Partial Occlusion Research Articles

Adaptive Granularity-Fused Keypoint Detection for 6D Pose Estimation of Space Targets

Estimating the 6D pose of a space target is an intricate task due to factors such as occlusions, changes in visual appearance, and background clutter. Accurate pose determination requires robust algorithms capable of handling these complexities while maintaining reliability under various environmental conditions. Conventional pose estimation for space targets unfolds in two stages: establishing 2D–3D correspondences using keypoint detection networks and 3D models, followed by pose estimation via the perspective-n-point algorithm. The accuracy of this process hinges critically on the initial keypoint detection, which is currently limited by predominantly singular-scale detection techniques and fails to exploit sufficient information. To tackle the aforementioned challenges, we propose an adaptive dual-stream aggregation network (ADSAN), which enables the learning of finer local representations and the acquisition of abundant spatial and semantic information by merging features from both inter-layer and intra-layer perspectives through a multi-grained approach, consolidating features within individual layers and amplifying the interaction of distinct resolution features between layers. Furthermore, our ADSAN implements the selective keypoint focus module (SKFM) algorithm to alleviate problems caused by partial occlusions and viewpoint alterations. This mechanism places greater emphasis on the most challenging keypoints, ensuring the network prioritizes and optimizes its learning around these critical points. Benefiting from the finer and more robust information of space objects extracted by the ADSAN and SKFM, our method surpasses the SOTA method PoET (5.8°, 8.1°/0.0351%, 0.0744%) by 0.5°, 0.9°, and 0.0084%, 0.0354%, achieving 5.3°, 7.2° in rotation angle errors and 0.0267%, 0.0390% in normalized translation errors on the Speed and SwissCube datasets, respectively.

Diagnosing heart failure with preserved ejection fraction in patients with unexplained dyspnoea using left ventricular pressure-volume loops at rest and on exertion

Abstract Background To date, diagnosing heart failure with preserved ejection fraction (HFpEF) remains challenging, especially in euvolaemic patients presenting with unexplained dyspnoea on exertion and reduced exercise capacity. A stepwise approach was introduced with the HFA-PEFF diagnostic algorithm*, in which a relevant number of patients has to undergo invasive workup for a final judgement. Purpose The present study aimed to examine a population of patients with unexplained dyspnoea on exertion, using the diagnostic methods endorsed by the HFA-PEFF algorithm as well as left ventricular (LV) pressure-volume loops at rest, on exertion, and during caval occlusion, in order to identify and describe different phenotypes of HFpEF. Methods We prospectively included patients with unexplained dyspnoea on exertion, a left ventricular ejection fraction (LVEF) of ≥ 50%, and without an obvious cause of the dyspnoea. All patients underwent a comprehensive invasive haemodynamic workup. After invasive rule-out of a haemodynamically relevant coronary artery stenosis, we performed a right heart catheterization at rest (R) and on exertion (E) with an arm ergometer. Real-time continuous pressure-volume loops were obtained using a 7-French conductance catheter at rest, on exertion, and under temporal preload reduction via partial occlusion of the vena cava inferior. Results Thirty patients were included. Two patients had to be excluded from further analysis (one due to a technical failure of the conductance catheter and one with severe hypertension (systolic blood pressure > 200 mmHg) during the assessment). The 28 patients in this analysis had a mean age of 64.4±9.7 years and 57% were female. Eleven patients fulfilled invasively easily obtainable diagnostic criteria of HFpEF (mean pulmonary capillary wedge pressure (mPCWP) at rest ≥ 15 mmHg, exertional mPCWP ≥ 25 mmHg, LV end-diastolic pressure (LVEDP) at rest ≥ 16 mmHg, or exertional LVEDP ≥ 25 mmHg) according to the current guideline*. An additional 15 patients had a normal mPCWP and LVEDP, but fulfilled diagnostic criteria for HFpEF measured by the conductance catheter (time constant of LV relaxation tau > 48 ms and/ or chamber stiffness b > 0.27). We referred to this group as "early HFpEF". Patients with early HFpEF had a significantly higher systolic blood pressure, a worse LV relaxation time, and were more likely to exhibit chronotropic insufficiency compared to the HFpEF group (Table 1). HFpEF patients were characterised by significantly higher natriuretic peptides, LVEDP on exertion, and LV stiffness compared to patients with early HFpEF (pressure-volume loops are depicted in Figure 1). Conclusion Invasive haemodynamic testing for HFpEF in patients with unexplained dyspnoea on exertion via right heart catheterization without obtaining LV pressure-volume loops had a false negative rate of 58%. Better detection, the prognosis, and treatment of this "early HFpEF" population warrants further research.Table 1Figure 1

YOLOv8n-CSD: A Lightweight Detection Method for Nectarines in Complex Environments

At present, the picking of nectarines mainly relies on manual completion in China, and the process involves high labor intensity during picking and low picking efficiency. Therefore, it is necessary to introduce automated picking. To improve the accuracy of nectarine fruit recognition in complex environments and to increase the efficiency of automatic orchard-picking robots, a lightweight nectarine detection method, YOLOv8n-CSD, is proposed in this study. This model improves on YOLOv8n by first proposing a new structure, C2f-PC, to replace the C2f structure used in the original network, thus reducing the number of model parameters. Second, the SEAM is introduced to improve the model’s recognition of the occluded part. Finally, to realize real-time detection of nectarine fruits, the DySample Lightweight Dynamic Upsampling Module is introduced to save computational resources while effectively enhancing the model’s anti-interference ability. With a compact size of 4.7 MB, this model achieves 95.1% precision, 84.9% recall, and a mAP@0.5 of 93.2%—the model’s volume has been reduced while the evaluation metrics have all been improved over the baseline model. The study shows that the YOLOv8n-CSD model outperforms the current mainstream target detection models, and can recognize nectarines in different environments faster and more accurately, which lays the foundation for the field application of automatic picking technology.

Partial Occlusion, Less AKI: an AORTA Registry Analysis of pREBOA-PRO

Abstract Background Non-compressible torso hemorrhage remains a leading cause of potentially preventable deaths. Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) has emerged as an adjunct temporizing hemorrhage control. The complete occlusion strategy with the ER-REBOA catheter can cause distal ischemia when used for longer than 30 minutes. To specifically address this limitation, the pREBOA-PRO catheter was developed. The objective of the current study is to investigate the impact of longer, partial occlusion times provided by pREBOA-PRO on acute kidney injury and mortality. Methods This is a retrospective analysis of the Aortic Occlusion for Resuscitation in Trauma and Acute Care Surgery (AORTA) registry as of August 2023. Patients in the pREBOA-PRO group (n = 110) receiving partial occlusion in Zone 1 were contrasted to patients in the ER-REBOA group (n = 752) treated with complete occlusion in Zone 1. Between-group comparisons included demographics, clinical presentation, aortic occlusion (AO) strategy, clinical complications, and mortality. Results Demographics, clinical presentation, and mortality were indistinguishable between groups, except for age which was higher in the ER-REBOA group (44 vs. 38, p < 0.002). The partial AO strategy was employed more often in the pREBOA-PRO group (87% vs 33%, p < 0.05) and for longer periods (59 min vs. 50 min, p < 0.003). In contrast, AKI occurred less frequently in the pREBOA-PRO group (19% vs. 33%, p < 0.05). Conclusions The more frequently partial and longer occlusion times in Zone 1 with the use of pREBOA-PRO resulted in lower AKI incidence suggesting that this newer device is a safer extended bridge to hemorrhage control.

A mattress suture with pledgets can partially occlude intrahepatic shunts in 23 dogs: evaluation of long-term survival.

To explore the differences in outcomes between dogs with intrahepatic portosystemic shunts (IHPSSs) partially occluded with a mattress suture with pledgets or attenuated with cellophane banding. 74 dogs with IHPSSs were included in this retrospective study. Medical records between January 2000 and February 2020 were evaluated for information on dogs undergoing laparotomy with cellophane banding (group C) or mattress suture with pledgets (group P) for treatment of IHPSSs, including specific outcomes of survival time, persistence of clinical signs, and necessity of continued medical management. Primary veterinarians and owners were contacted for long-term follow-up. 51 dogs were entered in group C and 23 in group P. The duration of surgery was 154.6 minutes (136.3 to 170 minutes) for group C and 154.9 minutes (128.9 to 180.9 minutes) for group P. The short-term mortality rate was 2% for group C and 4% for group P. Dogs in group C had a median survival time of 3,537 days, while dogs in group P had a median survival time of 2,141 days. In the long term, dogs in group P received more medications than dogs in group C, but the distribution of the quality-of-life score was not different. Mattress suture with pledgets can be used as an alternative to cellophane banding. For dogs with IHPSSs where full surgical dissection for placement of cellophane band is not possible, partial occlusion of the shunt with a mattress suture with pledgets is a viable option with acceptable long-term outcomes.

Implied occlusion and subset underestimation contribute to the weak-outnumber-strong numerosity illusion.

Four experimental studies are reported using a total of 712 participants to investigate the basis of a recently reported numerosity illusion called "weak-outnumber-strong" (WOS). In the weak-outnumber-strong illusion, when equal numbers of white and gray dots (e.g., 50 of each) are intermixed against a darker gray background, the gray dots seem much more numerous than the white. Two principles seem to be supported by these new results: 1) Subsets of mixtures are generally underestimated; thus, in mixtures of red and green dots, both sets are underestimated (using a matching task) just as the white dots are in the weak-outnumber-strong illusion, but 2) the gray dots seem to be filled in as if partially occluded by the brighter white dots. This second principle is supported by manipulations of depth perception both by pictorial cues (partial occlusion) and by binocular cues (stereopsis), such that the illusion is abolished when the gray dots are depicted as closer than the white dots, but remains strong when they are depicted as lying behind the white dots. Finally, an online investigation of a prior false-floor hypothesis concerning the effect suggests that manipulations of relative contrast may affect the segmentation process, which produces the visual bias known as subset underestimation.

DEEP Q-NETWORK (DQN) PARTIALOCCLUSION SEGMENTATION AND BACKTRACKING SEARCH OPTIMIZATION ALGORITHM (BSOA) WITH OPTICAL FLOW RECONSTRUCTION FOR FACIAL EXPRESSION EMOTION RECOGNITION

Video facial expression recognition (FER) has garnered a lot of attention recently and is helpful for several applications. Although many algorithms demonstrate impressive performance in a controlled environment without occlusion, identification in the presence of partial facial occlusion remains a challenging issue. Solutions based on reconstructing the obscured area of the face have been suggested as a way to deal with occlusions. These options mostly rely on the face’s shape or texture. Nonetheless, the resemblance in facial expressions among individuals appears to be a valuable advantage for the reconstruction. For semantic segmentation based on occlusions, Reinforcement Learning (RL) is introduced as the initial stage. From a pool of unlabeled data, an agent learns a policy to choose a subset of tiny informative image patches to be tagged instead of full images. In the second stage, a trained Backtracking Search Algorithm (BSA) is used to rebuild optical flows that have been distorted by the occlusion. On obtaining optical flows estimated from occluded facial frames, AEs restore optical flows of occluded regions. These recovered optical flows become inputs to anticipate classes f expressions. Optical flux reconstructions then classify stages. This study evaluates classification model’s performances for face expression identification based on Very Deep Convolution Networks (VGGNet). Furthermore, it produces more accurate confusion matrices and proposes approaches for the KMU-FED and CK+ databases, respectively. The results are evaluated using metrics including recall, f-measure, accuracy, and precision.

Robust Face Recognition System Based on Deep Facial Feature Extraction and Machine Learning

Facial Recognition is a common challenge in research for security applications. Wide-ranging applications of this technology include biometrics, security data, access to controlled locations, smart cards, and surveillance systems. A practical approach to identifying individuals depends on factors such as partial face occlusion, illumination, age, expression, makeup, and poses. These complex face recognition variables affect most face recognition systems. In this paper, we propose a deep transfer learning for facial features based on the pose and illumination variations of celebrities’ faces in a free environment for face recognition. The new approach that combines deep learning methods for feature extraction with machine learning classification methods. Also, studies the performance of the pre-trained model (VGGFace2 with ResNet-50 model weights) for feature extraction with a Multilayer Perceptron Classifier (MLP), Decision Tree, and Bootstrap Aggregation (Bagging) to perform classification. The convolution neural network has lately achieved excellent advancement in facial recognition. The outcome indicated that VGGFace2 with MLP obtained more precision and provided the best results (Accuracy, F-measure, Recall, and Precision). The results for all metric for the proposed model is 99%. The benchmark for this model is a dataset of 105 people’s faces.

Long-term liver deportalisation in stable and time prolonged prehepatic portal hypertension model affects expression of hypoxia, angiogenesis, apoptosis, and autophagy markers in the young rats’ liver

prehepatic portal hypertension in children cause severe and life-threatening complications, that highlights the need in in-depth investigations of pathogenetic mechanisms, which contribute to prehepatic portal hypertension-associated liver pathology. In developed stable experimental prehepatic portal hypertension model in adolescent rat males we aimed to assess the expression levels of the key molecular markers of hypoxia, angiogenesis, autophagy, and apoptosis in the liver tissue after 6-month deportalization. Partial portal vein ligation was performed in 4-week old male rats. After 6-months tissue samples from PHP-model, sham operated and control animals were studied by western blot to identify protein levels of markers related to prehepatic portal hypertension -induced liver injury. Partial portal vein occlusion upregulated hypoxia inducible factor -1α (by 4.67 folds vs. control, p<0.001) and vascular endothelial growth factor protein expression levels (by 2.33 folds vs. control, p<0.001) suggesting chronic hypoxia development. Abnormally high levels of angiostatin isoforms were found (by 9.88 folds vs. control, p<0.001) to signify angiogenesis dysregulation. Significant caspase-3 (23.4-fold increase vs. control, p<0.001) overexpression is executive phase of apoptotic cell death evidence. Dramatic LC3 level expression indicates existence of crosstalk between autophagy and apoptosis that contribute to fibrotic changes. Hypoxia-induced events, impaired angiogenesis regulation, enhanced autophagy and apoptosis are contributing factors of prehepatic portal hypertension -induced liver injury. A better understanding of subtle molecular mechanisms of this pathology may pave the way for innovative treatment options.

Evaluation of Novel Biomarker of Early Atherosclerosis in Patients With Chronic Kidney Disease in Wasit Governorate

The aim of the study was to evaluate some Biomarkers in patients with athreoscelerosis in Wasit Province. Atherosclerosis is a chronic arterial disease and a major cause of vascular death. Fatty streaks in arterial walls gradually develop into atheroma and characteristic plaques. The acute rupture of these atheromatous plaques causes local thrombosis, leading to partial or total occlusion of the affected artery. The clinical consequences of these plaques depend on their site and the degree and speed of vessel occlusion . Its major clinical manifestations include ischemic heart disease (IHD), ischemic stroke, and peripheral arterial disease. The study took place in the a hemodialysis unit Al-Zahraa Teaching Hospital in Wasit Governorate during the period from November 2023 to April 2024. This study aimed to examine risk factors (age, gender, high blood pressure, smoking, left ventricular hypertrophy, diabetes mellitus, dyslipidemia, physical inactivity) for atherosclerosis in the general population and patients with chronic kidney disease. Also studying the effect of some novel biomarkers (Homocysteine, Fibrinogen, myeloperoxidase, lipoprotein-associated phospholipase A2, pentraxin 3). The study include (90) samples: (60) patients suffering from early atherosclerosis and chronic kidney disease (dialysis stage) and 30 samples of healthy people (control group), their ages ranged from (40 to 70 years). The samples were divided into two age groups, where the first group had an average age of 40-55 years and the second group was 56-70 years old , the categories were divided equally into males and females Samples were collected based on the incidence of kidney disease first, and then the main risk factors of early atherosclerosis were relied upon, which are (smoking, age, sex, dyslipidemia, hypertension, diabetes, left ventricle valve, physical inactivity). The results of our study regarding diagnostic markers of atherosclerosis showed a significant increase in biomarkers (MPO, PTX3, HCy, FG and LpPLA2)of infected people at p ≥ 0.5. In patients with atherosclerosis the level of new biomarkers showed a significant increase in serum of infected people compared to healthy people at p<0.5. This is an important indication of the importance of these biomarkers in detecting the disease.

A parametric approach for creating finite element models from point clouds for steel superstructure components in steel girder bridges

Finite element (FE) analysis is widely used to evaluate the conditions of existing bridges. However, the creation of high-fidelity FE models (FEM) for existing bridges is often a challenging task. In view of the ability of 3D laser scanning to capture detailed geometrical information, this study proposes a direct scan-to-FEM strategy specifically for steel bridge superstructure and hence to facilitate the creation of high-fidelity FE models for existing steel girder bridges. Parametric representations are proposed to address partial occlusions in the point clouds as well as to reinforce the connectivity and alignment between the superstructure elements. Mesh generation algorithms are developed to automatically convert the parametric representations into all-hexahedron FE mesh assembly that can be used directly for FE analysis without any mesh verification or editing. Experimental validations are carried out to evaluate the effectiveness of proposed method in term of both mesh quality and analysis accuracy.

Face Recognition in the Modern Era: A Survey of Techniques, Challenges, and Innovations

This review paper talks about the development of face recognition, ranging from traditional methods to the latest methods of deep learning (Hasan et al., 2021; Sáez-Trigueros et al., 2018). The early methods were based on separate characteristics like SIFT and LBP (Balaban, 2015) that could not handle complex scenarios. The use of statistical subspace methods helped to improve face representation. Deep learning, however, has transformed the domain, where systems like DeepFace attain nearly human-like performance by taking advantage of vast and various datasets (Taigman et al., 2014). Nonetheless, the bias, fairness, and privacy issues that remain unsolved have led to the ongoing research to make the face recognition systems more robust and ethically acceptable. Keywords--- Face recognition; Illuminations; partial occlusion; pose invariance

Bistable perception of symbolic numbers.

Numerals, that is, semantic expressions of numbers, enable us to have an exact representation of the amount of things. Visual processing of numerals plays an indispensable role in the recognition and interpretation of numbers. Here, we investigate how visual information from numerals is processed to achieve semantic understanding. We first found that partial occlusion of some digital numerals introduces bistable interpretations. Next, by using the visual adaptation method, we investigated the origin of this bistability in human participants. We showed that adaptation to digital and normal Arabic numerals, as well as homologous shapes, but not Chinese numerals, biases the interpretation of a partially occluded digital numeral. We suggest that this bistable interpretation is driven by intermediate shape processing stages of vision, that is, by features more complex than local visual orientations, but more basic than the abstract concepts of numerals.

Management of Myocardial Infarction and the Role of Cardiothoracic Surgery.

Myocardial infarction (MI) is a leading cause of mortality globally and is predominantly attributed to coronary artery disease (CAD). MI is categorized as ST-elevation MI (STEMI) or non-ST-elevation MI (NSTEMI), each with distinct etiologies and treatment pathways. The goal in treatment for both is restoring blood flow back to the myocardium. STEMI, characterized by complete occlusion of a coronary artery, is managed urgently with reperfusion therapy, typically percutaneous coronary intervention (PCI). In contrast, NSTEMI involves a partial occlusion of a coronary artery and is treated with medical management, PCI, or coronary artery bypass grafting (CABG) depending on risk scores and clinical judgment. The Heart Team approach can assist in deciding which reperfusion technique would provide the greatest benefit to the patient and is especially useful in complicated cases. Despite advances in treatment, complications such as cardiogenic shock (CS) and ischemic heart failure (HF) remain significant. While percutaneous coronary intervention (PCI) is considered the primary treatment for MI, it is important to recognize the significance of cardiac surgery in treatment, especially when there is complex disease or MI-related complications. This comprehensive review analyzes the role of cardiac surgery in MI management, recognizing when it is useful, or not.

Enhancing Detection of Pedestrians in Low-Light Conditions by Accentuating Gaussian–Sobel Edge Features from Depth Maps

Owing to the low detection accuracy of camera-based object detection models, various fusion techniques with Light Detection and Ranging (LiDAR) have been attempted. This has resulted in improved detection of objects that are difficult to detect due to partial occlusion by obstacles or unclear silhouettes. However, the detection performance remains limited in low-light environments where small pedestrians are located far from the sensor or pedestrians have difficult-to-estimate shapes. This study proposes an object detection model that employs a Gaussian–Sobel filter. This filter combines Gaussian blurring, which suppresses the effects of noise, and a Sobel mask, which accentuates object features, to effectively utilize depth maps generated by LiDAR for object detection. The model performs independent pedestrian detection using the real-time object detection model You Only Look Once v4, based on RGB images obtained using a camera and depth maps preprocessed by the Gaussian–Sobel filter, and estimates the optimal pedestrian location using non-maximum suppression. This enables accurate pedestrian detection while maintaining a high detection accuracy even in low-light or external-noise environments, where object features and contours are not well defined. The test evaluation results demonstrated that the proposed method achieved at least 1–7% higher average precision than the state-of-the-art models under various environments.

Dynamic Target Tracking and Following with UAVs Using Multi-Target Information: Leveraging YOLOv8 and MOT Algorithms

This work presents an autonomous vision-based mobile target tracking and following system designed for unmanned aerial vehicles (UAVs) leveraging multi-target information. It explores the research gap in applying the most recent multi-object tracking (MOT) methods in target following scenarios over traditional single-object tracking (SOT) algorithms. The system integrates the real-time object detection model, You Only Look Once (YOLO)v8, with the MOT algorithms BoT-SORT and ByteTrack, extracting multi-target information. It leverages this information to improve redetection capabilities, addressing target misidentifications (ID changes), and partial and full occlusions in dynamic environments. A depth sensing module is incorporated to enhance distance estimation when feasible. A 3D flight control system is proposed for target following, capable of reacting to changes in target speed and direction while maintaining line-of-sight. The system is initially tested in simulation and then deployed in real-world scenarios. Results show precise target tracking and following, resilient to partial and full occlusions in dynamic environments, effectively distinguishing the followed target from bystanders. A comparison between the BoT-SORT and ByteTrack trackers reveals a trade-off between computational efficiency and tracking precision. In overcoming the presented challenges, this work enables new practical applications in the field of vision-based target following from UAVs leveraging multi-target information.

Improved Detection of Multi-Class Bad Traffic Signs Using Ensemble and Test Time Augmentation Based on Yolov5 Models

Various factors such as natural disasters, vandalism, weather, and environmental conditions can affect the physical state of traffic signs. The proposed model aims to improve detection of traffic signs affected by partial occlusion as a result of overgrown vegetation, displaced signs (those knocked down, bent), perforated signs (those damaged with holes), faded signs (color degradation), rusted signs (corroded surface), and de-faced signs (placing graffiti, etc., by vandals). This research aims to improve the detection of bad traffic signs using three approaches. In the first approach, Spiral Pooling Pyramid-Fast (SPPF) and C3TR modules are introduced to the architecture of Yolov5 models. SPPF helps provide a multi-scale representation of the input feature map by pooling at different scales, which is useful in improving the quality of feature maps and detecting bad traffic signs of various sizes and perspectives. The C3TR module uses convolutional layers to enhance local feature extraction and transformers to boost understanding of the global context. Secondly, we use predictions of Yolov5 as base models to implement a mean ensemble to improve performance. Thirdly, test time augmentation (TTA) is applied at test time by using scaling and flipping to improve accuracy. Some signs are generated using stable diffusion techniques to augment certain classes. We test the proposed models on the CCTSDB2021, TT100K, GTSDB, and GTSRD datasets to ensure generalization and use k-fold cross-validation to further evaluate the performance of the models. The proposed models outperform other state-of-the-art models in comparison.

Abstract P449: A Murine Model of Mid-Thoracic Aortic Coarctation

Vascular pressure can directly affect cardiovascular structure and function. Understanding the mechanisms, however, is complicated because conditions or interventions that chronically raise blood pressure (e.g. excess angiotensin II) can also have direct effects on the vasculature that occur independent of changes in blood pressure. One approach to mitigating this problem is to obstruct flow in a vascular segment sufficiently to reduce blood pressure in the segment downstream of the obstruction, while pressure upstream either stays the same or increases. As a result, all factors other than pressure are expected to be the same in upstream and downstream vascular segments. We have found evidence that differences in intravascular pressure can also affect closely adjacent tissues, specifically perivascular adipose tissue (PVAT). To test this idea in vivo , we developed a method to produce chronic, partial occlusion (or coarctation) of the mid-thoracic aorta in mice. This exposes upstream aortic PVAT depots to significantly higher aortic pressure than downstream aortic PVAT depots. The key to the method is producing a stable occlusion with a diameter small enough to produce a pressure gradient but not so small that the downstream flow is inadequate to support tissue oxygenation. To this end, a thoracotomy was performed to expose the thoracic aorta in adult mice anesthetized with isoflurane and artificially ventilated. A coarctation of the mid-thoracic aorta was produced by tying a ligature around the aorta and a blunted needle on the aorta, then removing the needle. In other mice, a silicone rubber or nitrile O-ring of varying dimensions was placed around the aorta. Mice were allowed to recover for varying periods of time (weeks), then the degree of coarctation was evaluated using both imaging methods (ultrasound) and direct measurement of the pressure gradient (catheters placed in a carotid and a femoral artery) under isoflurane anesthesia. In a group of 9 male mice with coarctation and 4 male mice with sham coarctation, we found an average mean arterial pressure gradient of 11.7 ± 5.0 mmHg (mean ± SEM) in coarct mice and 1.6 ± 2.0 mmHg in sham mice. Systolic pressure gradients averaged 14.0 ± 5.9 mmHg in coarct mice and 1.0 ± 3.2 mmHg in sham mice. These results suggest it is possible to produce a stable pressure gradient across the thoracic aorta of mice as a tool to explore the impact of arterial pressure on vascular and PVAT structure and function.

P049 RENOVASCULAR HYPERTENSIVE RATS (2K1C) HAVE REDUCED INTRACRANIAL COMPLIANCE INDUCED BY RAISED VENTRICULAR VOLUME COMPARED TO NORMOTENSIVE RATS

Background and Objective: Intracerebroventricular (ICV) infusions of increased volumes of saline can be used to study intracranial compliance (ICC). Since the two-kidneys,1-clip (2K1C) rat model of renovascular hypertension has an enhanced baseline level of intracranial pressure (ICP), the present study aimed to verify the effect of ICV infusions of 0.15 M NaCl on ICP and ICC in 2K1C rats. Methods: Male Holtzman rats (180-210 g) were randomly separated to be normotensive (NT; sham surgery, n = 5) or with 2K1C (n = 5), done by a partial left renal artery occlusion. Six weeks after, rats were anaesthetized with urethane (1.2 g/kg body weight, i.v.), tracheostomized, placed under artificial ventilation, and had an ICP sensor and a needle inserted into the lateral ventricle for, respectively, ICP recording and ICV 0.15 M infusions (30, 60 and 90 μL, at 100 μL/min). There was a 20-minute interval between each infusion. ICC was calculated by the ratio of volume change to ICP change [ICC = ΔV (μL)/Δ ICP (mmHg)]. Results: Baseline MAP, ICP, and P2/P1 ratio of 2K1C rats (166 ± 6 mmHg; 15.7 ± 1.7 mmHg; 1.6 ± 0.1, respectively) were higher than the ones in NT rats (94 ± 5 mmHg; 10.1 ±1.4 mmHg; 0.7 ± 0.1 respectively; p<0.05 vs 2K-1C). ICV infusions induced increased ICP in 2K1C rats (19 ±0.5; 42 ±1.2 and 55 ±5.5 mmHg, vs NT: 8 ±0.6; 25 ±3.2 and 36 ± 4.9 mmHg, respectively at 30, 60 and 90 μL infusion; p<0.05). In addition, 2K1C rats presented a reduced ICC only at 30 μl infusion (5.6 ±1.4, vs NT: 11.4 ±0.9; p<0.05). Conclusions: These findings suggest that renovascular hypertension impairs ICC to the well-documented increase in ICP. Support: FAPESP, CNPq.

Simultaneous image patch attention and pruning for patch selective transformer

Vision transformer models provide superior performance compared to convolutional neural networks for various computer vision tasks but require increased computational overhead with large datasets. This paper proposes a patch selective vision transformer that effectively selects patches to reduce computational costs while simultaneously extracting global and local self-representative patch information to maintain performance. The inter-patch attention in the transformer encoder emphasizes meaningful features by capturing the inter-patch relationships of features, and dynamic patch pruning is applied to the attentive patches using a learnable soft threshold that measures the maximum multi-head importance scores. The proposed patch attention and pruning method provides constraints to exploit dominant feature maps in conjunction with self-attention, thus avoiding the propagation of noisy or irrelevant information. The proposed patch-selective transformer also helps to address computer vision problems such as scale, background clutter, and partial occlusion, resulting in a lightweight and general-purpose vision transformer suitable for mobile devices.