Single View Research Articles

The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network

Objective: Scaphoid fractures, particularly occult and non-displaced fractures, are difficult to detect using traditional X-ray methods because of their subtle appearance and variability in bone density. This study proposes a two-stage CNN approach to detect and classify scaphoid fractures using anterior–posterior (AP) and lateral (LA) X-ray views for more accurate diagnosis. Methods: This study emphasizes the use of multi-view X-ray images (AP and LA views) to improve fracture detection and classification. The multi-view fusion module helps integrate information from both views to enhance detection accuracy, particularly for occult fractures that may not be visible in a single view. The proposed method includes two stages, which are stage 1: detect the scaphoid bone using Faster RCNN and a Feature Pyramid Network (FPN) for region proposal and small object detection. The detection accuracy for scaphoid localization is 100%, with Intersection over Union (IoU) scores of 0.8662 for AP views and 0.8478 for LA views. And stage 2: perform fracture classification using a ResNet backbone and FPN combined with a multi-view fusion module to combine features from both AP and LA views. This stage achieves a classification accuracy of 89.94%, recall of 87.33%, and precision of 90.36%. Results: The proposed model performs well in both scaphoid bone detection and fracture classification. The multi-view fusion approach significantly improves recall and accuracy in detecting fractures compared to single-view approaches. In scaphoid detection, both AP and LA views achieved 100% detection accuracy. In fracture detection, using multi-view fusion, the accuracy for AP views reached 87.16%, and for LA views, it reached 83.83%. Conclusions: The multi-view fusion model effectively improves the detection of scaphoid fractures, particularly in cases of occult and non-displaced fractures. The model provides a reliable, automated approach to assist clinicians in detecting and diagnosing scaphoid fractures more efficiently.

Russian science of public relations: stages of formation, specifics, development formats

INTRODUCTION. Any social institution presupposes scientific reflection of its activities. The purpose of the study is to trace the history of the formation of Russian scientific knowledge about public relations (PRology) as a component of a social institution, to characterize various approaches to scientific reflection of PR activities; to identify its national specifics and to determine possible foresights.MATERIALS AND METHODS. General scientific methods of deduction and induction, synthesis and analysis were used. The rather small domestic literature on the theory and history of PR knowledge was studied and analyzed.RESULTS AND DISCUSSION. It is analyzed various points of view on the science of public relations – classifying, problematic and historical. The analysis of the development of the Russian theory of public relations is given and the main characteristics of the stages of formation of Russian knowledge about PR are revealed, which generally correspond to the periodization of public relations in Russia. In the last five years, monographs and dissertations on the theory of PR have not appeared, but a significant number of works on media communications indicate the vulgarization of scientific knowledge about public relations due to the lack of a single scientific view on the nature and specificity of media communications. The tasks of the current stage of development of scientific knowledge about PR are outlined: reflection of the state of the PR industry; creation and legitimization of a single professional glossary; registration and generalization of regional experience in the field of communications; comprehension of the experience of European public relations.CONCLUSION. Among the foresight directions, the following are named: characteristics of the “model” mechanism of scientific description of modern PR-activity on the example of the communication model of G. Lasswell, operationalization in the scientific continuum of the concepts of “communication product”, “communication technology”. The area of application of the research results may be issues of the history of communication disciplines. In the prospects of scientific research, problems of interdisciplinary interaction of communication disciplines and the advancement of foresight topics of scientific research, reflecting the reflection of practical activities in the field of integrated communications, may be identified.

LA reservoir strain predicts elevated left atrial pressure in patients with Veno-Arterial (VA) extracorporeal membrane oxygenator (ECMO) support for cardiogenic shock

Abstract Background Veno-arterial (VA) extracorporeal membrane oxygenator (ECMO) is not a left ventricular (LV) support system as it increases aortic pressure and LV afterload due to retrograde blood flow in the aorta. This can lead to complications such as increased LV volume (LV distention), increased LV and left atrial (LA) pressures, and pulmonary edema. We sought to investigate the correlation between LA strain and invasive LA pressure (LAP) in patients with ECMO support for cardiogenic shock undergoing atrial septostomy with stenting. Methods and Results A total of 24 consecutive patients (52±20 years; 83% were male) undergoing atrial septostomy with stenting while being on ECMO support for cardiogenic shock for left heart decompression were analyzed. LAP was measured immediately after transeptal puncture and before deployment of interatrial septal stent. A comprehensive echocardiogram was performed in all patients prior to atrial septostomy. Median time difference between echocardiogram and LAP measurement was 3.5 (0.5-20) hours. LA strain analysis was performed using the TomTec Arena 2D-cardiac performance analysis (CPA) software. LA reservoir strain was measured at peak systole during the reservoir phase in a single apical 4-chamber view. Intraclass correlation coefficients between 2 different investigators were excellent (All> 0.95). Median LA reservoir strain and LAP were 3.2 (0.5-1) % and 23 (8-53) mmHg, respectively. LA reservoir strain significantly correlated with LAP (r=0.53, p=0.034). LA reservoir strain of < 1.5% can effectively predict markedly elevated LAP (LA> 30 mmHg) (OR =9.9, p =0.0016). Conclusions LA reservoir strain significantly correlated with invasive LAP. With the advent of strain imaging software, LA reservoir strain is a feasible, reproducible, noninvasive, and straightforward method to predict the need for left heart decompression and/or to guide optimal afterload management in patients with VA-ECMO for cardiogenic shock. Further a prospective simultaneous echocardiographic and invasive LAP study is needed.

MMLmiRLocNet: miRNA Subcellular Localization Prediction based on Multi-view Multi-label Learning for Drug Design.

Identifying subcellular localization of microRNAs (miRNAs) is essential for comprehensive understanding of cellular function and has significant implications for drug design. In the past, several computational methods for miRNA subcellular localization is being used for uncovering multiple facets of RNA function to facilitate the biological applications. Unfortunately, most existing classification methods rely on a single sequencebased view, making the effective fusion of data from multiple heterogeneous networks a primary challenge. Inspired by multi-view multi-label learning strategy, we propose a computational method, named MMLmiRLocNet, for predicting the subcellular localizations of miRNAs. The MMLmiRLocNet predictor extracts multi-perspective sequence representations by analyzing lexical, syntactic, and semantic aspects of biological sequences. Specifically, it integrates lexical attributes derived from k-mer physicochemical profiles, syntactic characteristics obtained via word2vec embeddings, and semantic representations generated by pre-trained feature embeddings. Finally, module for extracting multi-view consensus-level features and specific-level features was constructed to capture consensus and specific features from various perspectives. The full connection networks are utilized as the output module to predict the miRNA subcellular localization. Experimental results suggest that MMLmiRLocNet outperforms existing methods in terms of F1, subACC, and Accuracy, and achieves best performance with the help of multi-view consensus features and specific features extract network.

ANN uncertainty estimates in assessing fatty liver content from ultrasound data

Background and objectiveThis article uses three different probabilistic convolutional architectures applied to ultrasound image analysis for grading Fatty Liver Content (FLC) in Metabolic Dysfunction Associated Steatotic Liver Disease (MASLD) patients. Steatosis is a new silent epidemic and its accurate measurement is an impelling clinical need, not only for hepatologists, but also for experts in metabolic and cardiovascular diseases. This paper aims to provide a robust comparison between different uncertainty quantification strategies to identify advantages and drawbacks in a real clinical setting. MethodsWe used a classical Convolutional Neural Network, a Monte Carlo Dropout, and a Bayesian Convolutional Neural Network with the goal of not only comparing the goodness of the predictions, but also to have access to an evaluation of the uncertainty associated with the outputs. ResultsWe found that even if the prediction based on a single ultrasound view is reliable (relative RMSE [5.93%-12.04%]), networks based on two ultrasound views outperform them (relative RMSE [5.35%-5.87%]). In addition, the results show that the introduction of a “not confident” category contributes to increase the percentage of correctly predicted cases and to decrease the percentage of mispredicted cases, especially for semi-intrusive methods. ConclusionsThe possibility of having access to information about the confidence with which the network produces its outputs is a great advantage, both from the point of view of physicians who want to use neural networks as computer-aided diagnosis, and for developers who want to limit overfitting and obtain information about dataset problems in terms of out-of-distribution detection.

Hypertension and Left Ventricular Strain in Pediatric Chronic Kidney Disease.

Left ventricular global longitudinal strain (LV GLS) on echocardiography is a sensitive yet clinically significant marker of myocardial dysfunction. Reduced LV GLS is prevalent in adults with chronic kidney disease and hypertension and is associated with adverse cardiovascular outcomes. It may be a biomarker of chronic kidney disease-associated myocardial dysfunction in children, but data are limited. Our objective was to describe LV GLS in the CKiD study (Chronic Kidney Disease in Children) and to examine the association between blood pressure (BP) and reduced LV GLS. A single apical 4-chamber view was used to estimate LV GLS. Our main analyses examined the association of clinic BP with the absolute value of LV GLS and LV GLS dichotomized at 16. Sensitivity analyses using 24-hour ambulatory BP monitoring data were also performed. Generalized estimating equations were used to account for within-person correlation and to estimate robust SEs for 95% CIs. Covariates in adjusted models included: age, sex, race, estimated glomerular filtration rate, urine protein, hemoglobin, left ventricular hypertrophy, and the use of renin-angiotensin system inhibitors. LV GLS was measured in 962 person-visits. A total of 77 assessments had an LV GLS <16. In adjusted models, both clinic systolic BP (odds ratio, 1.02 [95% CI, 1.01-1.03]) and diastolic BP (odds ratio, 1.02 [95% CI, 1.00-1.03]) percentiles were associated with LV GLS <16. Having awake or nighttime diastolic BP hypertension on ambulatory BP monitoring was significantly associated with a lower absolute value of LV GLS. Office systolic and diastolic hypertension was associated with diminished LV GLS. Only diastolic hypertension detected on ambulatory BP monitoring was associated with lower LV GLS.

NEARER SCAN (LENO BESIK) evaluation of a task-sharing echocardiographic active case finding programme for rheumatic heart disease in Australia and Timor-Leste: protocol for a hybrid type II effectiveness-implementation study

IntroductionRheumatic heart disease (RHD) is underdiagnosed globally resulting in missed treatment opportunities and adverse clinical outcomes. We describe the protocol for a study which aims to co-design, implement and conduct...

TCT-599 The Prognostic Role of a Novel Computational Approach Assessing Microcirculatory Resistance Based on a Single Angiographic View in Patients Undergoing Transcatheter Aortic Valve Replacement

TCT-599 The Prognostic Role of a Novel Computational Approach Assessing Microcirculatory Resistance Based on a Single Angiographic View in Patients Undergoing Transcatheter Aortic Valve Replacement

Diagnostic accuracy of hemodynamic assessment of intracranial atherosclerotic stenosis from a single angiographic view: a validation study

BackgroundThe aim of this study is to assess the feasibility of identifying the hemodynamic status of intracranial atherosclerotic stenosis (ICAS) using angio-based fractional flow (FF) calculated from a single angiographic...

ICDDPM: Image-conditioned denoising diffusion probabilistic model for real-world complex point cloud single view reconstruction

Point cloud single-view reconstruction (PC-SVR) generates high-quality point clouds from low-cost 2D images, offering a cost-effective solution to the expensive and inefficient acquisition of point cloud for real-world scene typically achieved through expensive LiDAR systems. However, current models that generate point clouds from real-world 2D images (e.g. maritime vessels) still have shortcomings in terms of quality and model generalization. In this paper, we proposed a image-conditioned denoising diffusion probabilistic model (ICDDPM) for real-world complex point cloud single view reconstruction to address these issues. We re-designed the structure of classic diffusion model, use latent shape vectors to seamlessly integrate 2D image encoder, point cloud encoder, and conditional diffusion model, to cater PC-SVR task. By guiding the diffusion process with the 2D images, which serve as crucial conditional information, ICDDPM achieves end-to-end point cloud generation with superior quality. 2D images are also employed as input in the reverse diffusion process to further achieve point cloud generation. We conducted qualitative and quantitative experiments on synthetic dataset ShapeNet and real-world dataset PASCAL3D+ (focused on experiments of vessel point cloud data specifically). The results indicate that the ICDDPM model demonstrates superior performance compared to state-of-the-art models. It is capable of generating point clouds with a greater level of global and local details from various 2D image data. Additionally, the model exhibits strong generalization abilities and requires fewer computational resources.

Right ventricular dyssynchrony predicts outcome in pulmonary arterial hypertension when assessed in multiple CMR views

BackgroundRight ventricular (RV) dyssynchrony or post systolic contraction (PSC) cause inefficient pumping and have not been investigated as prognostic markers in pulmonary arterial hypertension (PAH). ObjectivesTo investigate if RV dyssynchrony and PSC are prognostic markers of transplantation-free survival in PAH and if multiple RV views improve the prognostication. MethodsPatients with PAH undergoing cardiac magnetic resonance (CMR) between 2003-2021 were included. For strain analysis, endocardial end-diastolic RV contours were delineated in RV 3-chamber (RV3ch), 4-chamber (4ch) and midventricular short axis slice (SAX). RV dyssynchrony was defined as standard deviation of time to peak strain in the walls from one (4ch), two (4ch and SAX) or three views (4ch, SAX and RV3ch). PSC was defined as peak strain occurring after pulmonary valve closure. Outcome was defined as death or lung transplantation. ResultsOne hundred-one patients (58±19 years, 66% women) were included. Median follow-up was 37 [51] months. There were 60 events (55 deaths and 5 lung transplantations). Outcome was associated with RV dyssynchrony from three views and with RV strain in 4ch. An increase of RV dyssynchrony - from 3 views - by 1% was associated with a 10% increased risk of lung transplantation or death. There was no association between outcome and RV dyssynchrony in one or two views nor with PSC. ConclusionRight ventricular dyssynchrony from three views were associated with outcome in PAH, whereas assessing dyssynchrony from one or two views and PSC were not. This implies that assessment of multiple instead of single RV views potentially could be used for prognostication in PAH.

LiDAR‐based place recognition for mobile robots in ground/water surface multiple scenes

AbstractLiDAR‐based 3D place recognition is an essential component of simultaneous localization and mapping systems in multi‐scene robotic applications. However, extracting discriminative and generalizable global descriptors of point clouds is still an open issue due to the insufficient use of the information contained in the LiDAR scans in existing approaches. In this paper, we propose a novel spatial‐temporal point cloud encoding network for multiple scenes, dubbed STM‐Net, to fully fuse the multi‐view spatial information and temporal information of LiDAR point clouds. Specifically, we first develop a spatial feature encoding module consisting of the single‐view transformer and multi‐view transformer. The module learns the correlation both within a single view and between two views by utilizing the multi‐layer range images generated by spherical projection and multi‐layer bird's eye view images generated by top‐down projection. Then in the temporal feature encoding module, we exploit the temporal transformer to mine the temporal information in the sequential point clouds, and a NetVLAD layer is applied to aggregate features and generate sub‐descriptors. Furthermore, we use a GeM pooling layer to fuse more information along the time dimension for the final global descriptors. Extensive experiments conducted on unmanned ground/surface vehicles with different LiDAR configurations indicate that our method (1) achieves superior place recognition performance than state‐of‐the‐art algorithms, (2) generalizes well to diverse sceneries, (3) is robust to viewpoint changes, (4) can operate in real‐time, demonstrating the effectiveness and satisfactory capability of the proposed approach and highlighting its promising applications in multi‐scene place recognition tasks.

Advanced visualization of aortic dissection anatomy and hemodynamics

Aortic dissection is a life-threatening cardiovascular disease constituted by the delamination of the aortic wall. Due to the weakened structure of the false lumen, the aorta often dilates over time, which can – after certain diameter thresholds are reached – increase the risk of fatal aortic rupture. The identification of patients with a high risk of late adverse events is an ongoing clinical challenge, further complicated by the complex dissection anatomy and the wide variety among patients. Moreover, patient-specific risk stratification depends not only on morphological, but also on hemodynamic factors, which can be derived from computer simulations or 4D flow magnetic resonance imaging (MRI). However, comprehensible visualizations that depict the complex anatomical and functional information in a single view are yet to be developed. These visualization tools will assist clinical research and decision-making by facilitating a comprehensive understanding of the aortic state. For that purpose, we identified several visualization tasks and requirements in close collaboration with cardiovascular imaging scientists and radiologists. We displayed true and false lumen hemodynamics using pathlines as well as surface hemodynamics on the dissection flap and the inner vessel wall. Pathlines indicate antegrade and retrograde flow, blood flow through fenestrations, and branch vessel supply. Dissection-specific hemodynamic measures, such as interluminal pressure difference and flap compliance, provide further insight of the blood flow throughout the cardiac cycle. Finally, we evaluated our visualization techniques with cardiothoracic and vascular surgeons in two separate virtual sessions.

A Survey of 3D Human Body Reconstruction from Single and Multiple Camera Views

A Survey of 3D Human Body Reconstruction from Single and Multiple Camera Views

Three-view cotton flower counting through multi-object tracking and RGB-D imagery

Monitoring the number of cotton flowers can provide important information for breeders to assess the flowering time and the productivity of genotypes because flowering marks the transition from vegetative growth to reproductive growth and impacts the final yield. Traditional manual counting methods are time-consuming and impractical for large-scale fields. To count cotton flowers efficiently and accurately, a multi-view multi-object tracking approach was proposed by using both RGB and depth images collected by three RGB-D cameras fixed on a ground robotic platform. The tracking-by-detection algorithm was employed to track flowers from three views simultaneously and remove duplicated counting from single views. Specifically, an object detection model (YOLOv8) was trained to detect flowers in RGB images and a deep learning-based optical flow model Recurrent All-pairs Field Transforms (RAFT) was used to estimate motion between two adjacent frames. The intersection over union and distance costs were employed to associate flowers in the tracking algorithm. Additionally, tracked flowers were segmented in RGB images and the depth of each flower was obtained from the corresponding depth image. Those flowers tracked with known depth from two side views were then projected onto the middle image coordinate using camera calibration parameters. Finally, a constrained hierarchy clustering algorithm clustered all flowers in the middle image coordinate to remove duplicated counting from three views. The results showed that the mean average precision of trained YOLOv8x was 96.4%. The counting results of the developed method were highly correlated with those counted manually with a coefficient of determination of 0.92. Besides, the mean absolute percentage error of all 25 testing videos was 6.22%. The predicted cumulative flower number of Pima cotton flowers is higher than that of Acala Maxxa, which is consistent with what breeders have observed. Furthermore, the developed method can also obtain the flower number distributions of different genotypes without laborious manual counting in the field. Overall, the three-view approach provides an efficient and effective approach to count cotton flowers from multiple views. By collecting the video data continuously, this method is beneficial for breeders to dissect genetic mechanisms of flowering time with unprecedented spatial and temporal resolution, also providing a means to discern genetic differences in fecundity, the number of flowers that result in harvestable bolls. The code and datasets used in this paper can be accessed on GitHub: https://github.com/UGA-BSAIL/Multi-view_flower_counting.

TSKPD: twin structure key point detection in point cloud

The point cloud keypoint detection algorithm like USIP that uses downsampling first and then fine-tuning the sampling points cannot effectively detect the defect part of the single view defect point cloud, resulting in the inability to output the keypoints of the defect part. Therefore, this paper proposes the twin structure key point detection algorithm named TSKPD based on the idea of contrastive learning, which uses two single-view defect point clouds to synthesize relatively more complete key points for learning, so as to promote the network model to learn the features of the complete point cloud. The robustness of key point detection of point cloud is effectively improved, and the detection of single view defect point cloud is realized. The test results on ModelNet40 and ShapeNet datasets show that the coverage rate of TSKPD on the missing part of the single view defect point cloud is 12.62 higher than the existing optimal algorithm.

Acetabular posterior column screws via an anterior approach.

Screw fixation of acetabular column fractures is a well-established alternative option to plate fixation providing comparable biomechanical strength and requiring less surgical exposure. For displaced acetabular fractures involving both columns open reduction and plate fixation of one column in combination with a column-crossing screw fixation of the opposite column via a single approach is a viable treatment option. Preoperative planning of posterior column screws (PCS) via an anterior approach is mandatory to assess the eligibility of the fracture for this technique and to plan the entry point and the screw trajectory. The intraoperative application requires fluoroscopic guidance using several views. A single view showing an extraarticular screw position is adequate to rule out hip joint penetration. The fluoroscopic assessment of cortical perforation of the posterior column requires several oblique views such as lateral oblique views, obturator oblique views and axial views of the posterior column or alternatively intraoperative CT scans. The application of PCS via an anterior approach is a technically demanding procedure, that allows for a relevant reduction of approach-related morbidity, surgical time and blood loss by using a single approach.

Prognostic value of angiographic based quantitative flow ratio and anatomic features in intracranial atherosclerotic stenosis

BackgroundPatients with intracranial atherosclerotic stenosis (ICAS) are prone to stroke recurrence despite aggressive medical treatment. Further assessment of the anatomy and physiology of ICAS is urgently needed to facilitate individualized...

Semi-Supervised Learning for Multi-View Data Classification and Visualization

Data visualization has several advantages, such as representing vast amounts of data and visually demonstrating patterns within it. Manifold learning methods help us estimate lower-dimensional representations of data, thereby enabling more effective visualizations. In data analysis, relying on a single view can often lead to misleading conclusions due to its limited perspective. Hence, leveraging multiple views simultaneously and interactively can mitigate this risk and enhance performance by exploiting diverse information sources. Additionally, incorporating different views concurrently during the graph construction process using interactive visualization approach has improved overall performance. In this paper, we introduce a novel algorithm for joint consistent graph construction and label estimation. Our method simultaneously constructs a unified graph and predicts the labels of unlabeled samples. Furthermore, the proposed approach estimates a projection matrix that enables the prediction of labels for unseen samples. Moreover, it incorporates the information in the label space to further enhance the accuracy. In addition, it merges the information in different views along with the labels to construct a consensus graph. Experimental results conducted on various image databases demonstrate the superiority of our fusion approach compared to using a single view or other fusion algorithms. This highlights the effectiveness of leveraging multiple views and simultaneously constructing a unified graph for improved performance in data classification and visualization tasks in semi-supervised contexts.

THE SPIRITUAL CONNECTION BETWEEN THE CARTOGRAPHY OF THE HUMAN SUBCONSCIOUS AND THE STRUCTURES OF NEOLIBERAL THEOLOGY

Usually, an economist, a manager, a business administrator, or any other participating member of the free market has a single and clear view of the pecuniary value of goods and the nature of capital. The logic of capitalism allows the economic agent to assign clear values to goods based on several factors. Although such a strict view of a good and its nature is mechanically correct, it is an incomplete one. Economists and economic theorists more broadly agree that commercial goods, whether they are directed to the consumer or intermediate goods in the production chain, are the result of human labour.