Performance of Multimodal Large Language Models and Humans on Curated AI-Generated Intraoral Images

Introduction and aims To evaluate the authenticity detection performance of multimodal large language models (MLLMs) using real and AI-generated intraoral photographs and to compare their performance with human evaluators with different levels of dental experience. Methods A dataset of 1,000 intraoral photographs (500 real and 500 AI-generated) across 5 standardised views was constructed from single-institution clinical images and the publicly available AI-Hub dataset. GPT-5.1 (OpenAI), Claude Opus 4.5 (Anthropic), and Gemini 3.0 Pro (Google) evaluated all images through vendor APIs. Human evaluation was conducted using a stratified random subset of 200 images by fourth-year dental students, dentists with ≤5 years, and dentists with ≥6 years of clinical experience (n = 5 per group). Results In the 200-image subset, dentists with ≥6 years showed the highest performance (accuracy: 0.740; F1-score: 0.675), followed by dentists with ≤5 years (accuracy: 0.690; F1-score: 0.557). Across the 1,000-image dataset, GPT-5.1 achieved the highest performance among the MLLMs (accuracy: 0.646; F1-score: 0.452), whereas Claude Opus 4.5 showed the lowest (accuracy: 0.571; F1-score: 0.249). All groups demonstrated substantially higher accuracy for real images than for the curated, visually plausible AI-generated images, with the MLLMs combining near-perfect specificity (0.998-1.000) and low recall (0.142-0.292), whereas human specificity was 0.890-0.990 and recall 0.390-0.540. The mandibular occlusal view showed the lowest accuracy among the MLLM groups. Conclusion Current MLLMs showed lower performance than experienced human evaluator panels, with limited recall for the AI-generated images in this study, suggesting that they are not yet suitable as standalone authenticity detection tools in dentistry. Clinical Relevance The increasing visual realism of generative artificial intelligence-generated intraoral photographs suggests that authenticity cannot be judged from visual inspection alone, and robust validation is needed before such images are used as clinical records, teaching material, or training data for artificial intelligence.

Authors

Institutions

Publication Details

Journal
International Dental Journal
Published
2026-11-18
DOI
https://doi.org/10.1016/j.identj.2026.111299
Primary Topic
Digital Media Forensic Detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Performance of Multimodal Large Language Models and Humans on Curated AI-Generated Intraoral Images

Wonse Park, Yiseul Choi, Dongsu Lee
6 links
International Dental Journal
Digital Media Forensic Detection
article

Performance of Multimodal Large Language Models and Humans on Curated AI-Generated Intraoral Images

Wonse Park, Yiseul Choi, Dongsu Lee
article en

Abstract

Introduction and aims To evaluate the authenticity detection performance of multimodal large language models (MLLMs) using real and AI-generated intraoral photographs and to compare their performance with human evaluators with different levels of dental experience. Methods A dataset of 1,000 intraoral photographs (500 real and 500 AI-generated) across 5 standardised views was constructed from single-institution clinical images and the publicly available AI-Hub dataset. GPT-5.1 (OpenAI), Claude Opus 4.5 (Anthropic), and Gemini 3.0 Pro (Google) evaluated all images through vendor APIs. Human evaluation was conducted using a stratified random subset of 200 images by fourth-year dental students, dentists with ≤5 years, and dentists with ≥6 years of clinical experience (n = 5 per group). Results In the 200-image subset, dentists with ≥6 years showed the highest performance (accuracy: 0.740; F1-score: 0.675), followed by dentists with ≤5 years (accuracy: 0.690; F1-score: 0.557). Across the 1,000-image dataset, GPT-5.1 achieved the highest performance among the MLLMs (accuracy: 0.646; F1-score: 0.452), whereas Claude Opus 4.5 showed the lowest (accuracy: 0.571; F1-score: 0.249). All groups demonstrated substantially higher accuracy for real images than for the curated, visually plausible AI-generated images, with the MLLMs combining near-perfect specificity (0.998-1.000) and low recall (0.142-0.292), whereas human specificity was 0.890-0.990 and recall 0.390-0.540. The mandibular occlusal view showed the lowest accuracy among the MLLM groups. Conclusion Current MLLMs showed lower performance than experienced human evaluator panels, with limited recall for the AI-generated images in this study, suggesting that they are not yet suitable as standalone authenticity detection tools in dentistry. Clinical Relevance The increasing visual realism of generative artificial intelligence-generated intraoral photographs suggests that authenticity cannot be judged from visual inspection alone, and robust validation is needed before such images are used as clinical records, teaching material, or training data for artificial intelligence.

International Dental JournalVol. 77(1)
Yonsei University (KR), Yonsei University Dental Hospital (KR), Yonsei University College of Dentistry (KR)
Strong, Yonsei University, Yonsei University College of Dentistry
Good health and well-being
Digital Media Forensic Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon