Abstract
Finding summaries from an orthopantomogram, or a dental panoramic radiograph, has significant potential to improve patient communication and to speed up clinical judgments. While orthopantomogram is a first-line tool for dental examinations, no existing work has explored the summarization of findings from it. A finding summary has to not only find teeth in the imaging study but also label the teeth with several types of treatments. To tackle the problem, we develop DeepOPG that breaks the summarization process into functional segmentation and teeth localization, the latter of which is further refined by a novel dental coherence module. We also leverage weak supervision labels to improve detection results in a reinforcement learning scenario. Experiments show high efficacy of DeepOPG on finding summarization, achieving an overall AUC of 88.2% in detecting six types of findings. The proposed dental coherence and weak supervision both are shown to improve DeepOPG by adding 5.9% and 0.4% to AP@IoU=0.5 respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2103.08290
