The Feasibility of One-Stage Instance Segmentation for Detecting Oral Potentially Malignant Disorders in White-Light Clinical Photographs: A Proof-of-Concept Study.

Researchers compared two deep learning approaches for detecting oral potentially malignant disorders in standard clinical photographs, finding that YOLOv8 segmentation outperformed global classification but achieved only 62% accuracy—insufficient for clinical use without addressing dataset limitations and specificity issues.

A plain-English summary of the study's own findings — we don't add our own claims or interpretation. Read the full paper for the complete methods and results, and apply your own clinical judgement.