3D Modeling Optimization with Artificial Intelligence

The research relevance is determined by the importance of a thorough study of methods, schemes and models used by artificial intelligence to mechanise creativity in modern conditions of active technological development. The study aims to analyse the main processes taking place in modern art in connection with active technologization of work processes, to identify the leading concepts regarding the possibility of creating machine art in the future, etc. The employed methods are theoretical, such as analysis, systematisation, generalisation, etc., for studying key problems and further development of creativity based on artificial intelligence. The study examines in detail the main developments of Artificial General Intelligence and Artificial Narrow Intelligence, in particular the achievements of Generative adversarial networks and Creative adversarial networks. Artificial intelligence-generated art demonstrates the remarkable capabilities of technologies. The evolving artificial intelligence in the arts introduces “digital art”. Generative Adversarial Networks are used as a foundational tool for artists who use digital methods and texture generation to create unique compositions. Furthermore, sculptors collaborate with artificial intelligence tools to convert drawings into 3D models or transform historical art databases into sculptures. Creative thinking, a hallmark of human intelligence, is determined as artificial intelligence’s ability to generate new and original ideas. The development of emotional intelligence in artificial intelligence enables empathetic responses and the identification of human emotions through voice and facial expressions. The issues of authorised internationality, awareness of the creative process, psychological foundations of artificial empathy and emotional intelligence define the prospects for the development of neuroscience. Challenges persist in defining creativity, authorship, and legal aspects of artificial intelligence-generated art. The study materials may be useful for artists, art educators, technologists, and researchers interested in the intersection of technology and art, legal professionals (especially intellectual property law), and individuals involved in artificial intelligence development may find these findings valuable

The research relevance is determined by the importance of a thorough study of methods, schemes and models used by artificial intelligence to mechanise creativity in modern conditions of active technological development. The study aims to analyse the main processes taking place in modern art in connection with active technologization of work processes, to identify the leading concepts regarding the possibility of creating machine art in the future, etc. The employed methods are theoretical, such as analysis, systematisation, generalisation, etc., for studying key problems and further development of creativity based on artificial intelligence. The study examines in detail the main developments of Artificial General Intelligence and Artificial Narrow Intelligence, in particular the achievements of Generative adversarial networks and Creative adversarial networks. Artificial intelligence-generated art demonstrates the remarkable capabilities of technologies. The evolving artificial intelligence in the arts introduces “digital art”. Generative Adversarial Networks are used as a foundational tool for artists who use digital methods and texture generation to create unique compositions. Furthermore, sculptors collaborate with artificial intelligence tools to convert drawings into 3D models or transform historical art databases into sculptures. Creative thinking, a hallmark of human intelligence, is determined as artificial intelligence’s ability to generate new and original ideas. The development of emotional intelligence in artificial intelligence enables empathetic responses and the identification of human emotions through voice and facial expressions. The issues of authorised internationality, awareness of the creative process, psychological foundations of artificial empathy and emotional intelligence define the prospects for the development of neuroscience. Challenges persist in defining creativity, authorship, and legal aspects of artificial intelligence-generated art. The study materials may be useful for artists, art educators, technologists, and researchers interested in the intersection of technology and art, legal professionals (especially intellectual property law), and individuals involved in artificial intelligence development may find these findings valuable

Engineering, Procurement, and Construction (EPC) projects rely heavily on detailed engineering data and accurate 3D models. Artificial Intelligence (AI) opportunities offer a transformative vision for this process, promising automation, optimization, and improved collaboration. Also, AI is being developed to build 3D models of process plants with multiple design scenarios augmenting human knowledge. However, integrating AI in FEED Engineering workflows comes with several challenges: Integration and collaboration of data: EPC projects involve numerous stakeholders with diverse data formats and software tools. Ensuring seamless data exchange and interoperability between AI-powered modelling platforms and existing software used by engineers, designers, and fabricators is crucial for such integration.Engineering Data Quality: AI models need to be trained on data that reflects specific engineering design requirements, codes and design practices relevant to each EPC project or process package. As part of this challenge is validation and verification of data. The complex nature of EPC projects necessitates robust validation processes to ensure the accuracy and efficiency of AI-generated models.The AI "black box": Capturing the design intent of specific design and modelling options or decisions is crucial for EPC projects. The "black box" nature of some AI algorithms can make it difficult to understand the rationale behind generated designs or gain support from engineering organizations for company wide deployment.Cultural Resistance to AI: Cultural resistance to AI solutions stems from hesitation, scepticism, or outright opposition that some individuals or groups within an organization may have towards adopting and implementing Artificial Intelligence (AI) technologies. This paper seeks to raise awareness of the challenges recognized by current literature in the industry and discuss opportunities for implementing AI solutions when developing 3D models for FEED projects. This paper will also propose best practices for harnessing the strengths of AI to optimize its benefits. The following key areas are discussed as AI opportunities on EPC projects during 3D modelling in FEED: Data Quality, Integration and Standardization: Ensure data used to train AI models is accurate, reliable and follows standardised formats throughout the EPC project lifecycle for seamless data exchange. Inconsistent data can lead to unreliable AI outcomes.Verification and Validation: Develop robust verification and validation processes to ensure the accuracy, quality, safety, and constructability of AI-generated 3D models.Integration of human knowledge and AI tools: While AI automates tasks, human expertise remains crucial. Integrate human oversight throughout the process for design intent capture, validation of AI outputs, and final decision-making.Develop Human skills: The effective use of AI in EPC projects requires a workforce with a blend of engineering expertise and AI skills. Developing an AI culture within the organization and investing in training programs that embraces human-AI collaboration is critical. By implementing the AI opportunities outlined in this paper, EPC projects can harness the advantages of AI to enhance efficiency, reduce costs, and improve project outcomes. Engineering firms should also focus on empowering and developing their employees with AI skills to foster collaboration between human expertise and AI tools, while addressing the cultural concerns surrounding job security. AI has the potential to serve as a powerful tool for automation, optimization, and collaboration of data during the full project lifecycle, revolutionizing the design and construction of complex engineering projects.

The operating theatre is a complex busy environment. Many anaesthetists learn how to deal with this and the data they must interpret at an almost subliminal level; their hearing becomes accustomed to the falling and rising of the tone of a pulse oximeter, the skip of a missed beat on the ECG, their eyes quickly take in the nature of the end-tidal carbon dioxide curve changing as respiratory mechanics alter chest wall and lung compliance and the increasing respiratory swing in a pulse pressure waveform signifying hypovolaemia. The psychologist James T. Reason has suggested that human rather than technical failures represent the greatest threat to complex and potentially hazardous systems, including healthcare 1. Any system that can help a clinician to interpret complex variables effectively and rapidly, allowing them to initiate interventions accurately, is always going to be welcome. Viscoelastic testing for assessing coagulation in peri-operative bleeding and haemostasis has been available for over 30 years 2. The thromboelastograph (TEG®, Haemonetics Corporation, Braintree, MA, USA) and rotational thromboelastometer (ROTEM® Instrumentation Laboratory, Bedford, MA, USA) are well-established monitoring devices for use in measuring clot formation, clot strength and component deficiency in many types of surgery including liver transplantation 3, trauma 4, obstetrics 5 and cardiothoracic surgery 6. Historically, these devices have presented their output in a two-dimensional screen drawn with respect to time. Although there has been some debate as to whether use of these devices is associated with improvements in patient-centred outcomes 7, it is clear their use does lead to reductions in red cell and platelet transfusion 7, 8. The devices are not naturally intuitive to use; although the newer devices are cartridge based, therefore reducing the capacity for user error, they still require training in their interpretation. Peri-operative bleeding is a complex state that can arise owing to surgical mishap as well as coagulopathies caused by plasma factor deficiencies, platelet deficiency or dysfunction, fibrinogen deficiency or lysis. It is often difficult for the clinician to tease out the cause of bleeding and treat appropriately. The accurate interpretation of viscoelastic tests requires an understanding of the clotting cascade as a dynamic process as well as the factors that can interact to produce a coagulopathic state. Learning the interpretation of viscoelastic tests and the appropriate action is a skill set that takes much training and continued practice. In this issue of Anaesthesia, Rössler et al. report a novel way of presenting complex haemostatic information with a three-dimensional model. This incorporates multiple variables in one place 9 and simplifies a complex process. Three-dimensional (3D) models have been used in anatomical training in medical schools to great effect 10 as well as in postgraduate education especially in concepts which are difficult to comprehend such as congenital heart disease. 11 Patient-specific 3D models are used when planning difficult surgery 12. It has been shown that the ability to extract information when presented as a visual model is diagnostically more accurate and rapid and can lead to less inter-individual variability in the interpretation of the same data. The model described by Rössler et al. is easily understood and interpretable. It has been shown to be more reliable and reproducible in a group of clinicians, when compared with the current methods of displaying the traces. Understanding by the human brain is improved by adding a third dimension and motion to the process. As the investigators show, they were able to get a more accurate, reliable and reproducible interpretation of the data by clinicians, allowing them to act upon it earlier. This has the potential to help clinicians who are less experienced and less familiar with these point-of-care tests. If these devices could be combined with physiological data and projected on heads-up augmented reality displays while the anaesthetist is assessing the surgical situation it could aid rapid treatment and become a genuine advance in patient safety. This novel technology may also allow tests to be used in previously unrealised situations such as military and pre-hospital care and by less expert trainees using artificial intelligence (AI)-assisted machine learning technologies. Like any new interpretation, the model requires further evaluation and ergonomic assessment. In particular, evaluation using clinical data derived from patients should be performed; data which are not as clear cut as the ROTEM-produced data used in the study by Rössler et al. It should be investigated to see whether in the real-world it remains easier to interpret. The model from Rössler et al. should be seen as the first step towards using technology in point-of-care coagulation testing. The natural next progression from the 3D model may well involve the use of artificial intelligence. Machine-based learning (the use of algorithms in computers so that they collect data and learn from them, such as customer recommendations on shopping websites) and deep learning (using complex algorithms to mimic the neural network of the human brain, such as voice recognition) within AI are rapidly growing fields in medicine. They are already used to help with the interpretation of ECGs with diagnostic accuracy, in robotic surgery and the use of 3D-augmented reality glasses for minimally invasive surgery. These advances aim to support doctors’ decision-making rather than replacing them. Similar to how doctors are educated through years of medical school, reading, doing practical exams and learning from mistakes, AI algorithms must also learn how to do their jobs. Usually AI algorithms are designed to complete tasks that need human intelligence, such as pattern and speech recognition, image analysis and decision-making. It is almost impossible to write a computer programme that will be clever; instead with AI they are programmed to learn from experience. However, people need to tell the computer exactly what they would look for in the image, for example, which parts of the TEG trace are more important. These artificial neural networks are digitised models of the human brain and are able to process incomplete and uncertain information, use logic to aid predictive diagnoses and use deep learning techniques to use the enormous amounts of data which are now generated. If they are fed enough data, they are likely to work, and to work better than clinicians alone. In order to generate an effective AI algorithm, computer systems are first fed patient data, for example, coagulation abnormalities and their treatment. After enough data have been entered, the algorithm is tested and the performance is analysed to ensure accuracy. These algorithm ‘exams’ generally involve the input of test data to which programmers already know the answers, allowing them to assess the algorithm's ability to determine the correct answer. Based on the testing results, the algorithm can be modified, fed more data or rolled out to help make decisions for the person who wrote the algorithm. The use of more visual conceptualisation of data which are difficult to understand may well be overtaken by the use of these AI algorithms which advise doctors on management based on hundreds of thousands of previous examples. Artificial intelligence is already gaining credence in anaesthesia. Studies have shown machine learning used to predict bispectral index (BIS) values from target-controlled propofol and remifentanil infusions 13, mortality from electronic health data 14 and hypotension during induction of anaesthesia 15. Very recently, Google demonstrated for the very first time that AI-read radiographs are non-inferior to clinician-read images for diagnosing breast cancer 16. Google's machine learning software, the TensorFlow™ (Google Inc., CA, USA), is used to help diagnose diabetic retinopathy, using deep learning to compare images of the retina to ones it has ‘seen’ before ( http://futurefriend.ly/health/14057/artificial-intelligence-in-medicine-how-tensorflow-is-used – accessed 04/02/2020). IBM's Watson™ for Health (IBM, NY, USA) can review and store medical information – journals, symptoms, case studies and responses to treatment – and use this information to help clinicians make decisions, quickly and using all the available information ( https://www.ibm.com/watson-health – accessed 20/01/2020). Researchers in the USA describe promising work using AI in risk prediction and more recently in tumour diagnosis ( https://labblog.uofmhealth.org/health-tech/artificial-intelligence-improves-brain-tumor-diagnosis – accessed 21/01/2020). The natural next step for management of coagulopathy pre-operatively may well be in using AI. As the use of machine-based and deep learning becomes more reliable and responsive, it may lead to more rapid and effective assisted clinical decision-making leading to earlier and diagnostically more accurate interventions. The work of Rössler et al. may well be the start of a brave new world in peri-operative coagulation testing with AI allowing a transition from evidence-based medicine to personalised medicine. However, as with all new technologies, we must remain aware of the limitations of the devices as well as their possible advantages in guiding clinical therapy. Spurious conclusions can be drawn from the use of big data and, as the consequences for mistakes in anaesthesia can be huge, the AI used must be near perfect. Clinicians may well have to learn about how these machine learning models are designed, much in the way that a basic knowledge of statistics is needed to read a scientific paper, multidisciplinary guidelines will need to be written and followed. We must also answer the crucial question of whose responsibility it is to ensure the AI performs as expected and who will be responsible if the doctor, taking the advice of AI, makes a costly mistake. Artificial intelligence is beginning to make forays into peri-operative medicine. The interpretation of point-of-care tests is amenable to analysis by AI to direct appropriate treatment of bleeding. In our opinion, AI offers the potential to assist the clinician in the rapid and accurate diagnosis of bleeding. Previously point-of-care tests have not been embedded into widespread clinical practice in part due to reluctance by infrequent users who lack confidence in their use. The new generation of cartridge-based systems have taken away much of the practical concerns; AI may take away concerns with their interpretation. As clinicians, we should embrace the introduction of AI into our arena. Just as robotic surgery is allowing pioneering work to be undertaken simultaneously by surgeons who may be in different parts of the world, in anaesthetics and critical care AI opens up the possibility of consulting specialists around the world. The personalisation of closed loop anaesthetic delivery systems utilising physiological data for maintenance of anaesthesia or in the control of blood pressure, heart rate, fluid loading and volume resuscitation is a distinct probability in an interesting automated future. Artificial intelligence has the potential to help us reduce our work-load and be faster and smarter; we must work with the technology companies to ensure it does so. SA in an editor of Anaesthesia and has received research funding and/or honoraria from Haemonetics, Pharmacosmos, Nordic and Octapharma. AA has received research funding and/or honoraria from Haemonetics, Nordic, Hemosonics, Medtronic and Masimo. No other competing interests declared.

Artificial intelligence (AI) has the potential to expand the role of chest imaging in COVID-19 beyond diagnosis to enable risk stratification, treatment monitoring, and discovery of novel therapeutic targets. AI’s power to generate models from large volumes of information – fusing molecular, clinical, epidemiological, and imaging data – may accelerate solutions to detect, contain, and treat COVID-19.

The development of Artificial Intelligence (AI), especially Machine Learning (ML) technology, has injected new vitality into the geospatial domain. Training Data (TD) plays a fundamental role in geospatial AI/ML. They are key items for training, validating, and testing AI/ML models. At present, open access Training Datasets (TDS) are usually packaged into public or personal file repository, without a standardized method to express its metadata and data content, making it difficult to be found, accessed, interoperated, and reused.Therefore, based on the Open Geospatial Consortium (OGC) standards baseline, the OGC Training Data Markup Language for AI (TrainingDML-AI) Standard Working Group (SWG) tried to develop the TD model and encoding methods to exchange and retrieve TD in the Web environment. The scope includes: how TD are prepared, how to specify different metadata used for different AI/ML tasks, how to differentiate the high-level TD information model and extended information models specific to various AI/ML applications. The work will describe the latest progress and status of the standard development.The TrainingDML-AI conceptual model includes the most relevant entities of the TD covering from dataset to individual training samples and labels. It specifies how and into which parts of the TD should be decomposed and classified. The core concepts include: AI_TrainingDataset, which represents a collection of training samples; AI_TrainingData, which is an individual training sample in a TDS; AI_Task, which identifies what task the TDS is used for; AI_Label, which represents the label semantics for TD; AI_Labeling, which provides the provenance for the TD; AI_TDChangeset, which records TD changes between two TDS versions; DataQuality, which can be associated with the TDS to document its quality.The TrainingDML-AI content model focuses on implementations with basic attributes defined for off-the-shelf deployment. Concepts related to the EO AI/ML applications are defined as additional elements. Six key components are highlighted:Training Dataset/Data. AI_AbstractTrainingDataset indicates the TDS, while each training sample is represented as AI_AbstractTrainingData. AI_EOTrainingDataset and AI_EOTrainingData are defined to convey attributes specific to EO domain. AI_EOTask is proposed by extending AI_AbstractTask to represent specific AI/ML tasks in the EO domain. The task type can refer to a particular type defined by an external category. Labels for each individual training sample can be represented using features, coverages, or semantic classes. The AI_AbstractLabel is extended to specify AI_SceneLabel, AI_ObjectLabel, and AI_PixelLabel respectively. AI_Labeling records basic provenance information on how to create the TDS. It includes the labeler and labeling procedure, which can be mapped to the agent and activity respectively in W3C PROV. DataQuality and QualityElements defined in the ISO 19157-1 are used to align with the existing efforts on geographic data quality. Change procedures of the TDS are documented in the AI_TDChangeset, which composes of changed training samples in the collection level. Finally, use case scenarios and best practices are provided to illustrate intended use and benefits of TrainingDML-AI for EO AI/ML applications. Totally five different tasks are provided, covering scene classification, object detection, semantic segmentation, change detection and 3D model reconstruction. Some software implementations including pyTDML and LuojiaSet are also presented.

Purpose The purpose of the study was to investigate the effects of artificial intelligence (A.I.) awareness, advertisement models and source-message incongruence on consumer evaluations of A.I.-generated advertisements. It explores how these factors interact in shaping consumer perceptions and advertising effectiveness. Design/methodology/approach A 2 (source-message (in)congruence: incongruent vs. congruent) x 3 (A.I. awareness: unawareness, pre-advertisement, post-advertisement) x 3 (advertisement model: traditional human, virtual human, digital twin) between-subjects design was employed in this study. Using stratified random sampling, a total of 231 undergraduate students were recruited from course groups and randomly assigned to one of nine experimental treatments, each involving the viewing of a specific A.I.-generated advertisement followed by a survey. Data were analyzed using two-way ANCOVA and regression analyses, controlling for participants' involvement in sports and brand. Findings The results indicated that A.I. awareness timing, advertisement model types and source-message incongruence significantly affected consumer evaluations of advertisements. A.I. awareness generally had a positive impact on evaluations, with the most favorable outcomes when awareness of the A.I.-generated nature occurred after viewing the advertisement. Virtual human models were rated the lowest, while digital twin and traditional human models received similarly positive evaluations. Source-message incongruence negatively influenced evaluations. An interaction effect was observed between A.I. awareness timing and advertisement model types under high source-message incongruence, where virtual human models showed the highest effectiveness when A.I. awareness occurred after viewing. Originality/value Given that sports are characterized by the transcendence of human limitations and the emphasis on physical and emotional challenges – elements that A.I. cannot replicate – it is essential to examine how sports consumers perceive A.I., which, despite offering efficiency and personalization advantages, contrasts with the fundamentally human nature of athletic performance. This research contributes to the literature on A.I.-generated advertising by uniquely investigating the interaction between A.I. awareness timing and advertisement model types within the context of source-message incongruence. It offers critical insights for practitioners and researchers on strategically timing A.I.-generated ad disclosures and selecting appropriate advertisement models to optimize their effectiveness. By addressing these underexplored variables, the study enhances understanding of consumer perceptions and provides a foundation for more effective A.I. integration in advertising practices.

<div class="section abstract"><div class="htmlview paragraph">Artificial Intelligence (AI) is currently regarded as the foremost technology for automating routine and repetitive tasks, leading to increased productivity. However, the quality of creative and design work with AI remains questionable. This paper presents a quantitative analysis of AI productivity through dynamic simulation and assesses the quality of AI results in the diameter calculation and construction of a 3D model of an engine piston as a case study. To evaluate productivity, the dynamic model segregates design tasks based on AI working hours. The quality of the formulation for calculating the engine piston diameter, derived from engine requirements, is compared with a standard formulation from a literature review. Additionally, the 3D model generated by AI is compared with a model created by human intelligence in Computer-Aided Design (CAD) software, reflecting the characteristics and properties of real engine pistons. While research on AI productivity is abundant, few studies address the quality and usefulness of AI-generated results. This study aims to evaluate these three aspects. As anticipated, the AI in a simulation model demonstrates a numerical increase in productivity as an enhancing variable. However, results for a design process involving mathematical formulation and 3D model construction lack utility without additional work. Our findings lead us to conclude that AI in the design process can enhance productivity when used to suggest and predict design instructions, thereby saving time. Nevertheless, the AI's ability to create mathematical and 3D models is limited to simplified conditions, and further knowledge must be imparted to the AI to enable it to produce readily usable designed components.</div></div>

This paper presents a theoretical framework for the implementation of Artificial Intelligence (AI) in architectural and structural design processes, and it is complemented by some practical applications. The aim is to demonstrate that AI can be used to simulate certain aspects of human cognition and can therefore be integrated into CAD software to support conceptual design and idea generation in a number of different ways. The aim of this study is also to investigate to what extent AI models can interact with a designer to explore future forms of human–machine interaction, including autonomous and participative design. This study identifies and applies AI models to simulate three distinct learning mechanisms: design expertise, playfulness and analogical reasoning. Each strategy has been applied to train different AI models, including generative models and reinforcement learning agents. In the first application, the AI model extracts visual features from a dataset of shell and spatial structures, and then recombines such features to generate new design propositions. In the second application, an AI agent learns a design strategy to solve a toy-design problem with no prior knowledge of precedents. The third application illustrates that AI can be trained to discover meaningful features from biological forms and generate simple design objects through the visual abstraction of such forms. The applications demonstrate the ability of AI to synthesise design options and interact with a designer through visual data formats, such as 2D images and 3D models. This work does not focus on assessing the usefulness of AI models in a real-world design scenario, or on comparing AI with current computational design tools and approaches. It instead investigates different forms of design exploration for computational design purposes, thus paving the way for the development of future autonomous and participative design systems.

Background: Musculoskeletal (MSK) medicine has undergone a rapid transformation in recent years, with artificial intelligence (AI) emerging as a key driver of innovation. Existing literature has predominantly explored AI in diagnostic imaging, predictive analytics, and Natural Language Processing for clinical decision support. While several studies have touched upon AI’s potential in medical education, there remains limited evidence specifically evaluating its role in MSK teaching, the pedagogical outcomes, and integration into established curricula. This gap is critical given the changing dynamics of healthcare delivery, the need for scalable training solutions, and the increasing emphasis on personalised, technology-driven learning. The current work addresses this shortfall by synthesising recent evidence and examining how AI-based tools can enhance MSK education. Methods: A comprehensive literature search (2018–2025) was conducted across PubMed, Scopus, and Web of Science using predefined keywords relating to AI and MSK teaching. Eligible studies were peer-reviewed articles, case studies, and trials in English that met specific inclusion criteria. From the 342 screened articles, 43 were selected for detailed analysis. Data extraction focused on AI applications in MSK training, reported benefits, limitations, and integration strategies. Non-peer-reviewed and opinion-based sources were excluded. Inclusion criteria: Peer-reviewed articles, case studies, and trials published in English between January 2018 and 2025, focusing on AI applications in MSK education among healthcare professionals in training. Both qualitative and quantitative studies were included. Exclusion criteria: Non-peer-reviewed articles, editorials, opinion pieces without empirical evidence, studies on non-human/animal subjects, and studies unrelated to AI or MSK systems. Results: The literature reveals that AI has enhanced MSK training through immersive technologies such as 3D modelling, augmented reality (AR), and virtual reality (VR). These innovations reduce reliance on traditional cadaveric and apprenticeship-based models, offering cost-effective, scalable, and interactive learning. AI-driven platforms facilitate personalised case-based learning, improve diagnostic accuracy, and support tailored intervention planning. However, significant challenges remain—most notably, limited longitudinal data on educational outcomes, barriers to large-scale adoption (cost, infrastructure), data privacy concerns, and the absence of standardised frameworks for integrating AI into formal MSK curricula. Conclusion: While AI shows considerable promise in transforming MSK teaching, the field lacks robust, outcome-focused research to guide evidence-based adoption. Addressing these gaps through targeted studies, standardisation of teaching protocols, and blended integration with conventional training will be essential to realising AI’s full potential in enhancing both learner competence and patient care outcomes.

The integration of artificial intelligence (AI) into medical practices has transformed fields like gastroenterological surgery. AI predicts patient prognoses using clinical and pathological data and develops technologies that create three-dimensional (3D) models for surgical simulations, thereby enhancing surgical precision and care quality. At our facility, AI-driven diagnostic and treatment systems have been developed under the "Strategic Innovation Creation Program" by the Cabinet Office. Our research focuses on perioperative care by constructing 3D models from preoperative imaging data to develop surgical support systems for preoperative simulations and navigation during surgery. Additionally, we use deep learning to predict disease progression and complications and natural language processing to analyze electronic medical records to predict postoperative complications. AI-based surgical support systems effectively convert two-dimensional imaging data into 3D models, thereby improving surgical precision. Predictive models for disease progression and complications developed using deep learning have high accuracy. AI applications in diagnostic imaging enable early detection and improved treatment planning. AI-based tools for informed consent and patient support enhance patient understanding and satisfaction. AI revolutionizes medical practices by improving diagnostic accuracy, surgical precision, and patient outcomes. Future projects will integrate remote diagnostic and treatment planning; leverage AI for comprehensive, high-quality care; and support work-style reforms for healthcare professionals. Advancements in AI will overcome current medical challenges and enhance the communication between physicians and patients.

<p>This study conducts an empirical exploration of generative Artificial Intelligence (AI) tools across the game development pipeline, from concept art creation to 3D model integration in a game engine. Employing AI generators like Leonardo AI, Scenario AI, Alpha 3D, and Luma AI, the research investigates their application in generating game assets. The process, documented in a diary-like format, ranges from producing concept art using fantasy game prompts to optimizing 3D models in Blender and applying them in Unreal Engine 5. The findings highlight the potential of AI to enhance the conceptualization phase and identify challenges in producing optimized, high-quality 3D models suitable for game development. This study reveals the current limitations and ethical considerations of AI in game design, suggesting that while generative AI tools hold significant promise for transforming game development, their full integration depends on overcoming these hurdles and gaining broader industry acceptance.<strong></strong></p>

Introduction The growing influence of artificial intelligence (AI) in medicine has extended to the field of robotic urology, holding the promise of enhancing diagnostic precision, patient safety, and overall efficiency in surgical procedures. This study aims to explore the current state of AI in robotic urology and its potential applications. Method A systematic review was conducted on AI utilization in robotic urology, encompassing relevant articles published from 2015 to 2022. Databases including PubMed, Scopus, and Web of Science were searched for studies focusing on AI's role in procedures like prostatectomy, nephrectomy, and cystectomy. Results The review revealed significant strides in integrating AI within robotic urology across three key domains:Image Guidance: AI enhances tumour identification and targeting during robot-assisted surgeries, minimizing errors and improving surgical outcomes.Surgical Planning: AI aids in creating 3D patient anatomical models, facilitating pre-surgery planning, and reducing operation time.Skill Assessment: AI algorithms provide real-time feedback on surgeons' techniques, contributing to improved training and consistent surgical outcomes. Conclusions This review highlights the substantial potential of AI in elevating the quality of robotic urological procedures. Its implementation may lead to more accurate diagnoses, streamlined surgeries, reduced complications, improved patient outcomes, and potential cost savings. Future research should concentrate on refining adaptable AI technologies that seamlessly integrate with existing robotic systems and provide real-time surgeon feedback. Nevertheless, comprehensive research, validation, and ethical considerations are essential before AI can be integrated into routine clinical practice.

The technical breakthrough of artificial intelligence (AI) in the field of oncology has moved from the laboratory to the clinic, but the realization of its social value is still facing the "last mile" dilemma. According to the WHO, there are more than 19 million new cancer cases worldwide every year, but the algorithmic advantages of AI are in sharp contrast to the uneven distribution of resources: while high-income countries are using AI to optimize personalized treatment programs, low-income regions are difficult to enjoy the technical dividends due to the lack of data. This work takes the " Technology-Ethics-Fairness" framework as the starting point to explore how to build a more inclusive AI oncology research ecology through interdisciplinary cooperation. Despite the outstanding performance of AI in the fields of tumor image recognition and genomics analysis, most studies focus on technical performance optimization and ignore the impact of social and cultural differences on the implementation of algorithms. For example, the driver gene mutation characteristics of lung cancer in Asian populations are significantly different from those in Europe and the United States, but the proportion of non-European ancestry samples in the public database is less than 10%, which leads to bias when the model is applied across regions. Furthermore, the inherent "black box" nature of AI decision-making exacerbates the crisis of trust between doctors and patients, especially in areas with limited medical resources, where technical authority may override clinical experience. To foster responsible and equitable AI in oncology, we propose three key pillars so that AI research can better serve society: (1) Data Equity: Establishing a global federated learning consortium for privacy-preserving, multi-omic data sharing to enable cross-regional model training. (2) Interpretability & Trust: Developing "decision traceability" tools that dynamically link AI outputs to clinical guidelines and supporting evidence. (3) Proactive Ethics: Integrating ethical impact assessments, informed by frameworks like the EU AI Act, into clinical trial design, including explicit metrics for equity and bias. The ultimate value of AI should not stop at improving the efficiency of diagnosis and treatment but also reshape the global collaboration network of cancer research. It is recommended to establish an international certification standard of "AI for Oncology," covering the dimensions of data representativeness, algorithm transparency, and cross-cultural adaptability. At the same time, bridging the technology gap through immersive medical education can help doctors in underdeveloped countries or regions to practice AI-assisted decision-making on 3D tumor models. As AI evolves from "technology enabler" to "ecological builder," cancer research will break through the boundaries of regions and disciplines and realize exponential growth of social value. We look forward to seeing more solutions that integrate technological innovation and humanistic care in the future. Citation Format: Zhicheng Du, Lijin Lian, Wenji Xi, Yu Zheng, Gang Yu, Hui-Yan Luo, Peiwu Qin. Artificial intelligence enables the ethical reconstruction and social value realization of global cancer research: From technological innovation to humanistic care [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr B024.

Use of artificial intelligence to predict survival in pulmonary hypertension