Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical world.

Thermal infrared detectors have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern. Recent works use bulb plate, "QR" suit, and infrared patches as physical perturbations to perform white-box attacks on thermal infrared detectors, which are effective but not practical for real-world scenarios. Some researchers have tried to utilize hot and cold blocks as physical perturbations for black-box attacks on thermal infrared detectors. However, this attempts has not yielded robust and multi-view physical attacks, indicating limitations in the approach. To overcome the limitations of existing approaches, we introduce a novel black-box physical attack method, called adversarial infrared blocks (AdvIB). By optimizing the physical parameters of the infrared blocks and deploying them to pedestrians from multiple views, including the front, side, and back, AdvIB can execute robust and multi-view attacks on thermal infrared detectors. Our physical tests show that the proposed method achieves a success rate of over 80% under most distance and view conditions, validating its effectiveness. For stealthiness, our method involves attaching the adversarial infrared block to the inside of clothing, enhancing its stealthiness. Additionally, we perform comprehensive experiments and compare the experimental results with baseline to verify the robustness of our method. In summary, AdvIB allows for potent multi-view black-box attacks, profoundly influencing ethical considerations in today's society. Potential consequences, including disasters from technology misuse and attackers' legal liability, highlight crucial ethical and security issues associated with AdvIB. Considering these concerns, we urge heightened attention to the proposed AdvIB. Our code can be accessed from the following link: https://github.com/ChengYinHu/AdvIB.git.

A systematic review of factors that impact reading comprehension in children with developmental language disorders.

Children with developmental language disorder (DLD) have a high rate of co-occurring reading difficulties. The current study aims to (i) examine which factors within the Active View of Reading (AVR; Duke & Cartwright, 2021) apply to individuals with DLD and (ii) investigate other possible factors that relate to reading comprehension ability in individuals with DLD, outside the components in the AVR. Electronic database search and journal hand-search yielded 5058 studies published before March 2022 related to reading comprehension in children with DLD. 4802 articles were excluded during abstract screening, yielding 256 studies eligible for full-text review. Following full-text review, 44 studies were included and further coded for demographics, language of assessment, description of reported disabilities, behavioral assessment, and reading comprehension assessment. While the results aligned with the AVR model, three additional factors were identified as significantly relating to reading comprehension abilities in children with DLD: expressive language (oral and written), question types of reading assessment, and language disorder history. Specifically, expressive language was positively associated with reading comprehension ability, while resolved DLD showed higher reading comprehension abilities than persistent DLD. Furthermore, children with DLD may face additional difficulties in comprehending inference-based questions. This study provides factors for researchers, educators, and clinical professionals to consider when evaluating the reading comprehension of individuals with DLD. Future research should further explore the relative importance of factors of the AVR to reading comprehension outcomes throughout development.

Dose Reduction in Pediatric Oncology Patients with Delayed Total-Body [18F]FDG PET/CT.

Our aim was to define a lower limit of reduced injected activity in delayed [18F]FDG total-body (TB) PET/CT in pediatric oncology patients. Methods: In this single-center prospective study, children were scanned for 20 min with TB PET/CT, 120 min after intravenous administration of a 4.07 ± 0.49 MBq/kg dose of [18F]FDG. Five randomly subsampled low-count reconstructions were generated using », ⅛, [Formula: see text], and [Formula: see text] of the counts in the full-dose list-mode reference standard acquisition (20 min), to simulate dose reduction. For the 2 lowest-count reconstructions, smoothing was applied. Background uptake was measured with volumes of interest placed on the ascending aorta, right liver lobe, and third lumbar vertebra body (L3). Tumor lesions were segmented using a 40% isocontour volume-of-interest approach. Signal-to-noise ratio, tumor-to-background ratio, and contrast-to-noise ratio were calculated. Three physicians identified malignant lesions independently and assessed the image quality using a 5-point Likert scale. Results: In total, 113 malignant lesions were identified in 18 patients, who met the inclusion criteria. Of these lesions, 87.6% were quantifiable. Liver SUVmean did not change significantly, whereas a lower signal-to-noise ratio was observed in all low-count reconstructions compared with the reference standard (P < 0.0001) because of higher noise rates. Tumor uptake (SUVmax), tumor-to-background ratio, and total lesion count were significantly lower in the reconstructions with [Formula: see text] and [Formula: see text] of the counts of the reference standard (P < 0.001). Contrast-to-noise ratio and clinical image quality were significantly lower in all low-count reconstructions than with the reference standard. Conclusion: Dose reduction for delayed [18F]FDG TB PET/CT imaging in children is possible without loss of image quality or lesion conspicuity. However, our results indicate that to maintain comparable tumor uptake and lesion conspicuity, PET centers should not reduce the injected [18F]FDG activity below 0.5 MBq/kg when using TB PET/CT in pediatric imaging at 120 min after injection.

Subtotal cholecystectomy with omental pedicle plug for the challenging gallbladder: A case report and review of the literature.

If patient anatomy or disease does not allow for a traditional or partial cholecystectomy, an omental pedicle plug may be a viable option to limit the risk of postoperative uncontrolled bile leak from the cystic duct and to control patient symptoms.

Multi-View Gait Analysis by Temporal Geometric Features of Human Body Parts.

A gait is a walking pattern that can help identify a person. Recently, gait analysis employed a vision-based pose estimation for further feature extraction. This research aims to identify a person by analyzing their walking pattern. Moreover, the authors intend to expand gait analysis for other tasks, e.g., the analysis of clinical, psychological, and emotional tasks. The vision-based human pose estimation method is used in this study to extract the joint angles and rank correlation between them. We deploy the multi-view gait databases for the experiment, i.e., CASIA-B and OUMVLP-Pose. The features are separated into three parts, i.e., whole, upper, and lower body features, to study the effect of the human body part features on an analysis of the gait. For person identity matching, a minimum Dynamic Time Warping (DTW) distance is determined. Additionally, we apply a majority voting algorithm to integrate the separated matching results from multiple cameras to enhance accuracy, and it improved up to approximately 30% compared to matching without majority voting.

Age-related differences on temporal source memory by using dynamic stimuli: the effects of POV and emotional valence.

Previous studies have highlighted that temporal source memory can be influenced by factors such as the individual's age and the emotional valence of the event to be remembered. In this study, we investigated how the different points of view (POVs) from which an event is presented could interact with the relationship between age-related differences and emotional valence on temporal source memory. One hundred and forty-one younger adults (aged 18-30) and 90 older adults (aged 65-74) were presented with a series of emotional videos shot from different POVs (first vs. third-person) in three sessions. In the fourth session, participants were asked to indicate in which session (1, 2, or 3) they viewed each video. The results indicated that the first-person POV amplified the effects of the emotional valence on temporal source memory. Only in this experimental condition, older adults "pushed away" negative stimuli by perceiving them as more distant in time, and "kept closer" positive stimuli by perceiving them as more recent. In comparison, younger adults "kept closer" positive stimuli. These findings add to the existing literature on the positivity effect on temporal source memory and highlighted the importance of considering the POV in relation to the emotional valence.

Measuring Greenspace in Rural Areas for Studies of Birth Outcomes: A Comparison of Street View Data and Satellite Data.

Using street view data, in replace of remotely sensed (RS) data, to study the health impact of greenspace has become popular. However, direct comparisons of these two methods of measuring greenspace are still limited, and their findings are inconsistent. On the other hand, almost all studies of greenspace focus on urban areas. The effectiveness of greenspace in rural areas remains to be investigated. In this study, we compared measures of greenspace based on the Google Street View data with those based on RS data by calculating the correlation between the two and evaluating their associations with birth outcomes. Besides the direct measures of greenness, we also compared the measures of environmental diversity, calculated with the two types of data. Our study area consists of the States of New Hampshire and Vermont, USA, which are largely rural. Our results show that the correlations between the two types of greenness measures were weak to moderate, and the greenness at an eye-level view largely reflects the immediate surroundings. Neither the street view data- nor the RS data-based measures identify the influence of greenspace on birth outcomes in our rural study area. Interestingly, the environmental diversity was largely negatively associated with birth outcomes, particularly gestational age. Our study revealed that in rural areas, the effectiveness of greenspace and environmental diversity may be considerably different from that in urban areas.

Inter-rater and Intra-rater Reliability of a Mobile App Method to Measure Lumbar Lordosis.

Background Measuring the exact quantitative values of lordotic curves is a vital factor in clinical settings to prevent musculoskeletal deformities in the future. Existing lordotic assessment methods are very diverse, expensive, inaccurate, and not handy, and their availability cannot be maintained in every clinic setup. Aim The purpose of this research was to study the reliability of a mobile app as a feasible method to measure lumbar lordosis angle using a lateral view radiograph. Methodology A lateral view low back region radiograph of 58 participants was taken based on the criteria, and the experienced physiotherapists uploaded the X-ray to the mobile app and measured the lordotic angles with the support of machine learning algorithms. Descriptive statistics were used to calculate the average and dispersion of the data of the lumbar lordosis angle measured using the mobile app method (Statistical Package for the Social Sciences (IBM SPSS Statistics for Windows, IBM Corp., Version 23, Armonk, NY)). Results Associations between and within raters were assessed using the Karl Pearson coefficient of correlation (1.000). Inter-rater and intra-rater reliability were determined by using Cronbach's alpha (.966) and the split-half method. The internal consistency of the mobile app was found to be good. Conclusions Based on our findings, we conclude that the mobile app method is reliable and useful in measuring lumbar lordosis objectively with less effort. Since the app is handy on smartphones, physiotherapists can conduct an objective lumbar lordosis assessment in clinical settings.

Does Self-View Mode Generate More Videoconferencing Fatigue in Women than Men? An Experiment Using EEG Signals.

The ability to see or hide one's own image is a typical feature of videoconferencing platforms. Previous research, informed primarily by self-reported data, has suggested that enabling self-view mode is associated with videoconferencing fatigue, particularly for women. Our goal in this study is to test this assumption by gathering neurophysiological evidence. We conducted an experiment using electroencephalography (EEG) with 32 volunteers (16 men and 16 women), who each participated in a live video meeting with the self-view mode both on and off. Our findings confirm the effects of self-view on fatigue, with significantly greater alpha activity when self-view was on than when it was off. Alpha activity did not change significantly across a 20-minute session, and was not significantly different for men or women. Thus, our study does not replicate previous findings that women experience greater videoconferencing fatigue because of the increased self-awareness generated when viewing themselves on a screen. We discuss why our EEG findings may diverge from prior self-reported studies.

Empathy bodyssence: temporal dynamics of sensorimotor and physiological responses and the subjective experience in synchrony with the other's suffering.

Background: Empathy is foundational in our intersubjective interactions, connecting with others across bodily, emotional, and cognitive dimensions. Previous evidence suggests that observing individuals in painful situations elicits whole bodily responses, unveiling the interdependence of the body and empathy. Although the role of the body has been extensively described, the temporal structure of bodily responses and its association with the comprehension of subjective experiences remain unclear. Objective: Building upon the enactive approach, our study introduces and examines "bodyssence," a neologism formed from "body" and "essence." Our primary goal is to analyze the temporal dynamics, physiological, and phenomenological elements in synchrony with the experiences of sportspersons suffering physical accidents. Methods: Using the empirical 5E approach, a refinement of Varela's neurophenomenological program, we integrated both objective third-person measurements (postural sway, electrodermal response, and heart rate) and first-person descriptions (phenomenological data). Thirty-five participants watched videos of sportspersons experiencing physical accidents during extreme sports practice, as well as neutral videos, while standing on a force platform and wearing electrodermal and heart electrodes. Subsequently, micro-phenomenological interviews were conducted. Results: Bodyssence is composed of three distinct temporal dynamics. Forefeel marks the commencement phase, encapsulating the body's pre-reflective consciousness as participants anticipate impending physical accidents involving extreme sportspersons, manifested through minimal postural movement and high heart rate. Fullfeel, capturing the zenith of empathetic engagement, is defined by profound negative emotions, and significant bodily and kinesthetic sensations, with this stage notably featuring an increase in postural movement alongside a reduction in heart rate. In the Reliefeel phase, participants report a decrease in emotional intensity, feeling a sense of relief, as their postural control starts to reach a state of equilibrium, and heart rate remaining low. Throughout these phases, the level of electrodermal activity consistently remains high. Conclusion: This study through an enactive approach elucidates the temporal attunement of bodily experience to the pain experienced by others. The integration of both first and third-person perspectives through an empirical 5E approach reveals the intricate nature of bodyssence, offering an innovative approach to understanding the dynamic nature of empathy.

Deep Few-view High-resolution Photon-counting Extremity CT at Halved Dose for a Clinical Trial.

The latest X-ray photon-counting computed tomography (PCCT) for extremity allows multi-energy high-resolution (HR) imaging for tissue characterization and material decomposition. However, both radiation dose and imaging speed need improvement for contrast-enhanced and other studies. Despite the success of deep learning methods for 2D few-view reconstruction, applying them to HR volumetric reconstruction of extremity scans for clinical diagnosis has been limited due to GPU memory constraints, training data scarcity, and domain gap issues. In this paper, we propose a deep learning-based approach for PCCT image reconstruction at halved dose and doubled speed in a New Zealand clinical trial. Particularly, we present a patch-based volumetric refinement network to alleviate the GPU memory limitation, train network with synthetic data, and use model-based iterative refinement to bridge the gap between synthetic and real-world data. The simulation and phantom experiments demonstrate consistently improved results under different acquisition conditions on both in- and off-domain structures using a fixed network. The image quality of 8 patients from the clinical trial are evaluated by three radiologists in comparison with the standard image reconstruction with a full-view dataset. It is shown that our proposed approach is essentially identical to or better than the clinical benchmark in terms of diagnostic image quality scores. Our approach has a great potential to improve the safety and efficiency of PCCT without compromising image quality.

MMR: A Multi-view Merge Representation model for Chemical-Disease relation extraction.

Chemical-Disease relation (CDR) extraction aims to identify the semantic relations between chemical and disease entities in the unstructured biomedical document, which provides a basis for downstream tasks such as clinical medical diagnosis and drug discovery. Compared with general domain relation extraction, it needs a more effective representation of the whole document due to the specialized nature of texts in the biomedical domain, including the biomedical entity and entity-pair representation. In this paper, we propose a novel Multi-view Merge Representation (MMR) model to thoroughly capture entity and entity-pair representation of the document. First, we utilize prior knowledge and a pre-trained transformer encoder to capture entity semantic representation. Then we employ the U-Net layer and Graph Convolution Network layer to capture global entity-pair representation. Finally, we get a specific merged representation for each entity pair to be classified. We evaluate our model on the CDR dataset published by the BioCreative-V community and achieve a state-of-the-art result.

Self-paced regularized adaptive multi-view unsupervised feature selection.

Multi-view unsupervised feature selection (MUFS) is an efficient approach for dimensional reduction of heterogeneous data. However, existing MUFS approaches mostly assign the samples the same weight, thus the diversity of samples is not utilized efficiently. Additionally, due to the presence of various regularizations, the resulting MUFS problems are often non-convex, making it difficult to find the optimal solutions. To address this issue, a novel MUFS method named Self-paced Regularized Adaptive Multi-view Unsupervised Feature Selection (SPAMUFS) is proposed. Specifically, the proposed approach firstly trains the MUFS model with simple samples, and gradually learns complex samples by using self-paced regularizer. l2,p-norm (0

Computer aided diagnosis of diabetic retinopathy based on multi-view joint learning.

Diabetic retinopathy (DR) is a kind of ocular complication of diabetes, and its degree grade is an essential basis for early diagnosis of patients. Manual diagnosis is a long and expensive process with a specific risk of misdiagnosis. Computer-aided diagnosis can provide more accurate and practical treatment recommendations. In this paper, we propose a multi-view joint learning DR diagnostic model called RT2Net, which integrates the global features of fundus images and the local detailed features of vascular images to reduce the limitations of single fundus image learning. Firstly, the original image is preprocessed using operations such as contrast-limited adaptive histogram equalization, and the vascular structure of the extracted DR image is segmented. Then, the vascular image and fundus image are input into two branch networks of RT2Net for feature extraction, respectively, and the feature fusion module adaptively fuses the feature vectors' output from the branch networks. Finally, the optimized classification model is used to identify the five categories of DR. This paper conducts extensive experiments on the public datasets EyePACS and APTOS 2019 to demonstrate the method's effectiveness. The accuracy of RT2Net on the two datasets reaches 88.2% and 85.4%, and the area under the receiver operating characteristic curve (AUC) is 0.98 and 0.96, respectively. The excellent classification ability of RT2Net for DR can significantly help patients detect and treat lesions early and provide doctors with a more reliable diagnosis basis, which has significant clinical value for diagnosing DR.

MUSCLE: multi-view and multi-scale attentional feature fusion for microRNA-disease associations prediction.

MicroRNAs (miRNAs) synergize with various biomolecules in human cells resulting in diverse functions in regulating a wide range of biological processes. Predicting potential disease-associated miRNAs as valuable biomarkers contributes to the treatment of human diseases. However, few previous methods take a holistic perspective and only concentrate on isolated miRNA and disease objects, thereby ignoring that human cells are responsible for multiple relationships. In this work, we first constructed a multi-view graph based on the relationships between miRNAs and various biomolecules, and then utilized graph attention neural network to learn the graph topology features of miRNAs and diseases for each view. Next, we added an attention mechanism again, and developed a multi-scale feature fusion module, aiming to determine the optimal fusion results for the multi-view topology features of miRNAs and diseases. In addition, the prior attribute knowledge of miRNAs and diseases was simultaneously added to achieve better prediction results and solve the cold start problem. Finally, the learned miRNA and disease representations were then concatenated and fed into a multi-layer perceptron for end-to-end training and predicting potential miRNA-disease associations. To assess the efficacy of our model (called MUSCLE), we performed 5- and 10-fold cross-validation (CV), which got average the Area under ROC curves of 0.966${\pm }$0.0102 and 0.973${\pm }$0.0135, respectively, outperforming most current state-of-the-art models. We then examined the impact of crucial parameters on prediction performance and performed ablation experiments on the feature combination and model architecture. Furthermore, the case studies about colon cancer, lung cancer and breast cancer also fully demonstrate the good inductive capability of MUSCLE. Our data and code are free available at a public GitHub repository: https://github.com/zht-code/MUSCLE.git.

AcquisitionFocus: Joint Optimization of Acquisition Orientation and Cardiac Volume Reconstruction Using Deep Learning.

In cardiac cine imaging, acquiring high-quality data is challenging and time-consuming due to the artifacts generated by the heart's continuous movement. Volumetric, fully isotropic data acquisition with high temporal resolution is, to date, intractable due to MR physics constraints. To assess whole-heart movement under minimal acquisition time, we propose a deep learning model that reconstructs the volumetric shape of multiple cardiac chambers from a limited number of input slices while simultaneously optimizing the slice acquisition orientation for this task. We mimic the current clinical protocols for cardiac imaging and compare the shape reconstruction quality of standard clinical views and optimized views. In our experiments, we show that the jointly trained model achieves accurate high-resolution multi-chamber shape reconstruction with errors of <13 mm HD95 and Dice scores of >80%, indicating its effectiveness in both simulated cardiac cine MRI and clinical cardiac MRI with a wide range of pathological shape variations.

An ensemble deep learning diagnostic system for determining Clinical Activity Scores in thyroid-associated ophthalmopathy: integrating multi-view multimodal images from anterior segment slit-lamp photographs and facial images.

Background: Thyroid-associated ophthalmopathy (TAO) is the most prevalent autoimmune orbital condition, significantly impacting patients' appearance and quality of life. Early and accurate identification of active TAO along with timely treatment can enhance prognosis and reduce the occurrence of severe cases. Although the Clinical Activity Score (CAS) serves as an effective assessment system for TAO, it is susceptible to assessor experience bias. This study aimed to develop an ensemble deep learning system that combines anterior segment slit-lamp photographs of patients with facial images to simulate expert assessment of TAO. Method: The study included 156 patients with TAO who underwent detailed diagnosis and treatment at Shanxi Eye Hospital Affiliated to Shanxi Medical University from May 2020 to September 2023. Anterior segment slit-lamp photographs and facial images were used as different modalities and analyzed from multiple perspectives. Two ophthalmologists with more than 10 years of clinical experience independently determined the reference CAS for each image. An ensemble deep learning model based on the residual network was constructed under supervised learning to predict five key inflammatory signs (redness of the eyelids and conjunctiva, and swelling of the eyelids, conjunctiva, and caruncle or plica) associated with TAO, and to integrate these objective signs with two subjective symptoms (spontaneous retrobulbar pain and pain on attempted upward or downward gaze) in order to assess TAO activity. Results: The proposed model achieved 0.906 accuracy, 0.833 specificity, 0.906 precision, 0.906 recall, and 0.906 F1-score in active TAO diagnosis, demonstrating advanced performance in predicting CAS and TAO activity signs compared to conventional single-view unimodal approaches. The integration of multiple views and modalities, encompassing both anterior segment slit-lamp photographs and facial images, significantly improved the prediction accuracy of the model for TAO activity and CAS. Conclusion: The ensemble multi-view multimodal deep learning system developed in this study can more accurately assess the clinical activity of TAO than traditional methods that solely rely on facial images. This innovative approach is intended to enhance the efficiency of TAO activity assessment, providing a novel means for its comprehensive, early, and precise evaluation.

Interferometric modulation for generating extended light sheet: improving field of view.

Significance: Light-sheet fluorescence microscopy (LSFM) has emerged as a powerful and versatile imaging technique renowned for its remarkable features, including high-speed 3D tomography, minimal photobleaching, and low phototoxicity. The interference light-sheet fluorescence microscope, with its larger field of view (FOV) and more uniform axial resolution, possesses significant potential for a wide range of applications in biology and medicine. Aim: The aim of this study is to investigate the interference behavior among multiple light sheets (LSs) in LSFM and optimize the FOV and resolution of the light-sheet fluorescence microscope. Approach: We conducted a detailed investigation of the interference effects among LSs through theoretical derivation and numerical simulations, aiming to find optimal parameters. Subsequently, we constructed a customized system of multi-LSFM that incorporates both interference light sheets (ILS) and noninterference light-sheet configurations. We performed beam imaging and microsphere imaging tests to evaluate the FOV and axial resolution of these systems. Results: Using our custom-designed light-sheet fluorescence microscope, we captured the intensity distribution profiles of both interference and noninterference light sheets (NILS). Additionally, we conducted imaging tests on microspheres to assess their imaging outcomes. The ILS not only exhibits a larger FOV compared to the NILS but also demonstrates a more uniform axial resolution. Conclusions: By effectively modulating the interference among multiple LSs, it is possible to optimize the intensity distribution of the LSs, expand the FOV, and achieve a more uniform axial resolution.

Beach surface model construction: A strategy approach with structure from motion - multi-view stereo.

In contrast to traditional beach profiling methods like topographic surveys and GNSS, which pose significant challenges in terms of cost and time, this research underscores the efficiency, cost-effectiveness, and simplicity of terrestrial photogrammetry employing the Structure from Motion-Multi View Stereo (SfM-MVS) method. Notably, this approach enables the utilization of commonplace devices such as smartphones for data capture. The methodology integrates a 12-megapixel camera for image acquisition, processed through Agisoft Metashape Professional software, and validated for accuracy using ground control points (GCPs) and checkpoints (CKPs) calibrated via GNSS. Findings reveal substantial disparities in positional accuracy according to the Ground Control Points distribution. The study underscores the critical role of strategically distributing GCPs and CKPs in effectively mapping coastal areas, thus affirming the potential of SfM-MVS as a powerful and accessible tool for coastal monitoring initiatives. This research contributes significantly to advancing the efficiency and accessibility of beach profile monitoring, offering invaluable insights for researchers and practitioners in coastal management and environmental conservation efforts.•A simplified beach profile modeling methodology is proposed.•The method is faster and more cost-effective than traditional surveys (RTK GNSS, lidar, RPA).•The study highlights the importance of GCP and CKP distribution in enhancing SfM-MVS accuracy for coastal mapping.