Challenges and Limitations of Multimodal Large Language Models in Interpreting Pediatric Panoramic Radiographs
Both LLMs failed to achieve clinically acceptable performance and cannot reliably identify nuanced discrepancies critical for pediatric dentistry. Further refinements and consistency improvements are essential before routine clinical use.
Authors
- Naoya Kakimoto (ORCID: https://orcid.org/0000-0003-1274-8991)
- Tzu‐Yu Peng (ORCID: https://orcid.org/0000-0002-7168-9429)
- Yuko Iwamoto (ORCID: https://orcid.org/0000-0002-9387-7746)
- Taku Nishimura (ORCID: https://orcid.org/0000-0002-9011-9245)
- Ryota Nomura (ORCID: https://orcid.org/0000-0001-5510-8535)
- Saori Takeda
- Shota Okazaki
- Yuichi Mine (ORCID: https://orcid.org/0000-0002-7057-1955)
- Takeshi MURAYAMA
- Eimi Tabata
Institutions
- Hiroshima University (JP)
- Hiroshima University of Economics (JP)
- Taipei Medical University (TW)
Publication Details
- Journal
- International Journal of Paediatric Dentistry
- Published
- 2025-09-16
- DOI
- https://doi.org/10.1111/ipd.70029
- Citations
- 3
- Primary Topic
- Dental Radiography and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 5.37