Visual Computing for Industry Biomedicine and Art最新文献

The use of extended reality (XR) spectrum technologies as substitutes to augment traditional simulators in pilot flight training has received significant interest in recent times. A systematic review was conducted to evaluate the efficacy of XR technologies for this purpose and better understand the motivating factors for this use. The systematic review followed the QUOROM framework (adapted for educational studies), screening 1237 candidate articles to 67 eligible for thematic analysis, with 5 of these also meeting meta-analysis criteria. Existing literature emphasizes the benefits of these technologies, particularly as a result of immersiveness and spatial awareness, enabling the application of more modern educational theories. Although the existing literature is concerned with much of the industry, there is a specific focus on general aviation and the more ab initio skills of flight. The results of the meta-analysis indicate improvements in pilot performance, with an overall meta-analytic effect size estimate of 0.884 (z = 2.248, P = 0.025), which is positive, statistically significant, and moderately strong. The findings of this review indicate support for the use and intention for the use of XR in pilot flight training simulators. However, multiple serious research gaps exist, such as the potential higher occurrence of simulator sickness and cybersickness, and a lack of robust research trials that examine transfer of training across the full pilot skill set and curricular contexts. This novel systematic review and meta-analysis represent a significant attempt to shape and direct better research to help to direct flourishing technological XR development in a time of increasing pilot shortages and aviation growth.

Gesture-based interactions in a virtual reality (VR) setting can enhance our experience of traditional practices as part of preserving and communicating heritage. Cultural experiences embodied within VR environments are suggested to be an effective approach for experiencing intangible cultural heritage. Ceremonies, rituals, and related ancestral enactments are important for preserving cultural heritage. Kāi Bǐ Lǐ, also known as the First Writing Ceremony, is traditionally held for Chinese children before their first year of elementary school. However, gesture-based immersive VR for learning this tradition is new, and have not been developed within the community. This study focused on how users experienced learning cultural practices using gesture-based interactive VR across different age groups and hardware platforms. We first conducted an experiment with 60 participants (30 young adults and 30 children) using the First Writing Ceremony as a case study in which gestural interactions were elicited, designed, implemented, and evaluated. The study showed significant differences in play time and presence between the head-mounted display VR and desktop VR. In addition, children were less likely to experience fatigue than young adults. Following this, we conducted another study after eight months to investigate the VR systems' long-term learning effectiveness. This showed that children outperformed young adults in demonstrating greater knowledge retention. Our results and findings contribute to the design of gesture-based VR for different age groups across different platforms for experiencing, learning, and practicing cultural activities.

In recent years, the application of artificial intelligence (AI) in medical image analysis has drawn increasing attention in clinical studies of gynecologic tumors. This study presents the development and prospects of AI applications to assist in the treatment of gynecological oncology. The Web of Science database was screened for articles published until August 2023. "artificial intelligence," "deep learning," "machine learning," "radiomics," "radiotherapy," "chemoradiotherapy," "neoadjuvant therapy," "immunotherapy," "gynecological malignancy," "cervical carcinoma," "cervical cancer," "ovarian cancer," "endometrial cancer," "vulvar cancer," "Vaginal cancer" were used as keywords. Research articles related to AI-assisted treatment of gynecological cancers were included. A total of 317 articles were retrieved based on the search strategy, and 133 were selected by applying the inclusion and exclusion criteria, including 114 on cervical cancer, 10 on endometrial cancer, and 9 on ovarian cancer. Among the included studies, 44 (33%) focused on prognosis prediction, 24 (18%) on treatment response prediction, 13 (10%) on adverse event prediction, five (4%) on dose distribution prediction, and 47 (35%) on target volume delineation. Target volume delineation and dose prediction were performed using deep Learning methods. For the prediction of treatment response, prognosis, and adverse events, 57 studies (70%) used conventional radiomics methods, 13 (16%) used deep Learning methods, 8 (10%) used spatial-related unconventional radiomics methods, and 3 (4%) used temporal-related unconventional radiomics methods. In cervical and endometrial cancers, target prediction mostly included treatment response, overall survival, recurrence, toxicity undergoing radiotherapy, lymph node metastasis, and dose distribution. For ovarian cancer, the target prediction included platinum sensitivity and postoperative complications. The majority of the studies were single-center, retrospective, and small-scale; 101 studies (76%) had single-center data, 125 studies (94%) were retrospective, and 127 studies (95%) included Less than 500 cases. The application of AI in assisting treatment in gynecological oncology remains limited. Although the results of AI in predicting the response, prognosis, adverse events, and dose distribution in gynecological oncology are superior, it is evident that there is no validation of substantial data from multiple centers for these tasks.

Postoperative venous thromboembolism (VTE) in colorectal cancer (CRC) patients undergoing surgery results in poor prognosis. However, there are no effective tools for early screening and predicting VTE. In this study, we developed a machine learning (ML)-based model for predicting the risk of VTE following CRC surgery and tested its performance using an external dataset. A total of 3227 CRC surgery patients were enrolled from the Affiliated Hospital of Qingdao University and Yantai Yuhuangding Hospital (from January 2016 to December 2023). Subsequently, 1596 patients from the Affiliated Hospital of Qingdao University were assigned to the training set, and 716 patients from Yantai Yuhuangding Hospital were assigned to the external validation set. A model was developed and trained using six ML algorithms using the stacking ensemble technique. Moreover, all models were developed using the tenfold cross-validation on the training set, and their performance was tested using an independent external validation set. In the training set, 173 (10.8%) patients developed VTE, 163 (10.2%) patients experienced deep venous thrombosis, and 29 (1.82%) cases had pulmonary embolism (PE). In the external validation set, 85 (11.9%) cases of VTE, 83 (11.6%) cases of deep vein thrombosis, and 14 (1.96%) cases of PE were recorded. The analysis revealed that the stacking model outperformed all other models in the external validation set, achieving significantly better performance in all metrics: the area under the receiver operating characteristic curve = 0.840 (0.790-0.887), accuracy = 0.810 (0.783-0.836), specificity = 0.819 (0.790-0.848), sensitivity = 0.741 (0.652-0.825), and recall = 0.959 (0.942-0.975). The stacking model for surgical CRC patients shows promise in enabling timely clinical detection of high-risk cases. This method facilitates the prioritized implementation of prophylactic anticoagulation in confirmed high-risk individuals, thereby mitigating unnecessary pharmacological intervention in low-risk populations.

This review examines the current applications, benefits, challenges, and future potential of artificial intelligence (AI) and immersive aviation technologies. AI has been applied across various domains, including flight operations, air traffic control, maintenance, and ground handling. AI enhances aviation safety by enabling pilot assistance systems, mitigating human error, streamlining safety management systems, and aiding in accident analysis. Lightweight AI models are crucial for mobile applications in aviation, particularly for resource-constrained environments such as drones. Hardware considerations involve trade-offs between energy-efficient field-programmable gate arrays and power-consuming graphics processing units. Battery and thermal management are critical for mobile device applications. Although AI integration has numerous benefits, including enhanced safety, improved efficiency, and reduced environmental impact, it also presents challenges. Addressing algorithmic bias, ensuring cybersecurity, and managing the relationship between human operators and AI systems are crucial. The future of aviation will likely involve even more sophisticated AI algorithms, advanced hardware, and increased integration of AI with augmented reality and virtual reality, creating new possibilities for training and operations, and ultimately leading to a safer, more efficient, and more sustainable aviation industry.

Post-stroke cognitive impairment (PSCI) is a common and debilitating consequence of stroke that often arises from complex interactions between diverse brain alterations. The accurate early prediction of PSCI is critical for guiding personalized interventions. However, existing methods often struggle to capture complex structural disruptions and integrate multimodal information effectively. This study proposes the multimodal dynamic hierarchical clustering network (MDHCNet), a graph neural network designed for accurate and interpretable PSCI prediction. MDHCNet constructs brain graphs from diffusion-weighted imaging, magnetic resonance angiography, and T1- and T2-weighted images and integrates them with clinical features using a hierarchical cross-modal fusion module. Experimental results using a real-world stroke cohort demonstrated that MDHCNet consistently outperformed deep learning baselines. Ablation studies validated the benefits of multimodal fusion, while saliency-based interpretation highlighted discriminative brain regions associated with cognitive decline. These findings suggest that MDHCNet is an effective and explainable tool for early PSCI prediction, with the potential to support individualized clinical decision-making in stroke rehabilitation.

Accurate, noninvasive diagnosis of compensated advanced chronic liver disease (cACLD) is essential for effective clinical management but remains challenging. This study aimed to develop a deep learning-based radiomics model using international multicenter data and to evaluate its performance by comparing it to the two-dimensional shear wave elastography (2D-SWE) cut-off method covering multiple countries or regions, etiologies, and ultrasound device manufacturers. This retrospective study included 1937 adult patients with chronic liver disease due to hepatitis B, hepatitis C, or metabolic dysfunction-associated steatotic liver disease. All patients underwent 2D-SWE imaging and liver biopsy at 17 centers across China, Japan, and Europe using devices from three manufacturers (SuperSonic Imagine, General Electric, and Mindray). The proposed generalized deep learning radiomics of elastography model integrated both elastographic images and liver stiffness measurements and was trained and tested on stratified internal and external datasets. A total of 1937 patients with 9472 2D-SWE images were included in the statistical analysis. Compared to 2D-SWE, the model achieved a higher area under the receiver operating characteristic curve (AUC) (0.89 vs 0.83, P = 0.025). It also achieved a highly consistent diagnosis across all subanalyses (P values: 0.21-0.91), whereas 2D-SWE exhibited different AUCs in the country or region (P < 0.001) and etiology (P = 0.005) subanalyses but not in the manufacturer subanalysis (P = 0.24). The model demonstrated more accurate and robust performance in noninvasive cACLD diagnosis than 2D-SWE across different countries or regions, etiologies, and manufacturers.

Unmanned aerial vehicle (UAV) tracking is a critical task in surveillance, security, and autonomous navigation applications. In this study, we propose graph neural network-tracker (GNN-tracker), a novel GNN-based UAV tracking framework that effectively integrates graph-based spatial-temporal modelling, Transformer-based feature extraction, and multi-sensor fusion to enhance tracking robustness and accuracy. Unlike traditional tracking approaches, GNN-tracker dynamically constructs a spatiotemporal graph representation, improving identity consistency and reducing tracking errors under OCC-heavy scenarios. Experimental evaluations on optical, thermal, and fused UAV datasets demonstrate the superiority of GNN-tracker (fused) over state-of-the-art methods. The proposed model achieves multiple object tracking accuracy (MOTA) scores of 91.4% (fused), 89.1% (optical), and 86.3% (thermal), surpassing TransT by 8.9% in MOTA and 7.7% in higher order tracking accuracy (HOTA). The HOTA scores of 82.3% (fused), 80.1% (optical), and 78.7% (thermal) validate its strong object association capabilities, while its frames per second of 58.9 (fused), 56.8 (optical), and 54.3 (thermal) ensures real-time performance. Additionally, ablation studies confirm the essential role of graph-based modelling and multi-sensor fusion, with performance drops of up to 8.9% in MOTA when these components are removed. Thus, GNN-tracker (fused) offers a highly accurate, robust, and efficient UAV tracking solution, effectively addressing real-world challenges across diverse environmental conditions and multiple sensor modalities.

Placental segmentation is critical for the quantitative analysis of prenatal imaging applications. However, segmenting the placenta using magnetic resonance imaging (MRI) and ultrasound is challenging because of variations in fetal position, dynamic placental development, and image quality. Most segmentation methods define regions of interest with different shapes and intensities, encompassing the entire placenta or specific structures. Recently, deep learning has emerged as a key approach that offer high segmentation performance across diverse datasets. This review focuses on the recent advances in deep learning techniques for placental segmentation in medical imaging, specifically MRI and ultrasound modalities, and cover studies from 2019 to 2024. This review synthesizes recent research, expand knowledge in this innovative area, and highlight the potential of deep learning approaches to significantly enhance prenatal diagnostics. These findings emphasize the importance of selecting appropriate imaging modalities and model architectures tailored to specific clinical scenarios. In addition, integrating both MRI and ultrasound can enhance segmentation performance by leveraging complementary information. This review also discusses the challenges associated with the high costs and limited availability of advanced imaging technologies. It provides insights into the current state of placental segmentation techniques and their implications for improving maternal and fetal health outcomes, underscoring the transformative impact of deep learning on prenatal diagnostics.

In human-robot collaborative tasks, human trust in robots can reduce resistance to them, thereby increasing the success rate of task execution. However, most existing studies have focused on improving the success rate of human-robot collaboration (HRC) rather than on enhancing collaboration efficiency. To improve the overall collaboration efficiency while maintaining a high success rate, this study proposes an active interaction strategy generation for HRC based on trust. First, a trust-based optimal robot strategy generation method was proposed to generate the robot's optimal strategy in a HRC. This method employs a tree to model the HRC process under different robot strategies and calculates the optimal strategy based on the modeling results for the robot to execute. Second, the robot's performance was evaluated to calculate human's trust in a robot. A robot performance evaluation method based on a visual language model was also proposed. The evaluation results were input into the trust model to compute human's current trust. Finally, each time an object operation was completed, the robot's performance evaluation and optimal strategy generation methods worked together to automatically generate the optimal strategy of the robot for the next step until the entire collaborative task was completed. The experimental results demonstrates that this method significantly improve collaborative efficiency, achieving a high success rate in HRC.