The application of artificial intelligence (AI) in anatomy teaching is gaining attention due to its potential to support personalized learning and its ability to provide customized, real-time feedback. While the potential impact of complete AI integration in medical education remains unclear, there is a suspicion that it could revolutionize pedagogical and assessment practices. Traditional anatomy teaching strategies that use donated human resources hinder continuous learning due to accessibility and ethical challenges. Existing resources, such as anatomy atlases, may not provide knowledge of spatial relationships. AI-powered applications enable students to access more flexible and accessible learning material beyond physical classrooms. This review critically evaluates current advances and the possible impacts of AI in learning anatomy based on the reported empirical original studies. Additionally, it recognizes the challenges and provides possible solutions for them. Most of the initiatives to integrate AI in anatomy teaching are directed towards the development of customized anatomy chatbots and their integration with virtual reality (VR). Although the crucial role of medical imaging in the anatomy curriculum is recognized, currently, no AI application has been developed to target this field. This review discusses the currently available AI tools for anatomy teaching. Additionally, the knowledge gaps and future directions of AI in medical education, especially anatomy education, are also discussed. With the present advances in AI technologies, their application in anatomical education is still deficient. This review paper provides an overview of recent tools used in anatomy teaching and learning.

Background: Accurate sex estimation from skeletal remains is essential in forensic identification, yet population-specific reference data for cervical vertebrae, particularly the first cervical vertebra (C1), are limited. This lack of data compromises the accuracy of sex estimation in forensic contexts where primary skeletal elements such as skull and pelvis are unavailable. Geometric morphometric (GM) analysis offers a robust alternative by quantifying shape variation independent of size, enabling precise assessment of morphological differences that conventional linear measurements may overlook. Objective: This study aimed to investigate the utility of C1 vertebra morphology for sex estimation among Omani adults using two-dimensional geometric morphometrics. Methods: A total of 320 lateral cervical radiographs (160 males, 160 females) were retrospectively collected from Sultan Qaboos University Hospital. Six anatomical landmarks on the atlas were digitized using TPSDig2, and shape analyses were performed using MorphoJ software. Statistical methods included Principal Component Analysis (PCA), Procrustes ANOVA, Canonical Variate Analysis (CVA), and Discriminant Function Analysis (DFA). Intra- and inter-observer reliability was also assessed. Results: While centroid size did not significantly differ between sexes (p = 0.2432), shape analysis revealed statistically significant sexual dimorphism (p = 0.0457). DFA correctly classified 77.19% of individuals by sex, with a cross-validated accuracy of 73.44%. Shape variation was most pronounced in the posterior tubercle and superior facets of the atlas. Conclusions: Two-dimensional geometric morphometric analysis of the first cervical vertebra (C1) reliably captures sexual dimorphism in the Omani population, providing a population-specific reference that enhances the accuracy and objectivity of forensic sex estimation.

Background: Autophagy is a conserved intracellular degradation pathway essential for maintaining cellular homeostasis by recycling damaged organelles and proteins. Dysregulation of autophagy has been implicated in pregnancy-related complications such as preeclampsia and fetal growth restriction, underscoring its importance in maternal and fetal health. However, the autophagy status in the placental tissue of COVID-19-infected pregnant women remains unknown. Objective: To investigate autophagy activity in term placentas from pregnant women infected with COVID-19 compared to those from uninfected control pregnant women. Methods: In this prospective cross-sectional single-center study, 15 COVID-19-positive and 15 COVID-19-negative term pregnant women who delivered at Sultan Qaboos University Hospital between January 2020 and December 2022 were included. Immediately after delivery, the placental tissue samples were collected and assessed for autophagy activity using immunohistochemistry for LC3B and p62 markers, histopathological examination, and transmission electron microscopy. The proportion and intensity of LC3B and p62 staining were quantified. Statistical analysis was performed using the Mann–Whitney U test. Results: There was a significant reduction in p62 and LC3B expression in both the proportion and intensity in COVID-19 placentas compared to the control group. The proportion of p62 (p = 0.001) and LC3B (U = 46.000, p = 0.003) was significantly reduced in infected placentas. Similarly, intensity levels of both markers showed significant differences (p < 0.05), supporting the evidence of reduced LC3B/p62, suggesting autophagy modulation in COVID-19 patients’ placentas. Additionally, abnormal ultrastructural changes were observed in COVID-19–positive placentas, including mitochondrial injury, endoplasmic reticulum stress, microvillus loss, and basement membrane thickening. Conclusion: The study results from a limited sample size demonstrate a significantly altered autophagy flux in the placental tissues of term pregnant women with COVID-19 infection. These findings highlight the potential impact of COVID-19 infection on placental function and fetal development and underscore the need for further investigation into autophagy-modulating strategies to improve maternal–fetal health.

Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is increasingly applied in neuro-oncology for the study and management of gliomas (the most common primary brain tumours in adults). AI is applied to a variety of tasks like prediction and classification, segmentation, grading, prognosis, as well as treatment response assessment. A recent literature search on several databases resulted in an increasing number of studies globally that aim to apply AI in glioma diagnosis and treatment. The majority of the studies focused on tumour diagnosis, often using a single or a combination of different features. A large number of the reviewed studies were of radiological nature, using magnetic resonance imaging (MRI) for image classification, where convolutional neural networks (CNNs), as part of a DL architecture, were often used for feature extraction and pattern recognition. Some of the studied approaches achieved high accuracy rates, mostly above 99%. Other studies investigated the histopathological and molecular diagnosis of low- and high-grade gliomas, and evaluated several approaches for optimizing treatment and for the prediction of the treatment response of glioma patients with acceptable performance. Even though several limitations and challenges for AI in glioma exist, the application of AI in various fields holds high potential for improved tumour diagnosis as well as for clinical decision support systems and for a better understanding of primary and secondary brain tumours.