Reproduce “Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jing Hao, Yuxuan Fan, Yanpeng Sun, Kaixin Guo, Lizhuo Lin, Jinrong Yang, Qi Yong H. Ai, Lun M. Wong and 2 more
Researchers from The University of Hong Kong and collaborators introduced MMOral, the first large-scale multimodal instruction dataset and benchmark specifically for panoramic X-ray interpretation. Their fine-tuned OralGPT model demonstrated a 24.73% performance improvement on the MMOral-Bench, highlighting the need for domain-specific AI in dentistry as even leading general LVLMs like GPT-4o achieved only 41.45% accuracy.
Key insights
- Existing large vision-language models (LVLMs), including leading proprietary and general medical models, achieve low accuracy (e.g., GPT-4o at 41.45%) on panoramic X-ray interpretation.
- Universal medical LVLMs do not provide a clear performance advantage over general-purpose LVLMs in specialized dental applications.
- Supervised fine-tuning with the domain-specific MMOral instruction dataset yields substantial performance gains, demonstrating the critical need for tailored data.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.