3 in patients with cataract. VOL had no significant correlation with AL in patients with cataract ( P > .05), neither in noncataract adolescents nor noncataract adults, when adjusted with LT, LD, age, and sex ( P > .05). On the other hand, eyes with longer ALs tended to have smaller LTs and larger LDs in all groups (all P -trend < .05). Larger VOL was associated with older age in all groups (all P < .001). A data set of VOLs in Chinese eyes over a wide age range was presented. It is inaccurate to predict VOL, LT, and LD solely according to AL. The direct measurement and calculation of VOL in vivo and the establishment of the normal range of VOL could help predict the size of lens capsular bag and plan cataract surgery.

Data Mining Techniques in Decision Making

Data mining aims to find relevant information for decision-making, forecasting, optimising, and other business or research reasons. In this study, data mining is used in the domain of decision-making. Various problems for this domain exist in the literature, including selection problems, considering unnecessary attributes, and removing irrelevant attributes in the dataset by applying different preprocessing techniques. For this purpose, a smartphone dataset is used, and different machine learning classifiers are applied. Decision Tree, Naive Bayes, SMO, bagging, and Random Forest were chosen for precision, recall, and F-measure. Results demonstrate that Random Forest obtains 57% accuracy and performs better on average than the other algorithms. The class "Saving Account" was classified with 52% accuracy as of the other attributes, but it has the fewest errors depending on the attributes. This study can be extended by applying the proposed methodology to a rich volume dataset and deep-learning techniques.

Three-dimensional/four-dimensional spatiotemporal image correlation morphology of the ductus arteriosus in fetuses with pulmonary atresia undergoing neonatal ductal stenting.

The value of prenatal identification of morphology of ductus arteriosus in fetuses with congenital heart defects (CHD) with pulmonary atresia and duct-dependent pulmonary circulation (DDPC) in planning neonatal ductal stenting procedure is untested. The aim of the study is to analyze the utility of three-dimensional/four-dimensional (3D/4D) spatiotemporal image correlation (STIC) fetal echocardiography in delineating the morphology of ductus arteriosus in fetuses with DDPC undergoing neonatal ductal stenting. In this retrospective study (2017-22), prenatal imaging of pulmonary artery (PA) anatomy, aortic arch sidedness, and morphology of ductus arteriosus (ductal origin was classified as vertical/horizontal and ductal course as tortuous/straight) was done using 3D/4D STIC imaging and volume datasets. Prenatal findings were correlated with angiographic findings during stenting and the degree of agreement was calculated. We included 27 fetuses with a prenatal diagnosis of CHD with DDPC who underwent neonatal ductal stenting. The accuracy of prenatal assessment of PA anatomy, branch PA stenosis, and arch sidedness was 100%, 92.6%, and 88.9%, respectively. The accuracy of prenatal assessment of ductal origin and course, compared with angiography, was 85.2% and 88.9%, respectively. Prenatal imaging had a diagnostic accuracy of 100% for vertical straight and horizontal tortuous ducts, 84.6% for vertical tortuous, and 67% for horizontal straight ducts. Duct stenting was successful in 25 (92.6%) babies; two died after the procedure from stent occlusion. Fetal echocardiography using 3D/4D STIC imaging enables accurate delineation of the morphology of ductus arteriosus in fetuses with DDPC, thereby aiding parental counseling and planning neonatal ductal stenting.

Acute anatomic and hemodynamic impact of mitral TEER: G4 MitraClip vs. PASCAL

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Transcatheter mitral edge-to-edge repair (TEER) represents a safe and effective alternative to surgery for high-risk patients suffering from symptomatic severe mitral regurgitation (MR). New devices and new device iterations are constantly developed and their impact on the mitral valve (MV) anatomy should be regularly evaluated to provide the best patient-tailored approach in the future. Purpose The purpose of this study was to compare the acute anatomic and hemodynamic effects of the worldwide most implanted commercially available TEER devices: the Abbott G4 MitraClip (MC) vs. the Edwards PASCAL. Methods Consecutive patients from our mitral registry treated by TEER were included. High quality volume datasets focused on the MV were acquired during each intervention. Mean transvalvular gradient (Gd) corrected for the heart rate (HR), 3D mitral valve area (MVA) and anteroposterior diameter (AP) of MV annulus were evaluated before and after the implantation of each device; remaining orifices created after implantation were measured independently and summed. Results Eighty patients were included in this analysis; the majority were treated with "bulky" first devices: PASCAL P10 (10mm wide) or MC NTW/XTW (6mm wide). Individuals treated with MC exhibited higher MVA before clipping, however there were no differences in the AP diameter of the annulus between both groups. The first device produced a significantly higher reduction of MVA in the MC group, while no difference in MVA reduction was seen after the second implant. The impact on the AP-diameter (i.e., the indirect annuloplasty) and on the transvalvular corrected Gd after one or two devices was not significantly different between groups despite the smaller native MVA in the PASCAL population. Conclusion The design differences between both devices with an active closure for MC and a passive one for PASCAL (possibly leading to a lower tension on the leaflets) could explain the lower impact of the latter on the MVA, despite the wider arms of the P10. A study including a higher number of patients is needed to confirm these findings, which may affect patient selection according to the native MVA and the treatment strategy.

IH-TCGAN: Time-Series Conditional Generative Adversarial Network with Improved Hausdorff Distance for Synthesizing Intention Recognition Data.

As military technology continues to evolve and the amount of situational information available on the battlefield continues to increase, data-driven deep learning methods are becoming the primary method for air target intention recognition. Deep learning is based on a large amount of high quality data; however, in the field of intention recognition, it often faces key problems such as low data volume and unbalanced datasets due to insufficient real-world scenarios. To address these problems, we propose a new method called time-series conditional generative adversarial network with improved Hausdorff distance (IH-TCGAN). The innovation of the method is mainly reflected in three aspects: (1) Use of a transverter to map real and synthetic data into the same manifold so that they have the same intrinsic dimension; (2) Addition of a restorer and a classifier in the network structure to ensure that the model can generate high-quality multiclass temporal data; (3) An improved Hausdorff distance is proposed that can measure the time order differences between multivariate time-series data and make the generated results more reasonable. We conduct experiments using two time-series datasets, evaluate the results using various performance metrics, and visualize the results using visualization techniques. The experimental results show that IH-TCGAN is able to generate synthetic data similar to the real data and has significant advantages in the generation of time series data.

Hemodynamic predictors for the onset of ischemic stroke due to carotid artery stenosis using a computational fluid dynamics analysis

Background: Carotid artery stenosis is one of the major diseases responsible for atherosclerotic ischemic stroke. It is difficult to predict the onset of cerebral infarction by means of their known risk factors, including age, sex, diabetes mellitus, hypertension, dyslipidemia, and smoking habit. The carotid artery shape itself is a risk factor for stenosis, in which hemodynamics may be involved. We conduct an observational clinical study using a computational fluid dynamics (CFD) technique to investigate hemodynamic risk factors for carotid stenosis progression by enrolling and prospectively examining patients with carotid artery stenosis who underwent three-dimensional imaging of the carotid artery and carotid echocardiography. A total of 546 patients were registered in this study, which is designated the NHO Carotid CFD Study. To investigate hemodynamic predictors for the onset of ischemic stroke, we performed a multivariate analysis of 90 cases with carotid stenosis with an area stenosis rate of 50% to 85% among those enrolled in this clinical study, after adjustment for known risks. Methods: Patient-specific geometries of the carotid arteries were segmented and reconstructed from the volume data set of three-dimensional computed tomography angiography images in Digital Imaging and Communications in Medicine (DICOM) format, using Mimics and 3-matic (Materialise, Leuven, Belgium). Pulsatile blood flow was simulated using a CFD software package, ANSYS CFX (ANSYS, PA, USA), based on the Navier-Stokes equations for incompressible fluid. Individual vessel diameters and peak-systolic and end-diastolic velocities were measured with the Doppler ultrasound technique on common carotid arteries and internal carotid arteries of each patient to compute the corresponding flow rates. The stenotic carotid artery defined three regions: the “stenotic site” where the stenosis is present, the “proximal site” from the lower end of the stenosis to 10 mm proximal, and the “distal site” from the upper end of the stenosis to 10 mm distal. Results: Metrics related to proximal wall shear stress (WSS) disturbances, such as proximal transverse WSS (transWSS) (odds ratio (OR) 2.42, 95% confidence interval (95%CI) 1.32 to 5.00), proximal normalized transWSS (NtransWSS) (OR 1.71, 95%CI 1.02 to 3.03), and the stenotic/proximal ratio of transWSS (1/OR 1.59, 95%CI 0.39 to 0.88), had significant correlations with a history of cerebral infarction on the ipsilateral side of the stenotic artery. Conclusions: Our present analysis suggested that carotid arteries with the same degree of stenosis may be more likely to have a cerebral infarction in cases with higher transWSS in the proximal site than the stenotic one. In patients with these hemodynamic risks, underlying diseases should be controlled more strictly with imaging examinations at shorter intervals. This study was supported by a Grant-in-Aid for Japanese National Hospital Organization Multi-Center Clinical Research, and AMED under Grant Number JP15gm0810006h0301. This is the full abstract presented at the American Physiology Summit 2023 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Establishment of Age- and Sex-Specific Reference Cerebral Ventricle Volumes

The diagnosis of hydrocephalus is dependent on clinical symptoms and radiographic findings including ventriculomegaly. Our goal was to generate a data set of ventricular volume utilizing non-pathologic computed tomography (CT) scans for adults to help define reference ventricle size. We performed a retrospective analysis of non-contrast head CTs for adults at a single institution to identify patients who had undergone imaging and did not have a diagnosis of hydrocephalus, history of ventriculoperitoneal shunting, or treatments for hydrocephalus. A convolutional neural network was trained on hand-segmented scans from a variety of age ranges and then utilized to automate the segmentation of the entire data set. Ventricles on 866 CT scans were segmented to generate a reference range of volumes for both male and female individuals ranging in age from 18-99 years. The generated data were binned by age ranges. We have developed a convolutional neural network that can segment the ventricles on CT scans of adult patients over a range of ages. This network was used to measure the ventricular volume of non-pathologic head CTs to produce reference ranges for several age bins. This data set could be utilized to aid in the diagnosis of hydrocephalus by comparing potentially pathologic scans to reference ventricular volumes.

An assessment of potential causal links between deglaciation and eruption rates at arc volcanoes

One of the fundamental questions that underpins studies of the interactions between the cryosphere and volcanism is: do causal relationships exist between the ice volume on a volcano and its eruption rate? In particular, it is critical to determine whether the decompression of crustal magma systems via deglaciation has resulted in enhanced eruption rates along volcanic arcs in the middle to high latitudes. Evidence for such a feedback mechanism would indicate that ongoing glacier retreat could lead to future increases in eruptive activity. Archives of eruption frequency, size, and style, which can be used to test whether magma generation and eruption dynamics have been affected by local ice volume fluctuations, exist in the preserved eruptive products of Pleistocene-Holocene volcanoes. For this contribution, we have reviewed time-volume-composition trends for 33 volcanoes and volcanic groups in arc settings affected by glaciation, based on published radiometric ages and erupted volumes and/or compositions of edifice-forming products. Of the 33 volcanic systems examined that have geochronological and volumetric data of sufficient resolution to compare to climatic changes since ∼250 ka, increases in apparent eruption rates during post-glacial periods were identified for 4, with unclear trends identified for a further 12. Limitations in the geochronological and eruption volume datasets of the case studies make it difficult to test whether apparent eruption rates are correlated with ice coverage. Major caveats are: 1) the potential for biased preservation and exposure of eruptive materials within certain periods of a volcano’s lifespan; 2) the relative imprecision of geochronological constraints for volcanic products when compared with high-resolution climate proxy records; 3) the reliance on data only from immediately before and after the Last Glacial Termination (∼18 ka), which are rarely compared with trends throughout the Pleistocene to test the reproducibility of eruptive patterns; and 4) the lack of consideration that eruption rates and magma compositions may be influenced by mantle and crustal processes that operate independently of glacial advance/retreat. Addressing these limitations will lead to improvements in the fields of geochronology, paleoclimatology, and eruption forecasting, which could make valuable contributions to the endeavours of mitigating future climate change and volcanic hazards.

Dynamic Multi-View Graph Neural Networks for Citywide Traffic Inference

Accurate citywide traffic inference is critical for improving intelligent transportation systems with smart city applications. However, this task is very challenging given the limited training data, due to the high cost of sensor installment and maintenance across the entire urban space. A more practical scenario to study the citywide traffic inference is effectively modeling the spatial and temporal traffic patterns with limited historical traffic observations. In this work, we propose a dynamic multi-view graph neural network for citywide traffic inference with the method CTVI+. Specifically, for the temporal dimension, we propose a temporal self-attention mechanism that is capable of learning the dynamics of traffic data with the time-evolving traffic volume variations. For spatial dimension, we build a multi-view graph neural network, employing the road-wise message passing scheme to capture the region dependencies. With the designed spatial-temporal learning paradigms, we enable our traffic inference model to encode the dynamism from both spatial and temporal traffic patterns, which is reflective of intra- and inter-road traffic correlations. In our evaluation, CTVI+ achieves consistent better performance compared with different baselines on real-world traffic volume datasets. Further ablation study validates the effectiveness of key components in CTVI+. We release the model implementation at https://github.com/dsj96/TKDD.

Coal Gangue Classification Based on the Feature Extraction of the Volume Visual Perception ExM-SVM

Computer-vision-based separation methods for coal gangue face challenges due to the harsh environmental conditions in the mines, leading to the reduction of separation accuracy. So, rather than purely depending on the image features to distinguish the coal gangue, it is meaningful to utilize fixed coal characteristics like density. This study achieves the classification of coal and gangue based on their mass, volume, and weight. A dataset of volume, weight and 3_side images is collected. By using 3_side images of coal gangue, the visual perception value of the volume is extracted (ExM) to represent the volume of the object. A Support Vector Machine (SVM) classifier receives (ExM) and the weight to perform the coal gangue classification. The proposed system eliminates computer vision problems like light intensity, dust, and heterogeneous coal sources. The proposed model was tested with a collected dataset and achieved high recognition accuracy (KNN 100%, Linear SVM 100%, RBF SVM 100%, Gaussian Process 100%, Decision Tree 98%, Random Forest 100%, MLP 100%, AdaBosst 100%, Naive Bayes 98%, and QDA 99%). A cross-validation test has been done to verify the generalization ability. The results also demonstrate high classification accuracy (KNN 96%, Linear SVM 100%, RBF SVM 96%, Gaussian Process 96%, Decision Tree 99%, Random Forest 99%, MLP 100%, AdaBosst 99%, Naive Bayes 99%, and QDA 99%). The results show the high ability of the proposed technique ExM-SVM in coal gangue classification tasks.