A bibliometric analysis of artificial intelligence in anatomy education: Current situation, hot spots, and global trends Authors: Yuanyuan Fan, Xun Zheng, Guang Yang, Pengyu Li, Yanhao Ran, Tianfeng Xu, Tao Wei Published: 2026 ABSTRACT Introduction:Artificial intelligence (AI) is increasingly being integrated into anatomy education, yet a comprehensive overview of the field’s development and emerging trends remains lacking. This study identifies research hotspots and trends in AI applications in anatomy education through a bibliometric analysis.Methods:English-language publications on AI in anatomy education were systematically collected from the Web of Science database. Using bibliometric tools, including R, VOSviewer, CiteSpace, and Excel, data were synthesized to explore global research trends and focal areas.Results:A total of 184 papers published between 2005 and 2024 were included. The United States emerged as the leading contributor in terms of publication output and citation impact. Over the past 2 decades, research focus has shifted from general medical education applications toward AI-driven image segmentation, deep learning, and surgical guidance. More recently, large language models (e.g., ChatGPT) have begun to attract attention in anatomy education.Conclusion:This bibliometric analysis maps the intellectual landscape of AI in anatomy education, identifying key thematic shifts and emerging frontiers. The findings provide a foundation for guiding future research directions in this rapidly evolving field. 1. Introduction Artificial intelligence (AI) is increasingly being integrated into anatomy education, yet a comprehensive overview of the field’s development and emerging trends remains lacking. AI research encompasses various domains, including intelligent robotics, machine learning (ML), speech and image recognition, natural language processing, and expert systems.[1] In the context of anatomy education, AI-driven tools (particularly large language models [LLMs]) have demonstrated significant potential. The generative pretrained transformer language model developed by OpenAI,[2] especially its ChatGPT variant, can produce accurate, detailed, and well-structured anatomical descriptions, assisting medical students in understanding complex anatomical terminology.[3,4] Beyond language models, deep learning (DL)-powered computer vision has been widely applied in medical imaging and surgical guidance, with demonstrated success in dermatology,[5] hematology,[6] cardiovascular medicine,[7] ophthalmology and gastrointestinal endoscopy.[8] More relevant to anatomy education, in minimally invasive surgery, AI enables the precise identification of critical anatomical landmarks, significantly reducing surgical complications.[9,10] These applications underscore the importance of anatomical knowledge and highlight how AI can support anatomical training in clinical contexts. Bibliometric analysis has emerged as an invaluable tool for managing substantial volumes of scientific data, offering meaningful insights by evaluating article, journal, country, and author performance, and illuminating collaboration patterns within the scientific community.[11] Such analyses are crucial for understanding the structural and developmental dynamics that shape specific research fields. While bibliometric studies have extensively investigated AI’s integration with medicine,[12–14] there remains a noticeable gap in examining AI’s role within anatomical education. Addressing this gap could uncover existing knowledge deficiencies while highlighting emerging research trends and focal areas. Given the limited comprehensive studies on AI in anatomy education, this study uses bibliometric tools to systematically collect and analyze literature from the last 2 decades, sourced from the Web of Science database. It addresses 3 primary research questions: Which countries, institutions, journals, and authors contribute most frequently to AI-related publications in anatomy education and what is the degree of collaboration among research teams? What are the primary research hotspots within AI applications for anatomy education? What thematic trends are emerging in AI’s role in anatomy education? This bibliometric review aims to map the current landscape and identify evolving frontiers, providing a foundational reference for researchers, educators, and policymakers interested in the integration of AI into anatomy education. 2. Material and methods 2.1. Data collection Literature on AI in anatomy education was systematically sourced from the Web of Science Core Collection (WoSCC, https://webofscience.clarivate.cn/wos/alldb/basic-search) on September 1, 2024, with the Science Citation Index Expanded and Social Sciences Citation Index serving as the citation indices. The WoSCC serves as a key citation resource, curating high-impact research from 1990 onward, including peer-reviewed journals (open access available), conference proceedings, and selected book chapters. Employing an advanced search strategy, terms were defined as: (TS = (“Artificial Intelligence” OR “Computational Intelligence” OR “Machine Intelligence” OR “Computer Reasoning” OR “AI” OR “Computer Vision System” OR “Machine learning” OR “robot*” OR “robot technology” OR “assistant robot” OR “robot-assisted” OR “computer reasoning” OR “deep learning” OR “sentiment analysis” OR “neural network” OR “expert* system*” OR “natural language processing” OR “decision tree” OR “data mining” OR “Bayesian network” OR “intelligent learning” OR “supervised learning” OR “semantic segmentation” OR “deep network” OR “neural learning” OR “neural nets model” OR “graph mining” OR “ChatGPT” OR “Chatbot” OR “Large Language Model” OR “random forest” OR “particle swarm optimization” OR “pattern recognition” OR “genetic algorithm” OR “supervised algorithm” OR “unsupervised algorithm” OR “knowledge-based” OR “casebased reasoning” OR “decision support system” OR “self-organizing map” OR “evolutionary computation” OR “reinforcement learning” OR “clustering” OR “support vector machine”)) AND (TS = (“anatom* education*” OR “anatom* knowledge” OR “anatom* training” OR “anatom* learning” OR “informatic* anatom*” OR “anatom* study” OR “anatom* teaching” OR “anatom* academic” OR “anatom* educator” OR “anatom* teacher” OR “anatom* course*”OR “anatom* class*”)). This initial search yielded 293 documents. To ensure a focused and relevant dataset, the following refinement criteria were applied: time span from January 1, 2005, to August 31, 2024; inclusion of document types limited to articles and reviews; restriction to publications in English. Based on the established inclusion criteria, we conducted a comprehensive manual review of the selected literature, ultimately identifying 184 articles relevant to the application of AI in anatomical education for inclusion in the final bibliometric analysis. A detailed methodology flowchart is provided in Figure S1. As the data used in this study was from a public source, obtaining ethical permissions was not required. 2.2. Statistical analysis For statistical analysis and the evaluation of annual publication trends, Microsoft Office Excel 2021 was employed to compile data and create histograms. The “bibliometrix” package of R (v4.3.2; R Foundation for Statistical Computing), a robust and open-source tool, was employed for conducting a comprehensive science mapping analysis (Massimo & Corrado, 2017).[15] This package facilitated the graphical representation of the global distribution of publications among various countries. Additionally, bibliometric analyses were further augmented using 2 specific software tools: CiteSpace 6.3.R3 (64-bit) for citation burst analysis and keyword clustering, and generating timeline views of keywords; and VOSviewer (version 1.6.20) for constructing visual maps based on citations, keywords, countries, institutions, journals, and authors, delineating the intricate networks of collaboration, co-citation, and thematic co-occurrence. The integrated results from both CiteSpace and VOSviewer were synthesized to provide a comprehensive, multidimensional bibliometric portrayal. 3. Results 3.1. Publication year A comprehensive retrieval from the WoSCC yielded 184 documents pertinent to the integration of AI in anatomy education, comprising 165 articles and 19 reviews. As depicted in Figure 1, the annual distribution of publications has followed an upward trend over the last 2 decades, culminating in 27 publications (14.67%) in 2024, with the growth trajectory remaining steady. The steady rise in publications indicates a growing scholarly focus on the application of AI in anatomy education, highlighting the dynamic evolution and broadening scope of knowledge in this area. Linear regression analysis demonstrated a strong fit of the polynomial curve to the annual literature growth trend, with a high coefficient of determination (R2 = 0.6501, where R2 > 0.4, Figure 1), denoting sustained and escalating academic inquiry. Annual trends of global publication outputs in AI in anatomy education from 2005 to 2024. The blue bars represent the number of publications per year, and the red line represents the polynomial trend line (R2 = 0.6501). AI = artificial intelligence. 3.2. Countries distribution To explore productivity and publishing trends, we recorded collective contributions from 42 countries/regions on the topics under investigation. According to the data presented in Table 1, the United States (U.S.) leads in publication volume with 67 documents, constituting 36.41% of total output, followed by significant contributions from China, England, Japan, and Germany. While English and German publications are fewer in number compared to those from the U.S., they achieve a higher average citation rate, emphasizing the significant qualitative impact of their contributions. Conversely, despite China’s high publication volume, its lower citation impact suggests a potential need for improving research quality. Table 1The top 5 productive countries.RankCountriesPublicationsCitationsCitations per publication1USA67159223.762China4749910.623England2075837.904Japan1847626.445Germany1556537.67USA = United States of America. The top 5 productive countries. USA = United States of America. The collaborative network of countries with a minimum of 8 publications is mapped in Figure S2, demonstrating the academic partnership across 9 countries grouped into 4 distinct clusters. This visualization illustrates the dominant role of the U.S., China, England, and France in fostering international collaborations. Nonetheless, there is a noticeable lack of cooperation among these core nations, suggesting a need for improvement in this area. Global publication patterns, as depicted in Figure 2, show significant scholarly contributions from Europe, Asia, and North America. European publications are more evenly distributed among various countries, North American output is concentrated mainly in the U.S., and China dominates academic contributions in Asia. Geographical distribution of countries contributing to AI in anatomy education research. Countries with at least 5 publications are shown. The size of each circle represents the publication volume, and the color intensity represents the total citation count. AI = artificial intelligence. 3.3. Journal analysis The comprehensive search yielded 184 documents from the AI in anatomy education research corpus, published across 120 distinct journals. Of the journals reviewed, Anatomical Sciences Education and Medical Image Analysis were the most prolific, each contributing 10 publications on the integration of AI in anatomy education. Presented in Table 2, the data highlight the significant contributions of these journals in the dissemination of research focused on the theme. Table 2The top 5 most productive journals.RankJournalsPublicationsJCR*IF*1Anatomical Sciences Education10Q15.22Medical Image Analysis10Q110.73International Journal of Computer Assisted Radiology and Surgery6Q22.34Medical Physics4Q23.05Computer Methods and Programs in Biomedicine4Q14.9IF - impact factors, JCR = journal citation reports.*Journal citation reports (JCR) and impact factors (IF) for 2023 to 2024. The top 5 most productive journals. IF - impact factors, JCR = journal citation reports. Journal citation reports (JCR) and impact factors (IF) for 2023 to 2024. Using Bradford Law, we identified 14 core journals by analyzing the descending order distribution, as shown in Figure S3, with Anatomical Sciences Education emerging as the leading journal. In a more detailed analysis, Figure 3 undertakes a co-citation assessment of the journals, applying a threshold of 12 citations to refine the data. The colored line connections denote partnerships among journals, while the dot size represents the citation volume of the respective journal’s publications. Notably, Neuroimage, Institute of Electrical and Electronics Engineers Transactions on Medical Imaging, Anatomical Sciences Education, and the Journal of Urology rank as the top journals by citation count, signifying their prominence and impact in the field. Co-citation network visualization of journals cited in AI in anatomy education research. Journals with at least 12 citations are included. The node size represents the citation count, and the connecting lines indicate co-citation relationships. AI = artificial intelligence. 3.4. Research institutions distribution The analysis performed using VOSviewer reveals widespread global involvement, with 409 institutions contributing to the research field. Table 3 showcases the most prominent institutions, all of which have published at least 4 papers. Remarkably, Stanford University in the U.S. leads with 8 publications accumulating 219 citations. This is followed by significant contributions from Johns Hopkins University in the U.S. and University College London in England, underscoring the global scope of research efforts. In terms of citation impact, the University of Pennsylvania in the U.S. stands out, with its scholarly work receiving the highest citation rates among the most productive institutions. This affirms the outstanding quality and notable influence of U.S. research in driving AI advancements in anatomy education. Table 3The most productive institutions.RankInstitutionsPublicationsCitationsCountryCitations per publication1Stanford University8219USA27.382JHU6106USA17.673UCL6192UK32.004University of Pennsylvania5277USA55.45Osaka University585Japan17.006University of Colorado490USA22.507University of Sydney495Australia23.758Moorfields Eye Hospital (NHS)4127UK31.759Sun Yat-sen University458China14.5010Shanghai Jiao Tong University481China20.2511Chinese Academy of Sciences422China5.50JHU = Johns Hopkins University, NHS = National Health Service, UCL = University College London, UK = United Kingdom, USA = United States of America. The most productive institutions. JHU = Johns Hopkins University, NHS = National Health Service, UCL = University College London, UK = United Kingdom, USA = United States of America. Figure S4A further elaborates on these collaborations by visualizing the co-occurrence network among institutions. Central nodes such as Stanford University, Johns Hopkins University, and Osaka University function as key hubs, indicating strong partnerships and dynamic academic collaborations. 3.5. Authors analysis According to VOSviewer analysis, 1055 authors have been involved in AI research within anatomy education throughout a nearly 24-year period. This prolific community of scholars is represented in Table 4, highlighting the top 8 authors by publication count. Among these prominent contributors, 6 are from the U.S., underscoring the nation’s substantial impact on the field. Outstandingly, Holsinger, F. Christopher of the U.S. has published 4 papers, receiving 137 citations, establishing his leadership in this area of research. Table 4The most productive authors.RankAuthorsDocumentsCitationsAverage Citation/PublicationCountry1Holsinger, F. Christopher413734.25USA2Jabs, Douglas A.49022.50USA3Palestine, Alan G.49022.50USA4Thorne, Jennifer E.49022.50USA5Lightman, Susan l.38729.00England6Oden, Neal38729.00USA7Trusko, Brett E.38729.00USA8Sato, Yoshinobu34715.67JapanUSA = United States of America. The most productive authors. USA = United States of America. Figure S4B provides a visual representation of the collaborative networks among these prolific authors. The size of the nodes indicates the volume of publications, while the lines denote co-authorship, revealing patterns and potential gaps in collaboration. Intriguingly, the graph exposes that these core authors are largely separated into 3 distinct groups, with minimal collaboration between them. This reflects a fragmentation in research partnerships, pointing to the need for improved interdisciplinary and interinstitutional collaboration. 3.6. Keywords and research hotspots Serving as the foundation of an article, keywords distill its primary focus and thematic essence. VOSviewer’s analysis, applying a threshold of 11 occurrences, delineates the top 10 keywords that represent the major research hotspots and focus areas in AI in anatomy education, as summarized in Table 5. Figure S5, generated using the “bibliometrix” package in R, enhances this by presenting the most frequent keywords, where the font size correlates with frequency, offering a clear visual representation of research priorities. These keywords, notable for their frequency and practical significance, capture the primary research themes and directional trends in the study of AI in anatomy education. Table 5The top 10 keywords.RankKeywordsOccurrences1deep learning292artificial intelligence233segmentation184anatomy175image segmentation146surgery127performance118robotic surgery119classification1110image11 The top 10 keywords. Figure S6 displays a keyword cluster analysis plot generated with CiteSpace, revealing a dense cluster around “AI,” “automatic segmentation,” “image segmentation,” “laparoscopic,” and “lumbar interbody fusion,” identifying these areas as key focuses of investigative interest. 3.7. Research trends analysis The timeline viewer in Figure S7A organizes keywords into 10 distinct clusters, delivering a chronological insight into the evolution and interrelation of major research themes. Recent advancements in AI within anatomy education focus on areas such as “gross anatomy education,” “performance,” “adaptation models,” “medical image segmentation,” and “robotic surgery,” suggesting a widening scope. The dominant research trajectory now encompasses not only anatomy education but also the segmentation of medical anatomical images and surgical step guidance. Figure S7B highlights the top 20 keywords exhibiting the most significant citation bursts, a measure of their burgeoning impact and relevance in the literature. “deep learning” tops the list with a burst strength of 7.75, followed by keywords such as “artificial intelligence,” “transoral robotic surgery,” and “magnetic resonance imaging.” These trends reflect the rising focus on robotic surgery and imaging atlas analysis as part of the broader integration of AI into anatomical education. The thematic map generated using the “bibliometrix” package in R, as depicted in Figure S8, identifies “performance,” “surgery,” and “system,” among others, as motor themes. The placement in the upper-right quadrant reflects both the breadth of exploration and their crucial role in driving the research forward. Conversely, themes like “features,” “gastric cancer,” and “upper gastrointestinal endoscopy” are positioned in niche areas, reflecting their more specialized or emerging roles in the field. Prominently, “image registration,” “resection,” and “image segmentation” stand out as focal themes, signifying the heightened focus on surgical excision and preoperative anatomical image analysis in the integration of AI into the realm of anatomy education. 4. Discussion In this comprehensive review, 184 articles published between January 2005 and September 2024 from 42 countries have been systematically analyzed. This period marks significant growth in research on AI integration into anatomy education, assessed through advanced bibliometric tools including CiteSpace, VOSviewer, and the bibliometrix package. The scope of analysis covers publications, countries, institutions, scholars, journals, and keywords, all aimed at addressing the 4 central research questions of this study. The first research question examines contributions to the literature by analyzing publication counts and trends and investigates collaboration across nations, institutions, and academic contributors. The past 2 decades have witnessed a steady rise in publications on AI applications in anatomy education, with a marked acceleration post-2021, likely driven by AI advancements and the shift to online learning during COVID-19.[16] Currently, research teams are integrating various AI technologies, including artificial neural networks, convolutional neural networks (CNN), Bayesian U-Net, robotics, and virtual consultations, into anatomy education.[17] The analysis reveals limited international collaboration in this field, likely stemming from political, geographical, and socioeconomic disparities.[18] Addressing this necessitates global efforts to ensure the equitable distribution of educational resources. The second research question investigates research hotspots within AI applications to anatomy education, identified through high-frequency keyword and clustering analysis. Our analysis reveals that research areas are currently dominated by DL, ML, and CNNs, as well as automatic image segmentation and innovations in surgical procedures, particularly robotic surgery. Anatomy education research frequently focuses on the integration of AI technologies, including DL, ML, and CNNs, to enhance teaching methodologies. For instance, Rechowicz et al[19] applied natural language processing with a dictionary-based approach to analyze emotional content in students’ gross anatomy reflections, enabling educators to customize learning plans. Intelligent virtual reality enables teachers to provide guidance through virtual agents in remote laboratory settings.[20] Interactive teaching systems, including anatomy chatbots,[21] immediate assessment tools, and clinical application quizzes, may be optimized and integrated into AI frameworks to monitor and assess students’ learning progress.[22] Furthermore, AI employs algorithms to forecast students’ academic performance, including learning progression, grades, and assignment-related challenges.[23] The integration supports the idea that no single modality or teaching method can be considered superior to others, as the most effective pedagogical approach typically involves the integration of multiple learning modalities into educational practices.[24–26] AI-driven image segmentation has become pivotal in anatomy education. The digital transformation of anatomy education has gained widespread adoption since the onset of the COVID-19 pandemic.[27] Developed by Dr Donald A. B. Lindberg, the Visible Human Project exemplifies the efficacy of digital education tools and 3-dimensional (3D) anatomical visualization in enhancing anatomy instruction.[28] By utilizing 3D animation, students can dynamically interact with anatomical models and visualize structures in diverse planes. Coupling this with traditional cadaveric training enhances both student confidence and the effectiveness of anatomy education.[29] Jinga, M. R. et al implemented 3D segmentation to facilitate student training in CT scan interpretation and anatomical comprehension.[30] Furthermore, this approach has been adopted in anatomy education for specialized areas such as nerves, cardiovascular, vascular, and oral and maxillofacial anatomy.[31–33] However, the application of this supportive teaching methodology should be broadened to include clinicians across all disciplines. AI algorithms demonstrate high accuracy and efficiency in 3-dimensional cone-beam computed tomography imaging, contributing to the diagnosis of various dental conditions.[34,35] In oncology, AI techniques assist clinicians in quantifying malignant tumor volumes, segmenting and classifying pathological lesions, and detecting micrometastases.[36] In laparoscopic surgery, ML has demonstrated significant advantages in organ anatomy segmentation. Particularly, given the critical need for precise anatomical identification in surgical procedures, DL technology has become instrumental in detecting subtle and anatomically variable structures, including the gallbladder, urinary tract nerves, and abdominal autonomic nerves,[9,10] thereby offering valuable guidance to surgeons for the identification of anatomical structures. Obviously, AI systems offer substantial support in mastering complex anatomy, enhancing both anatomical recognition and the diagnostic accuracy of pathological findings for medical students and junior doctors,[25] while simultaneously driving innovations in surgical access methodologies. The shift toward AI-driven image segmentation and surgical applications does not occur by chance. Several factors may explain this trend. First, the COVID-19 pandemic accelerated the adoption of digital and online teaching tools, creating an urgent need for accessible, high-quality anatomical visualization resources.[27] Second, advances in DL have made automatic segmentation more accurate and efficient, enabling its integration into routine educational and clinical workflows.[30] Third, in surgical training, the ability to identify anatomical structures with AI assistance directly addresses patient safety concerns by reducing intraoperative complications.[9,10] Together, these findings suggest that AI in anatomy education is evolving from a supplementary teaching aid toward an integrated component of both classroom learning and clinical training. Future research should focus on evaluating the educational outcomes of these AI applications and exploring their long-term impact on medical competency development. The third research question assesses major trends in AI applications to anatomy education, analyzing keyword evolution and identifying emerging themes. This includes evaluating AI technology expansion, pedagogical intent, and educational outcomes in anatomy teaching. AI integration offers promise for enhancing instructional accuracy and consistency while identifying subtle issues that human observation may overlook (Lazarus et al, 2024).[37] AI-driven tutoring platforms, in particular, could “understand” students more effectively and efficiently than human instructors.[38] Research priorities should include ML-based adaptive platforms utilizing decision tree algorithms for objective practical exam grading, facilitating personalized learning and real-time curricular adaptations.[39] Furthermore, computer vision enables automated, standardized assessment of practical skills, objectively evaluating medical students’ clinical expertise. While simulation technologies (robotic and virtual reality systems), replicate complex clinical scenarios and surgical anatomy, advancing diagnostic proficiency and surgical skill acquisition. Anatomy education reform requires aligning AI development with curricular goals through rigorous needs assessment, ensuring scalable and sustainable integration of AI-driven teaching innovations.[40] Assessing behavioral motivation and educational outcomes is crucial to ensuring effective AI applications in anatomy education. While AI supports curriculum design and pedagogical optimization through data-driven engagement analytics, educators must retain central oversight to ensure human-centered instructional delivery. Meanwhile, misuse of AI in anatomy education risks eroding trust and promoting academic violations.[41] Educators should, therefore, incorporate AI ethics training to ensure responsible and transparent technology use. Future research should examine acceptance, learning outcomes, and behavioral intentions among students and educators while addressing the balance between AI support and self-directed learning in anatomy education. From an anatomical education perspective, AI has emerged as an indispensable tool for optimizing student learning experiences, diversifying pedagogical approaches, and refining learning outcome assessments. Emerging LLMs, including ChatGPT and DeepSeek, demonstrate significant potential in anatomical education by enhancing conceptual understanding, enabling personalized learning experiences, and delivering tailored challenges.[42–44] Since 2023, a growing number of studies have explored the application of LLMs in anatomy education, covering areas such as generating anatomical descriptions, answering student queries, and providing interactive learning support. However, due to the time lag in Web of Science indexing, some of the most recent LLM-related publications may not be included in the present analysis. Future bibliometric studies should consider incorporating preprint servers (e.g., medRxiv, bioRxiv) and open-source repositories (e.g., GitHub) to capture these emerging trends in a more timely manner. Looking forward, several trends are likely to shape the future of AI in anatomy education. First, the integration of LLMs into anatomy curricula is expected to grow, with AI-powered chatbots serving as personalized tutoring tools for students. Second, the combination of AI-driven image segmentation with virtual and augmented reality may create immersive, interactive learning environments that go beyond traditional cadaveric dissection. Third, as AI tools become more embedded in education, research will need to shift from descriptive studies toward evaluating their actual impact on learning outcomes and long-term clinical competency. Addressing these directions will require close collaboration among anatomists, AI researchers, and medical educators. Consequently, fostering the integration of AI into anatomical education and cultivating appropriate motivational frameworks for its use are critical priorities for advancing future medical pedagogy. 5. Limitation This study represents the first bibliometric analysis of AI integration in anatomy education. However, several limitations should be acknowledged. Primarily, reliance solely on the WoSCC may have excluded relevant studies from other databases, potentially restricting the scope of the analysis. Moreover, the exclusion of non-English publications may introduce language bias, omitting potentially significant contributions from non-English-speaking regions. Finally, given the fast-paced nature of AI research, this study only included peer-reviewed articles indexed in WoSCC and did not incorporate preprints (e.g., medRxiv, bioRxiv) or open-source repositories (e.g., GitHub). Preprints often contain the most up-to-date findings, and GitHub hosts many AI tools for anatomical segmentation and education. Their exclusion may mean that the very latest advances, particularly those related to LLMs published after 2023, are not fully captured in this analysis. Future bibliometric studies could benefit from integrating these sources to provide a more timely and comprehensive overview of this rapidly evolving field. Nevertheless, the potential impact of these omissions is minimal and is unlikely to compromise the validity of the study’s overarching conclusions.[45] These limitations contextualize the findings and highlight the need for broader, more inclusive approaches in future research. 6. Conclusion This research offers a comprehensive bibliometric evaluation and visual mapping of the current literature on AI applications in anatomy education. Through bibliometric tools, this analysis provides a detailed overview of the current research landscape, identifying key themes and projecting emerging trends in AI integration within anatomy education. Key AI applications in anatomy education include techniques such as DL, ML, image segmentation, and feature extraction, all of which are driving ongoing innovation within anatomy education. Future research should prioritize increased investment in scientific resources, strengthening international collaboration, and enhancing data security measures to ensure the continued progression and advancement of AI technologies in anatomy education. Acknowledgments The authors declare that this study received funding from the Sichuan University West China Hospital Discipline Excellence Development 1 · 3 · 5 Project (No. ZYJC21033). The funder was not involved in the study design, collection, analysis, interpretation of data, the writing of this article, or the decision to submit it for publication. Author contributions Conceptualization: Yuanyuan Fan, Xun Zheng. Data curation: Yuanyuan Fan, Xun Zheng, Tianfeng Xu. Formal analysis: Yuanyuan Fan, Xun Zheng, Guang Yang, Pengyu Li, Yanhao Ran. Funding acquisition: Tao Wei. Investigation: Yuanyuan Fan. Methodology: Xun Zheng, Guang Yang. Supervision: Tao Wei. Visualization: Yuanyuan Fan. Writing – original draft: Yuanyuan Fan, Guang Yang, Pengyu Li, Yanhao Ran, Tianfeng Xu. Writing – review & editing: Yuanyuan Fan, Xun Zheng, Tao Wei.