Can Large Language Models Grasp 3D Medical Anatomy Shapes? (Student Abstract)

What if the next generation of human-computer interaction is not a screen... but a conversation? Large Language Models (LLMs) offer a new paradigm for interacting with computers through text, but they lack shape reasoning capabilities. We introduce Textual Anatomy Encoding (TAE), a workflow that connects LLMs with 3D anatomies. TAE employs clinician-validated semantic annotations and rule-based prompts to achieve deterministic and interpretable landmark localization. The results indicate that TAE enables LLMs to move beyond textual knowledge, achieving an accurate understanding of anatomical localization. This framework opens opportunities for diagnosis, surgical planning, and scalable medical annotation, positioning LLMs as a foundation for next-generation human–computer interaction in healthcare.

Authors

• Yao Gao KU Leuven, 3000 Leuven, Belgium University Hospitals Leuven (UZ Leuven), 3000 Leuven, Belgium
• Feng Li BSH Home Appliances Holding (China) Co. , Ltd
• Jeroen Van Dessel KU Leuven, 3000 Leuven, Belgium University Hospitals Leuven (UZ Leuven), 3000 Leuven, Belgium
• Yi Sun
• Robin Willaert KU Leuven, 3000 Leuven, Belgium University Hospitals Leuven (UZ Leuven), 3000 Leuven, Belgium

Keywords

No keywords are indexed for this paper.