[4M3-OS-14c] OS-14

[4M3-OS-14c-04] Generating educational resources using large-scale language models based on context expressed in radiological, anatomical and pathological images.

〇MASATO TANAKA¹, TAKESHI HARA², TSUGUMI MATSUO², SEIJI YAMADA³ (1. Medical Education Support Center, University of Fukui, 2. Gifu University Faculty of Engineering, 3. National Institute of Informatics)

Keywords:LLM, Medical Image Education

[Purpose] We furthered the study "Learning and understanding lung structure described by the context of radiological, anatomical, and pathological images" presented at the 38th Japanese Society for Artificial Intelligence in 2024, and attempted to generate learning content with the accuracy that can actually be used by students by inputting individual image data that form the context and the linguistic information that explains them into LLM (GPT-4o).
[Method] LLM learning was performed using prompt learning and fine-tuning. For prompt learning, multi-modal data was used, which used image data and linguistic information as learning data. The output was educational content in a Q&A format.
[Results] When generating educational resources using one-shot learning with prompts, the resulting Q&As were highly logical and promoted understanding of the input learning information. On the other hand, when learning using Fine-Tuning, Q&As containing incorrect information that deviated from the learning data were occasionally found. Based on this experiment, we believe that generating learning resources using Prompt Engineering is suitable for practical use.