Global Guidance Research Articles

Mobile phone aided reminder to promote childhood vaccination: a bibliometric analysis

Background: Vaccines have been demonstrated to reduce the incidence of disease. With global and regional guidance, the World Health Organization provides information and assistance to immunization programs worldwide. Despite all of the efforts, some countries’ vaccination rates remain low. When reminder and recall strategies are employed, vaccination rates in youngsters have been proven to improve. Only a few studies have looked into the effect of reminders sent through mobile phones on vaccine uptake. Objectives and methods: This study aims to evaluate how successful mobile phone-assisted reminders are at improving vaccination uptake rates. For this research, Pub Med, Scopus, Science Direct, and Google Scholar were used to look for papers published in the previous ten years that looked at the effectiveness of mobile phone vaccine reminders for children. These databases’ papers were chosen, extracted, and assessed using the inclusion and exclusion criteria. Out of a total of 1016 articles, ten were chosen for review. Results: According to the chosen articles, the majority of the study involved randomized control trials in both rural and urban settings spanning Africa, Asia, America, and Australia. Most of the research used text message/SMS interventions rather than voice call or phone call treatments. The outcome was determined by appointment adherence, vaccine coverage, and regular immunization completion. Regardless of the type of intervention utilized, the study group had higher vaccination coverage and completion rates than the control groups. In terms of vaccine timeliness, the research groups demonstrated an improvement. Extra incentives, manual calendars, and training have all been shown to be more successful. Providing extra incentives, manual calendars, or training is a more successful means of improving outcomes. Conclusion: Immunization coverage, schedule compliance, and vaccine uptake timeliness have all been proven to improve using mobile phone-assisted reminders in the form of text messages, voice messages, or phone calls. When used in conjunction with incentives, calendars, and training, these reminders help to increase success rates.

Geriatric drug trials on solid tumor are scarce worldwide.

Conducting geriatric trials is the most feasible way to address the vast underrepresentation of older adults in clinical trials of cancer therapies. This study is a globally comprehensive examination of geriatric trials for solid tumor worldwide over the last decade. Up-to-date information on cancer drug trials in older adults aged over 59 years from the beginning of 2012 to the end of 2021 was collected from Trialtrove and Pharmaprojects. The number of identified trials was the dependent variable and corresponding analysis was conducted from the perspective of time trend, status quo and comparisons by region and country, sponsor type and cancer type, study status and phase. A total of 292 geriatric cancer drug trials were identified, of which 287 were single-region studies, 219 were initiated by academic groups, and 55 (18.8%) were terminated. Decreasing trends in the annual number of all trials (-9.2% per year) and the annual number of trials by academic groups (-9.4%) were observed over time. Of the geriatric trials, 183 were conducted in Asia; this number was significantly higher than that in Europe (74), North America (37), Oceania (4), and South America (1). Similar difference was found in participation rate in trials by academic groups ranging from 71.7% in Asia to 0.5% in South America. Of the trials, 19 and 97 were initiated before drug and indication approval, respectively, and the remaining 176 were initiated after indication approval. Phase II trials accounted for the highest proportion of trials (213, 72.9%), while phase I trials accounted for the lowest proportion (14, 4.8%). Trials by academic groups had a higher termination rate (21.5% vs. 11.0%) and fewer were phase IV trials (8.2% vs. 21.9%). Treatment was explored for 16 different cancers, with lung, colorectal and breast cancers being the most common. Geriatric trials of solid tumor drugs are scarce and partially prematurely terminated. Moreover, the number of geriatric trials has decreased and differs according to region. Global guidance and regulatory supervision are needed to facilitate the acquisition of adequate evidence on drug risk-benefit profiles in older adults, and thus to achieve high-quality care and safe medication.

STrans-YOLOX: Fusing Swin Transformer and YOLOX for Automatic Pavement Crack Detection

Automatic pavement crack detection is crucial for reducing road maintenance costs and ensuring transportation safety. Although convolutional neural networks (CNNs) have been widely used in automatic pavement crack detection, they cannot adequately model the long-range dependencies between pixels and easily lose edge detail information in complex scenes. Moreover, irregular crack shapes also make the detection task challenging. To address these issues, an automatic pavement crack detection architecture named STrans-YOLOX is proposed. Specifically, the architecture first exploits the CNN backbone to extract feature information, preserving the local modeling ability of the CNN. Then, Swin Transformer is introduced to enhance the long-range dependencies through a self-attention mechanism by supplying each pixel with global features. A new global attention guidance module (GAGM) is used to ensure effective information propagation in the feature pyramid network (FPN) by using high-level semantic information to guide the low-level spatial information, thereby enhancing the multi-class and multi-scale features of cracks. During the post-processing stage, we utilize α-IoU-NMS to achieve the accurate suppression of the detection boxes in the case of occlusion and overlapping objects by introducing an adjustable power parameter. The experiments demonstrate that the proposed STrans-YOLOX achieves 63.37% mAP and surpasses the state-of-the-art models on the challenging pavement crack dataset.

Global-guidance chaotic multi-objective particle swarm optimization method for pneumatic suspension handling and ride quality enhancement on the basis of a thermodynamic model of a full vehicle

In this paper, the parameters of the validated suspension system model of a full-vehicle are tuned through design sensitivity analyses, and then Multi-Objective Particle Swarm Optimization (MOPSO) is used to enhance vehicle ride comfort, which is the vertical whole-body vibrations, and handling features, that is, roll motion and road holding, simultaneously. The parameters of this thermodynamic-based pneumatic suspension system model are comprised of the air spring reservoir volume, orifice resistance, initial volume, and pressure of the pneumatic springs. To enhance the convergence rate, computational times, and diversity of the swarm particles, we have incorporated chaotic dynamics into the MOPSO using the Logistic Map chaotic method to initialize the population and also employed the leader-based global guidance techniques to conduct the potential solutions in each iteration. The analysis of the proposed modeling and optimization results show that the suspension system has been reasonably boosted in terms of vehicle handling and ride comfort. Quantitatively, the RMS acceleration and pitch angle has been reduced by about 71% and 57%, respectively, showing a substantial improvement in passenger comfort. Furthermore, the proposed approach caused an increase in tire road-holding force by about 148% and a reduction of roll angle by 33% which results in an enhancement in vehicle handling, boosting vehicle driving safety.

Reliability-Based Fire Resistance Periods for Buildings in England

The traditional route to achieving adequate structural performance in the event of fire is through ensuring that structural elements attain fire resistance ratings. The magnitude of these ratings typically varies in function of the building use, size, and height. In their genesis, fire resistance ratings were a proxy for the specification required of elements such that they had a reasonable likelihood of surviving the full duration of a fire, i.e., burn-out. As such, fire resistance periods were specified in the function of fire load, which, over time, progressively increased in consideration of the consequences of fire induced structural failure. This ratcheting of fire resistance periods was seemingly done so based on the collective experience of the profession, in response to observations from real fires and, where applicable, resulting disasters. That is, the safety levels associated with current fire resistance recommendations in most global codes and guidance documents are not determined. Therefore, this paper presents a review of reliability-based acceptance criteria for structures, ahead of their application, to determine fire resistance recommendations for buildings in England based on both codified reliability indices and the principle of relative (marginal) lifesaving costs. The study applies a novel form of probabilistic time equivalence, which is augmented by fire occurrence related statistics/parameters, to arrive at risk-informed fire resistance ratings that directly relate to the life safety consequences of fire induced structural failure (i.e., fatalities) to adequate fire resistance ratings. In determining these building fire resistance periods, it is observed that safety targets which implicitly include material damage and building reconstruction costs result in fire resistance recommendations that are well-aligned with National codes and standards. That is, to some extent, the ratcheting of fire resistance periods with time has resulted in some potential resilience to fire. Where safety targets are rationalised in consideration of life safety only, i.e., through the principle of relative (marginal) lifesaving costs, it is shown that fire resistance periods can be optimised, particularly in sprinkler protected buildings. However, this has the potential to introduce vulnerabilities to common mode failures.

SDSC-UNet: Dual Skip Connection ViT-Based U-Shaped Model for Building Extraction

Benefiting from effective global information interaction, vision-transformers (ViTs) have been widely used in the building extraction task. However, buildings in remote sensing (RS) images usually differ greatly in size. Mainstream ViT-based segmentation models for RS images are based on Swin Transformer, which lacks multi-scale information inside the ViT block. In addition, they only connect the output of the entire ViT encoder block to the decoder, which ignore the similarity information of the attention maps inside the ViT encoder block, and are unable to provide better global dependencies for the decoder. To solve above problems, we introduce a novel Shunted Transformer, which enables the model to capture multi-scale information internally while fully establishing global dependencies, to build a pure ViT-based U-shaped model for building extraction. Furthermore, unlike the previous single-skip-connection structure of U-shaped methods, we build a novel dual skip connection structure inside the model. It simultaneously transmits the attention maps inside the ViT encoder block and its entire output to the decoder, thereby fully mining the information of the ViT encoder block and providing better global information guidance for the decoder. Thus, our model is named Shunted Dual Skip Connection UNet (SDSC-UNet). We also design a feature fusion module called Dual Skip Upsample Fusion Module (DSUFM) to aggregate the information. Our model has yields state-of-the-art (SOTA) performance (83.02%IoU) on the Inria Aerial Image Labeling Dataset. Code will be available.

Weakly Supervised Local–Global Anchor Guidance Network for Landslide Extraction With Image-Level Annotations

Weakly supervised learning using image-level annotations has become a popular choice for reducing labeling efforts of remote sensing object extraction. Existing methods exploit inter-pixel relations within an individual image patch for object localizations. When facing large-scale remote sensing images, it is still challenging to obtain global semantic contexts across image patches for feature representation, resulting in inaccurate object localizations. To remedy these issues, we propose a local-global anchor guidance network (LGAGNet) for weakly supervised landslide extraction. Specifically, a structure-aware object locating (SOL) module is developed to capture the spatial structure of landslide objects and extract local category anchors containing informative feature embeddings. Furthermore, we leverage a global anchor aggregation (GAA) module to excavate semantic patterns across image patches based on a memory bank, which is then used as additional context cues to enhance the feature presentation through a cross-attention mechanism. Finally, a hybrid loss function is designed to guide the network training, considering category-aware semantic contrasts and local activation consistency. Experimental results on high-resolution aerial and satellite image datasets verify the effectiveness of the proposed approach on landslide extraction.

C$^{2}$DFNet: Criss-Cross Dynamic Filter Network for RGB-D Salient Object Detection

The ability to deal with intra and inter-modality features has been critical to the development of RGB-D salient object detection. While many works have advanced in leaps and bounds in this field, most existing methods have not taken their way down into the inherent differences between the RGB and depth data due to widely adopted conventional convolution in which fixed parameter kernels are applied during inference. To promote intra and inter-modality interaction conditioned on various scenarios, as RGB and depth data are processed independently and later fused interactively, we develop a new insight and a better model. In this paper, we introduce a criss-cross dynamic filter network by decoupling dynamic convolution. First, we propose a Model-specific Dynamic Enhanced Module (MDEM) that dynamically enhances the intra-modality features with global context guidance. Second, we propose a Scene-aware Dynamic Fusion Module (SDFM) to realize dynamic feature selection between two modalities. As a result, our model achieves accurate predictions of salient objects. Extensive experiments demonstrate that our method achieves competitive performance over 28 state-of-the-art RGB-D methods on 7 public datasets. The code and results of our method are available at https://github.com/OIPLab-DUT/C2DFNet.

TSFNet: Triple-Steam Image Captioning

Image captioning is a challenging task that generates a natural language description based on the visual understanding of the given image. Significant region representation is a milestone in image captioning. Despite the great success of existing region-based works, they only focus on the salient objects and encode these objects independently, still plagued by the lack of global contextual information and visual relationships. In fact, the global contextual information and structured visual relationships are exactly the merits of traditional grid features and emerging scene graph features. In this paper, we present a Triple-Steam Feature Fusion Network (TSFNet) to leverage the complementary advantages of the grid, region, and scene graph triple-steam visual representations in image captioning. Concretely, in our TSFNet, a novel Dual-level Attention (DA) mechanism is proposed to simultaneously explore visual intrinsic properties and word-related attributes uniformly of different features. Then attention enhanced features of different modalities are mapped into a joint representation to guide the caption generation. Moreover, we design a new global-aware decoder, which leverages the concatenated representation of triple-steam features and the joint attention representation to obtain global visual guidance information, further refine the complex multimodal reasoning. To verify the effectiveness of our feature fusion model, we perform extensive experiments on the highly competitive MSCOCO dataset to evaluate the model quantitatively and qualitatively. The results illustrate that the proposed framework outperforms many state-of-the-art image captioning approaches in various evaluation metrics, and generates more accurate and abundant captions.

PoolNet+: Exploring the Potential of Pooling for Salient Object Detection.

We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a 300 ×400 image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/.

MISNet: Multiscale Cross-Layer Interactive and Similarity Refinement Network for Scene Parsing of Aerial Images

Although progress has been made in multisource data scene parsing of natural scene images, extracting complex backgrounds from aerial images of various types and presenting the image at different scales remain challenging. Various factors in high-resolution aerial images (HRAIs), such as imaging blur, background clutter, object shadow, and high resolution, substantially reduce the integrity and accuracy of object segmentation. By applying multisource data fusion, as in scene parsing of natural scene images, we can solve the aforementioned problems through the integration of auxiliary data into HRAIs. To this end, we propose a multiscale cross-layer interactive and similarity refinement network (MISNet) for scene parsing of HRAIs. First, in a feature fusion optimization module, we extract, filter, and optimize multisource features and further guide and optimize the features using a feature guidance module. Second, a multiscale context aggregation module increases the receptive field, captures semantic information, and extracts rich multiscale background features. Third, a dense decoding module fuses the global guidance information and high-level fused features. We also propose a joint learning method based on feature similarity and a joint learning module to obtain deep multilevel information, enhance feature generation, and fuse multiscale and global features to enhance network representation for accurate scene parsing of HRAIs. Comprehensive experiments on two benchmark HRAIs datasets indicate that our proposed MISNet is qualitatively and quantitatively superior to similar state-of-the-art models.

Hierarchical Belief Propagation on Image Segmentation Pyramid.

The Markov random field (MRF) for stereo matching can be solved using belief propagation (BP). However, the solution space grows significantly with the introduction of high-resolution stereo images and 3D plane labels, making the traditional BP algorithms impractical in inference time and convergence.We present an accurate and efficient hierarchical BP framework using the representation of the image segmentation pyramid (ISP). The pixel-level MRF can be solved by a top-down inference on the ISP. We design a hierarchy of MRF networks using the graph of superpixels at each ISP level. From the highest/image to the lowest/pixel level, the MRF models can be efficiently inferred with constant global guidance using the optimal labels of the previous level. The large texture-less regions can be handled effectively by the MRF model on a high level. The advanced 3D continuous labels and a novel support-points regularization are integrated into our framework for stereo matching. We provide a data-level parallelism implementation which is orders of magnitude faster than the best graph cuts (GC) algorithm. The proposed framework, HBP-ISP, outperforms the best GC algorithm on the Middlebury stereo matching benchmark.

Global guidance for the recognition, diagnosis, and management of tumor-induced osteomalacia.

Tumor-induced osteomalacia (TIO) is a rare paraneoplastic syndrome caused by mesenchymal tumors that secrete fibroblast growth factor 23 (FGF23). Patients present with progressive bone pain, muscle weakness, and fragility fractures. TIO is characterized by hypophosphatemia, excess renal phosphate excretion, and low/inappropriately normal 1,25-dihydroxyvitamin D (1,25(OH)2 D) levels. Rarity and enigmatic clinical presentation of TIO contribute to limited awareness among the medical community. Accordingly, appropriate diagnostic tests may not be requested, leading to delayed diagnosis and poorer patient outcomes. We have developed a global guidance document to improve the knowledge of TIO in the medical community, enabling the recognition of patients with TIO and appropriate referral. We provide recommendations aiding diagnosis, referral, and treatment, helping promote a global standard of patient management. We reviewed the literature and conducted a three-round Delphi survey of TIO experts. Statements were drafted based on published evidence and expert opinions (≥70% consensus required for final recommendations). Serum phosphate should be measured in patients presenting with chronic muscle pain or weakness, fragility fractures, or bone pain. Physical examination should establish features of myopathy and identify masses that could be causative tumors. Priority laboratory evaluations should include urine/serum phosphate and creatinine to assess renal tubular reabsorption of phosphate and TmP/GFR, alkaline phosphatase, parathyroid hormone, 25-hydroxyvitamin D, 1,25(OH)2 D, and FGF23. Patients with the clinical/biochemical suspicion of TIO should be referred to a specialist for diagnosis confirmation, and functional imaging should be used to localize causative tumor(s). Recommended treatment is tumor resection or, with unresectable/unidentifiable tumors, phosphate salts plus active vitamin D, or burosumab.

Environmental effects of surgical procedures and strategies for sustainable surgery.

There is a bidirectional relationship between climate change and health care. Climate change threatens public health, and health care contributes to climate change. For example, surgery is the most energy-intensive practice in the health-care sector, and gastrointestinal conditions are responsible for a substantial environmental burden. However, environmental costs associated with health care are often overlooked. This issue has been examined more closely in current times. Emerging data are mainly focused on surgery, as the most resource-intensive practice. However, there is still a lack of global awareness and guidance on sustainable surgical practices. This Perspective aims to reassess the evidence on health care and surgery carbon footprints, focusing on gastrointestinal conditions, identify issues that need to be addressed to achieve a more sustainable practice and develop perspectives for future surgical procedures. The proposed framework to mitigate the environmental effects of surgery could be translated to other health-care sectors.

BANet: Boundary-Assistant Encoder-Decoder Network for Semantic Segmentation

Recently, boundary information has gained great attraction for semantic segmentation. This paper presents a novel encoder-decoder network, called BANet, for accurate semantic segmentation, where boundary information is employed as an additional assistance for producing more consistent segmentation outputs. BANet is composed of three components: the pre-trained backbone using dilated-ResNet101, semantic flow branch (SFB) and boundary flow branch (BFB) for semantic segmentation and boundary detection, respectively. More specifically, to delineate more accurate object shapes and boundaries, a global attention block (GAB) is designed in SFB as global guidance for high-level feature. On the other hand, BFB directly extracts features on boundaries, avoiding the unexpected interference from the non-boundary parts. Finally, we adopt a joint loss function to further optimize the segmentation results and boundary outputs synchronously. Moreover, compared with previous state-of-the-art methods, e.g., non-local block and ASPP module, our BFB leverages detection accuracy and computational efficiency in a lightweight fashion. To evaluate BANet, we have conducted extensive experiments on several semantic segmentation datasets: Cityscapes, PASCAL Context, and ADE20K. The experimental results show that, with the aid of boundary information, BANet is able to produce more consistent segmentation predictions with accurately delineated object shapes and boundaries, leading to the state-of-the-art performance on Cityscapes, and competitive results on PASCAL Context and ADE20K with respect to recent semantic segmentation networks.

Improved Dyna-Q: A Reinforcement Learning Method Focused via Heuristic Graph for AGV Path Planning in Dynamic Environments

Dyna-Q is a reinforcement learning method widely used in AGV path planning. However, in large complex dynamic environments, due to the sparse reward function of Dyna-Q and the large searching space, this method has the problems of low search efficiency, slow convergence speed, and even inability to converge, which seriously reduces the performance and practicability of it. To solve these problems, this paper proposes an Improved Dyna-Q algorithm for AGV path planning in large complex dynamic environments. First, to solve the problem of the large search space, this paper proposes a global path guidance mechanism based on heuristic graph, which can effectively reduce the path search space and, thus, improve the efficiency of obtaining the optimal path. Second, to solve the problem of the sparse reward function in Dyna-Q, this paper proposes a novel dynamic reward function and an action selection method based on the heuristic graph, which can provide more intensive feedback and more efficient action decision for AGV path planning, effectively improving the convergence of the algorithm. We evaluated our approach in scenarios with static obstacles and dynamic obstacles. The experimental results show that the proposed algorithm can obtain better paths more efficiently than other reinforcement-learning-based methods including the classical Q-Learning and the Dyna-Q algorithms.

Using Stochastically Perturbed Parameterizations to Represent Model Uncertainty. Part II: Comparison with Existing Techniques in an Operational Ensemble

Abstract The ability of a stochastically perturbed parameterization (SPP) approach to represent uncertainties in the model component of the Canadian Global Ensemble Prediction System was demonstrated in Part I of this investigation. The goal of this second step in SPP evaluation is to determine whether the scheme represents a viable alternative to the current operational combination of a multiphysics configuration and stochastically perturbed parameterization tendencies (SPPT). An assessment of the impact of each model uncertainty estimate in isolation reveals that, although the multiphysics configuration is highly effective at generating ensemble spread, it is often the result of differing biases rather than a reflection of flow-dependent error growth. Moreover, some of the members of the multiphysics ensemble suffer from large errors on regional scales as a result of suboptimal configurations. The SPP scheme generates a greater diversity of member solutions than the SPPT scheme in isolation, and it has an impact on forecast performance that is similar to that of current operational uncertainty estimates. When the SPP framework is combined with recent upgrades to the model physics suite that are only applicable in the stochastic perturbation context, the quality of global ensemble guidance is significantly improved. Significance Statement The stochastically perturbed parameterization (SPP) technique was introduced in Part I to represent model uncertainties in forecasts generated by an operational global ensemble prediction system. We focus here on the viability of this technique as a replacement for the system’s current uncertainty estimates: multiphysics and stochastic perturbations of physics tendencies. Despite the practical success of this combination, it suffers from physical inconsistencies and poor conservation properties. The adoption of SPP allows the ensemble to benefit from a recent set of model updates that couple with this new representation of model uncertainty to yield significant improvements in the quality of forecasts generated by the system.

Challenges and response to pandemics as seen in a One Health perspective

The global pandemic caused by the coronavirus disease 2019 not only exposed the fragility of global preparedness and response to public health emergence, but also illustrated the fragmentation and gaps of research and development ecosystem. This emphasizes the need for planned actions against the potentiality of new pandemics and requires research to better understand how viruses bridge the animal/human divide making human-to-human transmission of new diseases possible. Major challenges to response to new epidemics under the current health framework reside in the so called 4-CC approach that focuses on Concept, Communication, Coherence, and Continuity. There is a need to also add a One Health perspective with emphasis on governance, surveillance, capacity building and multi-disciplinary research to achieve a holistic and better integrated system. Using a regulatory framework to equip professionals might facilitate the function of a multi-sector approach that recognizes the value of their mandates and a One Health approach in their work. Collaborative, multisectoral actions under the global regulations and guidance would make evidence-based One Health approaches sustainable and accessible to everyone.

Novel automated spinal ultrasound segmentation approach for scoliosis visualization.

Scoliosis is a 3D deformity of the spine in which one or more segments of the spine curve laterally, usually with rotation of the vertebral body. Generally, having a Cobb angle (Cobb) greater than 10° can be considered scoliosis. In spine imaging, reliable and accurate identification and segmentation of bony features are crucial for scoliosis assessment, disease diagnosis, and treatment planning. Compared with commonly used X-ray detection methods, ultrasound has received extensive attention from researchers in the past years because of its lack of radiation, high real-time performance, and low price. On the basis of our previous research on spinal ultrasound imaging, this work combines artificial intelligence methods to create a new spine ultrasound image segmentation model called ultrasound global guidance block network (UGBNet), which provides a completely automatic and reliable spine segmentation and scoliosis visualization approach. Our network incorporates a global guidance block module that integrates spatial and channel attention, through which long-range feature dependencies and contextual scale information are learned. We evaluate the performance of the proposed model in semantic segmentation on spinal ultrasound datasets through extensive experiments with several classical learning segmentation methods, such as UNet. Results show that our method performs better than other approaches. Our UGBNet significantly improves segmentation precision, which can reach 74.2% on the evaluation metric of the Dice score.

Global public health must end the neglect of oral health

Abstract Oral diseases are among the most common health problems and constitute major public health challenges across countries and health systems worldwide. The main diseases dental caries, severe periodontal disease, oral cancer and toothlessness affect populations everywhere and show significant social gradients - poor, disadvantaged, rural, or otherwise vulnerable groups suffer from a much higher burden, while at the same time having more difficulties to access prevention and care. Similarly, low- and middle-income countries have the highest prevalence of oral diseases while their healthcare systems are ill-equipped to address the challenges. Due to the predominant clinical care model of dentistry that favours an interventionist approach requiring costly technology provided by a dentist, many health systems and large population segments are not able to afford even basic oral health care. Moreover, oral health has been largely absent from the global health arena for the last 20 years leading to faltering political priority and attention. This has changed recently with the convergence of several initiatives of global relevance, supported by advocacy of the wider oral health community. Following the first ever paper series on oral health in The Lancet, a Lancet Commission on Oral Health was established in 2019, which sparked a group of WHO member states to embark on a remarkable policy development process dedicated to oral health. We now have a Global Strategy for Oral Health and will soon have a Global Action Plan complemented by a comprehensive Monitoring Framework. In addition, work on defining Best Buys in Oral Health and other supportive workstreams are under way. The presentation will provide an introduction and overview to these global policy guidance frameworks that are shaping a new reform agenda for oral health as part of NCDs, Universal Health Coverage and the SDGs towards 2030. Particular implications for public oral health in Europe will be discussed.