Dr. Shalini Singh’s research interests focus on Embryology and Neuroanatomy, with particular emphasis on developmental anatomy and structural variations of the human body. She is especially interested in anthropometric studies, including cephalic index research in diverse populations, and the clinical application of anatomical knowledge in physiotherapy practice. Additionally, she is engaged in advancing anatomy education through competency-based medical education (CBME), simulation-based learning, and innovative 3D digital teaching methodologies.

Dr. Shalini Singh is an Assistant Professor of Physiotherapy at Galgotias University, specializing in Medical Anatomy education. She holds an M.Sc. in Medical Anatomy from Era’s Lucknow Medical College and Hospital, where her research focused on the cephalic index in the North Indian population. She also earned a Bachelor of Physiotherapy from the Institute of Health Sciences. With over eight years of academic and clinical experience, Dr. Singh has served as Assistant Professor at Jain University and as a Medical Advisor & Content Creator at the Federation of Digital Health Sciences, where she developed innovative 3D anatomy-based learning modules aligned with NMC competencies. She is also a Review Board Member for ACTA Journal of Anatomical Sciences. Her academic interests include Embryology and Neuroanatomy, with a strong focus on integrating digital tools and simulation-based teaching into anatomy education. Reference: Explainable Artificial Intelligence Models for Anatomical Image Interpretation: Enhancing Transparency in Medical Education and Clinical Decision-Making Background: While artificial intelligence is being more widely integrated into medical image analysis, most deep learning systems have the limitation of being unintelligible "black boxes," which hampers interpretability and trust among educators and clinicians. In anatomy education and diagnostic training, the significance of understanding why a model makes a prediction is equal to the significance of the prediction itself. Explainable AI (XAI) provides tools including attention maps and feature visualisation to improve transparency. This study aimed to create and assess an explainable AI framework for the interpretation of anatomical images, and evaluate its potential for educational use. Methods: A convolutional neural network (CNN) model was trained using a carefully selected dataset of labelled anatomical images, which included both radiological and gross specimens. Visualization techniques based on Grad-CAM were integrated to produce heatmaps that highlighted anatomical regions most significantly affecting model predictions. The model's performance was assessed via accuracy, precision, recall, and F1-score metrics. A structured feedback survey was conducted with 60 undergraduate medical students and 15 faculty members to evaluate the interpretability, perceived learning improvement, and trust in AI-generated results. Results: The AI model attained a global classification accuracy of 91.3% and an F1-score of 0.89. Grad-CAM visualizations consistently correlated with anatomically relevant structures, thereby enhancing interpretative clarity. The survey results showed 84% of students claimed improved spatial comprehension and 78% of instructors stated that interpretable AI outputs boosted their confidence in AI-assisted analysis versus non-interpretive models. Conclusion: Explainable AI models substantially improve transparency, trustworthiness, and educational value in the interpretation of anatomical images. Integrating XAI into anatomy curricula could help close the gap between computational intelligence and human anatomical reasoning, promoting the responsible and effective use of AI in medical education and clinical settings.