Controllable Panoramic Radiograph Synthesis Using a Generative Model

Researchers developed a generative model that creates realistic panoramic dental radiographs from text descriptions of diseases and sketch-based anatomical guidance, addressing data scarcity and annotation challenges. The synthetic images improved AI segmentation and diagnostic performance when added to training datasets and were judged clinically realistic by radiologists.

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.