RESUMEN

Research on goal-predictive gaze shifts in infancy so far has mostly focused on the effect of infants' experience with observed actions or the effect of agency cues that the observed agent displays. However, the perspective from which an action is presented to the infants (egocentric vs. allocentric) has received only little attention from researchers despite the fact that the natural observation of own actions is always linked to an egocentric perspective, whereas the observation of others' actions is often linked to an allocentric perspective. The current study investigated the timing of 6-, 9-, and 12-month-olds' goal-predictive gaze behavior, as well as that of adults, during the observation of simple human grasping actions that were presented from either an egocentric or allocentric perspective (within-participants design). The results showed that at 6 and 9 months of age, the infants predicted the action goal only when observing the action from the egocentric perspective. The 12-month-olds and adults, in contrast, predicted the action in both perspectives. The results therefore are in line with accounts proposing an advantage of egocentric versus allocentric processing of social stimuli, at least early in development. This study is among the first to show this egocentric bias already during the first year of life.

RESUMEN

Building characteristics are vital across various domains such as construction management and architectural design. Static Street View Images (SSVIs) can be utilized with deep learning techniques to interpret building characteristics without the need for a physical visit. Deep learning approaches have demonstrated a high capability for generalization, enabling the automation of manual tasks related to image analysis. However, there is no publicly available labeled dataset of building characteristics from building facade images for training deep learning models. In this article, we focus on constructing a dataset for four different tasks: classification of the number of stories, classification of building typologies, classification of exterior cladding materials, and classification of usable SSVIs. To develop deep learning models, this article constructed a dataset sourced from London and Scotland in the UK. The dataset was labeled by annotation experts. While the focus of this research is on specific tasks, the raw dataset can be used for other purposes (e.g., ascertaining the age of buildings or identifying window types) by annotating the data for the corresponding tasks.

RESUMEN

Purpose: Interpreting echocardiographic exams requires substantial manual interaction as videos lack scan-plane information and have inconsistent image quality, ranging from clinically relevant to unrecognizable. Thus, a manual prerequisite step for analysis is to select the appropriate views that showcase both the target anatomy and optimal image quality. To automate this selection process, we present a method for automatic classification of routine views, recognition of unknown views, and quality assessment of detected views. Approach: We train a neural network for view classification and employ the logit activations from the neural network for unknown view recognition. Subsequently, we train a linear regression algorithm that uses feature embeddings from the neural network to predict view quality scores. We evaluate the method on a clinical test set of 2466 echocardiography videos with expert-annotated view labels and a subset of 438 videos with expert-rated view quality scores. A second observer annotated a subset of 894 videos, including all quality-rated videos. Results: The proposed method achieved an accuracy of 84.9 % ± 0.67 for the joint objective of routine view classification and unknown view recognition, whereas a second observer reached an accuracy of 87.6%. For view quality assessment, the method achieved a Spearman's rank correlation coefficient of 0.71, whereas a second observer reached a correlation coefficient of 0.62. Conclusion: The proposed method approaches expert-level performance, enabling fully automatic selection of the most appropriate views for manual or automatic downstream analysis.

RESUMEN

How we view the passage of past time determines how we face time itself as well as our futures, which has a strong impact particularly during the highly creative and malleable college years. Chinese culture cherishes time deeply, and for centuries there has been a tradition of "educating children and youth to inspect the passage of time." However, in today's age of information and intelligence, time has shown a trend toward fragmentation. How do contemporary Chinese college students view the passage of time, and what structures or content does it contain? The answer to this question remains uncertain, necessitating further exploration. Following Flavell's theory of metacognitive knowledge (MK), we adopted a semi-structured interview method and used the results to first outline the basic structure of Chinese college students' view of time passing, identifying four major aspects: priming aftereffect, life touching, positive promotion, and negative inhibition. Then, using the initial four-dimensional structure as a starting point, we developed the Metacognitive Knowledge of Time Passing Scale (MKTPS), and carried out exploratory factor analysis and confirmatory factor analysis to test its fit. The results showed that the four-factor scale and its 22 items had a good fit to the data. Third, the reliability and validity of the self-developed scale were tested. The results show that the internal consistency, split-half, and retest reliability of the MKTPS are good (all rs > 0.60). The construct validity of the MKTPS is also good (r between subscales is 0.33-0.60, r between subscales and total scale is 0.64-0.87), the convergent validity with Zimbardo's negative past time perspective is high (r = 0.37), and the discriminant validity with Zimbardo's future time perspective is significant (r = 0.18). Regarding criterion correlation validity, the total scores of the MKTPS have a significantly higher positive correlation with those of the time management disposition (TMD) scale (r = 0.45). Future points for studying the view of time passing in adults of all ages and across cultures field and shortcomings of the current study are also discussed.

RESUMEN

Multi-view multi-label learning (MVML) aims to train a model that can explore the multi-view information of the input sample to obtain its accurate predictions of multiple labels. Unfortunately, a majority of existing MVML methods are based on the assumption of data completeness, making them useless in practical applications with partially missing views or some uncertain labels. Recently, many approaches have been proposed for incomplete data, but few of them can handle the case of both missing views and labels. Moreover, these few existing works commonly ignore potentially valuable information about unknown labels or do not sufficiently explore latent label information. Therefore, in this paper, we propose a label semantic-guided contrastive learning method named LSGC for the dual incomplete multi-view multi-label classification problem. Concretely, LSGC employs deep neural networks to extract high-level features of samples. Inspired by the observation of exploiting label correlations to improve the feature discriminability, we introduce a graph convolutional network to effectively capture label semantics. Furthermore, we introduce a new sample-label contrastive loss to explore the label semantic information and enhance the feature representation learning. For missing labels, we adopt a pseudo-label filling strategy and develop a weighting mechanism to explore the confidently recovered label information. We validate the framework on five standard datasets and the experimental results show that our method achieves superior performance in comparison with the state-of-the-art methods.

RESUMEN

The limited data poses a crucial challenge for deep learning-based volumetric medical image segmentation, and many methods have tried to represent the volume by its subvolumes (i.e., multi-view slices) for alleviating this issue. However, such methods generally sacrifice inter-slice spatial continuity. Currently, a promising avenue involves incorporating multi-view information into the network to enhance volume representation learning, but most existing studies tend to overlook the discrepancy and dependency across different views, ultimately limiting the potential of multi-view representations. To this end, we propose a cross-view discrepancy-dependency network (CvDd-Net) to task with volumetric medical image segmentation, which exploits multi-view slice prior to assist volume representation learning and explore view discrepancy and view dependency for performance improvement. Specifically, we develop a discrepancy-aware morphology reinforcement (DaMR) module to effectively learn view-specific representation by mining morphological information (i.e., boundary and position of object). Besides, we design a dependency-aware information aggregation (DaIA) module to adequately harness the multi-view slice prior, enhancing individual view representations of the volume and integrating them based on cross-view dependency. Extensive experiments on four medical image datasets (i.e., Thyroid, Cervix, Pancreas, and Glioma) demonstrate the efficacy of the proposed method on both fully-supervised and semi-supervised tasks.

RESUMEN

Image clustering aims to divide a set of unlabeled images into multiple clusters. Recently, clustering methods based on contrastive learning have attracted much attention due to their ability to learn discriminative feature representations. Nevertheless, existing clustering algorithms face challenges in capturing global information and preserving semantic continuity. Additionally, these methods often exhibit relatively singular feature distributions, limiting the full potential of contrastive learning in clustering. These problems can have a negative impact on the performance of image clustering. To address the above problems, we propose a deep clustering framework termed Efficient Contrastive Clustering via Pseudo-Siamese Vision Transformer and Multi-view Augmentation (ECCT). The core idea is to introduce Vision Transformer (ViT) to provide the global view, and improve it with Hilbert Patch Embedding (HPE) module to construct a new ViT branch. Finally, we fuse the features extracted from the two ViT branches to obtain both global view and semantic coherence. In addition, we employ multi-view random aggressive augmentation to broaden the feature distribution, enabling the model to learn more comprehensive and richer contrastive features. Our results on five datasets demonstrate that ECCT outperforms previous clustering methods. In particular, the ARI metric of ECCT on the STL-10 (ImageNet-Dogs) dataset is 0.852 (0.424), which is 10.3% (4.8%) higher than the best baseline.

RESUMEN

MicroRNAs (miRNAs) are a key class of endogenous non-coding RNAs that play a pivotal role in regulating diseases. Accurately predicting the intricate relationships between miRNAs and diseases carries profound implications for disease diagnosis, treatment, and prevention. However, these prediction tasks are highly challenging due to the complexity of the underlying relationships. While numerous effective prediction models exist for validating these associations, they often encounter information distortion due to limitations in efficiently retaining information during the encoding-decoding process. Inspired by Multi-layer Heterogeneous Graph Transformer and Machine Learning XGboost classifier algorithm, this study introduces a novel computational approach based on multi-layer heterogeneous encoder-machine learning decoder structure for miRNA-disease association prediction (MHXGMDA). First, we employ the multi-view similarity matrices as the input coding for MHXGMDA. Subsequently, we utilize the multi-layer heterogeneous encoder to capture the embeddings of miRNAs and diseases, aiming to capture the maximum amount of relevant features. Finally, the information from all layers is concatenated to serve as input to the machine learning classifier, ensuring maximal preservation of encoding details. We conducted a comprehensive comparison of seven different classifier models and ultimately selected the XGBoost algorithm as the decoder. This algorithm leverages miRNA embedding features and disease embedding features to decode and predict the association scores between miRNAs and diseases. We applied MHXGMDA to predict human miRNA-disease associations on two benchmark datasets. Experimental findings demonstrate that our approach surpasses several leading methods in terms of both the area under the receiver operating characteristic curve and the area under the precision-recall curve.

Asunto(s)

RESUMEN

In this paper, we present a noise-robust approach for the 3D pose estimation of multiple people using appearance similarity. The common methods identify the cross-view correspondences between the detected keypoints and determine their association with a specific person by measuring the distances between the epipolar lines and the joint locations of the 2D keypoints across all the views. Although existing methods achieve remarkable accuracy, they are still sensitive to camera calibration, making them unsuitable for noisy environments where any of the cameras slightly change angle or position. To address these limitations and fix camera calibration error in real-time, we propose a framework for 3D pose estimation which uses appearance similarity. In the proposed framework, we detect the 2D keypoints and extract the appearance feature and transfer it to the central server. The central server uses geometrical affinity and appearance similarity to match the detected 2D human poses to each person. Then, it compares these two groups to identify calibration errors. If a camera with the wrong calibration is identified, the central server fixes the calibration error, ensuring accuracy in the 3D reconstruction of skeletons. In the experimental environment, we verified that the proposed algorithm is robust against false geometrical errors. It achieves around 11.5% and 8% improvement in the accuracy of 3D pose estimation on the Campus and Shelf datasets, respectively.

RESUMEN

The accurate reconstruction of indoor environments is crucial for applications in augmented reality, virtual reality, and robotics. However, existing indoor datasets are often limited in scale, lack ground truth point clouds, and provide insufficient viewpoints, which impedes the development of robust novel view synthesis (NVS) techniques. To address these limitations, we introduce a new large-scale indoor dataset that features diverse and challenging scenes, including basements and long corridors. This dataset offers panoramic image sequences for comprehensive coverage, high-resolution point clouds, meshes, and textures as ground truth, and a novel benchmark specifically designed to evaluate NVS algorithms in complex indoor environments. Our dataset and benchmark aim to advance indoor scene reconstruction and facilitate the creation of more effective NVS solutions for real-world applications.

RESUMEN

Dobutamine stress echocardiography is an integral part of the evaluation of aortic stenosis (AS) severity in low-gradient AS. In transthoracic echocardiography, in 20% of the patients, the highest aortic valve peak transvalvular velocity and mean gradient are achieved with continuous wave Doppler, from the suprasternal or right parasternal view. We present a case of a 79-year-old-male, with low-gradient aortic stenosis, where the highest peak aortic valve velocity and mean gradient, were consistently obtained from the right parasternal view, during all stages of a dobutamine stress echocardiogram. Use of the right parasternal view was important in avoiding overestimation of aortic valve area and underestimation of aortic valve mean gradients and therefore AS severity at rest. Furthermore, it correctly identified significant increase of aortic valve mean gradients during stress and therefore confirmed the diagnosis of severe AS. This case report highlights the importance of routinely attempting right parasternal view, in patients undergoing stress echocardiography to ensure the maximum possible aortic valve gradient is obtained.

RESUMEN

New data sources and AI methods for extracting information are increasingly abundant and relevant to decision-making across societal applications. A notable example is street view imagery, available in over 100 countries, and purported to inform built environment interventions (e.g., adding sidewalks) for community health outcomes. However, biases can arise when decision-making does not account for data robustness or relies on spurious correlations. To investigate this risk, we analyzed 2.02 million Google Street View (GSV) images alongside health, demographic, and socioeconomic data from New York City. Findings demonstrate robustness challenges; built environment characteristics inferred from GSV labels at the intracity level often do not align with ground truth. Moreover, as average individual-level behavior of physical inactivity significantly mediates the impact of built environment features by census tract, intervention on features measured by GSV would be misestimated without proper model specification and consideration of this mediation mechanism. Using a causal framework accounting for these mediators, we determined that intervening by improving 10% of samples in the two lowest tertiles of physical inactivity would lead to a 4.17 (95% CI 3.84-4.55) or 17.2 (95% CI 14.4-21.3) times greater decrease in the prevalence of obesity or diabetes, respectively, compared to the same proportional intervention on the number of crosswalks by census tract. This study highlights critical issues of robustness and model specification in using emergent data sources, showing the data may not measure what is intended, and ignoring mediators can result in biased intervention effect estimates.

Asunto(s)

RESUMEN

OBJECTIVE: Performing obstetric ultrasound scans is challenging for inexperienced operators; therefore, the prenatal screening artificial intelligence system (PSAIS) software was developed to provide real-time feedback and guidance for trainees during their scanning procedures. The aim of this study was to investigate the potential benefits of utilizing such an artificial intelligence system to enhance the efficiency of obstetric ultrasound training in acquiring and interpreting standard basic views. METHODS: A prospective, single-center randomized controlled study was conducted at The First Affiliated Hospital of Sun Yat-sen University. From September 2022 to April 2023, residents with no prior obstetric ultrasound experience were recruited and assigned randomly to either a PSAIS-assisted training group or a conventional training group. Each trainee underwent a four-cycle practical scan training program, performing 20 scans in each cycle on pregnant volunteers at 18-32 gestational weeks, focusing on acquiring and interpreting standard basic views. At the end of each cycle, a test scan evaluated trainees' ability to obtain standard ultrasound views without PSAIS assistance, and image quality was rated by both the trainees themselves and an expert (in a blinded manner). The primary outcome was the number of training cycles required for each trainee to meet a certain standard of proficiency (i.e. end-of-cycle test scored by the expert at ≥ 80%). Secondary outcomes included the expert ratings of the image quality in each trainee's end-of-cycle test and the discordance between ratings by trainees and the expert. RESULTS: In total, 32 residents and 1809 pregnant women (2720 scans) were recruited for the study. The PSAIS-assisted trainee group required significantly fewer training cycles compared with the non-PSAIS-assisted group to meet quality requirements (P = 0.037). Based on the expert ratings of image quality, the PSAIS-assisted training group exhibited superior ability in acquiring standard imaging views compared with the conventional training group in the third (P = 0.012) and fourth (P < 0.001) cycles. In both groups, the discordance between trainees' ratings of the quality of their own images and the expert's ratings decreased with increasing training time. A statistically significant difference in overall trainee-expert rating discordance between the two groups emerged at the end of the first training cycle and remained at every cycle thereafter (P < 0.013). CONCLUSION: By assisting inexperienced trainees in obtaining and interpreting standard basic obstetric scanning views, the use of artificial intelligence-assisted systems has the potential to improve training effectiveness. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

RESUMEN

Background: The use of digital online teaching media in improving the surgical skills of medical students is indispensable, yet it is still not widely explored objectively. The first-person-view online teaching method may be more effective as it provides more realism to surgical clerkship students in achieving basic surgical skills. Objective: This study aims to objectively assess the effectiveness of the first-person-view live streaming (LS) method using a GoPro camera compared to the standard face-to-face (FTF) teaching method in improving simple wound suturing skills in surgical clerkship students. Methods: A prospective, parallel, nonblinded, single-center, randomized controlled trial was performed. Between January and April 2023, clerkship students of the Department of Surgery, Pelita Harapan University, were randomly selected and recruited into either the LS or FTF teaching method for simple interrupted suturing skills. All the participants were assessed objectively before and 1 week after training, using the direct observational procedural skills (DOPS) method. DOPS results and poststudy questionnaires were analyzed. Results: A total of 74 students were included in this study, with 37 (50%) participants in each group. Paired analysis of each participant's pre-experiment and postexperiment DOPS scores revealed that the LS method's outcome is comparable to the FTF method's outcome (LS: mean 27.5, SD 20.6 vs FTF: mean 24.4, SD 16.7; P=.48) in improving the students' surgical skills. Conclusions: First-person-view LS training sessions could enhance students' ability to master simple procedural skills such as simple wound suturing and has comparable results to the current FTF teaching method. Teaching a practical skill using the LS method also gives more confidence for the participants to perform the procedure independently. Other advantages of the LS method, such as the ability to study from outside the sterile environment, are also promising. We recommend improvements in the audiovisual quality of the camera and a stable internet connection before performing the LS teaching method.

Asunto(s)

RESUMEN

OBJECTIVES: The selection of treatment for dental plaque is closely related to the condition of the plaque on different teeth. This study validated the ability of CNN models in assessing the dental plaque indices. MATERIALS AND METHODS: In 70 (20 male and 50 female) healthy adults (18 to 55 years old), frontal and lateral view intraoral images (210) of plaque disclosing agent stained permanent and deciduous dentitions were obtained. A three-stage method was employed, where the You Look Only Once version 8 (YOLOv8) model was first used to detect the target teeth, followed by the prompt-based Segment Anything Model (SAM) segmentation algorithm to segment teeth. A new single-tooth dataset consisting of 1400 photographs was obtained after applying a two-stage method. Finally, a multi-class classification model DeepPlaq was trained and evaluated on the accuracy of dental plaque indexing based on the Quigley-Hein Index (QHI) scoring system. Classification performance was measured using accuracy, recall, precision, and F1-score. RESULTS: The teeth detector exhibited an accuracy (mean average precision, mAP) of approximately 0.941 ± 0.005 in identifying teeth with plaque disclosing agents. The maximum accuracy attained in the plaque indexing through DeepPlaq was 0.84 (probability that DeepPlaq scored identical to experts), and the smallest average scoring error was less than 0.25 on a 0 to 5 scale for scoring. CONCLUSIONS: A three-stage approach demonstrated excellent performance in detecting and segmenting target teeth, and DeepPlaq model also showed strong performance in assessing dental plaque indices. CLINICAL RELEVANCE: Application of artificial intelligence to the evaluation of dental plaque distribution could enhance diagnostic accuracy and treatment efficiency and accuracy.

Asunto(s)

RESUMEN

Troubleshooting is an important part of experimental research, but graduate students rarely receive formal training in this skill. In this article, we describe an initiative called Pipettes and Problem Solving that we developed to teach troubleshooting skills to graduate students at the University of Texas at Austin. An experienced researcher presents details of a hypothetical experiment that has produced unexpected results, and students have to propose new experiments that will help identify the source of the problem. We also provide slides and other resources that can be used to facilitate problem solving and teach troubleshooting skills at other institutions.

Asunto(s)

RESUMEN

Following the discovery of the least squares method in 1805 by Legendre and later in 1809 by Gauss, surrogate modeling and machine learning have come a long way. From identifying patterns and trends in process data to predictive modeling, optimization, fault detection, reaction network discovery, and process operations, machine learning became an integral part of all aspects of process design and process systems engineering. This is enabled, at the same time necessitated, by the vast amounts of data that are readily available from processes, increased digitalization, automation, increasing computation power, and simulation software that can model complex phenomena that span over several temporal and spatial scales. Although this paper is not a comprehensive review, it gives an overview of the recent history of machine learning models that we use every day and how they shaped process design problems from the recent advances to the exploration of their prospects.

RESUMEN

Introduction Surgeons-in-training (SIT) perform laparoscopic cholecystectomy (LC); however, it is challenging to complete the procedure safely in difficult cases. We present a surgical technique during difficult LC, which we named the hanging strap method. Methods We retrospectively compared the perioperative outcomes between patients undergoing difficult LC with the hanging strap method (HANGS, n = 34), and patients undergoing difficult LC without the hanging strap method (non-HANGS, n = 56) from 2022 and 2024. Difficult LC was defined as cases classified as more than grade II cholecystitis by the Tokyo Guidelines 18 and cases when LC was undergoing over five days after the onset of cholecystitis. Results The proportion of SIT with post-graduate year (PGY) ≤ 7 was significantly higher in the HANGS group than in the non-HANGS group (82.4% vs. 33.9%, P < 0.001). The overall rate of bile duct injury (BDI), postoperative bile leakage and operative mortality were zero in the whole cohort. There were no significant differences between the HANGS and non-HANGS groups in background characteristics, operative time (122 min vs. 132 min, P = 0.830) and surgical blood loss (14 mL vs. 24 mL, P = 0.533). Conclusions Our findings suggested that the hanging strap method is safe and easy to use for difficult LC. We recommend that the current method be selected as one of the surgical techniques for SIT when performing difficult LC.

RESUMEN

Background: Resting-state brain networks represent the interconnectivity of different brain regions during rest. Utilizing brain network analysis methods to model these networks can enhance our understanding of how different brain regions collaborate and communicate without explicit external stimuli. However, analyzing resting-state brain networks faces challenges due to high heterogeneity and noise correlation between subjects. This study proposes a brain structure learning-guided multi-view graph representation learning method to address the limitations of current brain network analysis and improve the diagnostic accuracy (ACC) of mental disorders. Methods: We first used multiple thresholds to generate different sparse levels of brain networks. Subsequently, we introduced graph pooling to optimize the brain network representation by reducing noise edges and data inconsistency, thereby providing more reliable input for subsequent graph convolutional networks (GCNs). Following this, we designed a multi-view GCN to comprehensively capture the complexity and variability of brain structure. Finally, we employed an attention-based adaptive module to adjust the contributions of different views, facilitating their fusion. Considering that the Smith atlas offers superior characterization of resting-state brain networks, we utilized the Smith atlas to construct the graph network. Results: Experiments on two mental disorder datasets, the Autism Brain Imaging Data Exchange (ABIDE) dataset and the Mexican Cocaine Use Disorders (SUDMEX CONN) dataset, show that our model outperforms the state-of-the-art methods, achieving nearly 75% ACC and 70% area under the receiver operating characteristic curve (AUC) on both datasets. Conclusions: These findings demonstrate that our method of combining multi-view graph learning and brain structure learning can effectively capture crucial structural information in brain networks while facilitating the acquisition of feature information from diverse perspectives, thereby improving the performance of brain network analysis.

RESUMEN

Introduction: Moral Intelligence (MI) as a concept has gained importance in recent years due to its wide applicability in individual, organizational, and clinical settings or even policy making. The present study employed Bibliometric analysis to understand the emerging topics associated with MI and its global research trend. This paper's primary aim was (i) to explore the temporal and geographic growth trends of the research publication on MI. (ii) to identify the most prolific countries, institutions, and authors, working on MI, (iii) to identify the most frequent terminologies, (iv) to explore research topics and to provide insight into potential collaborations and future directions, and (v) to explore the significance of the concept of moral intelligence. Method: Bibliometric analysis was used to understand the emerging topics associated with MI and its global research trend using the SCOPUS database. VOS viewer and R were employed to analyze the result. Through the analysis conducted, the development of the construct over time was analyzed. Results: Results have shown that Iran and the United States and these two combined account for 53.16% of the total country-wise publications. Switzerland has the highest number of Multi-county publications. Authors from Iran and Switzerland have the most number of publications. Emerging topics like decision-making, machine ethics, moral agents, artificial ethics, co-evolution of human and artificial moral agents, green purchase intention etc were identified. Discussion: The application of MI in organisational decision-making, education policy, artificial intelligence and measurement of moral intelligence are important areas of application as per the results. Research interest in MI is projected to increase according to the results delineated in this article.