Detection Transformer for Teeth Detection, Segmentation, and Numbering in Oral Rare Diseases: Focus on Data Augmentation and Inpainting Techniques

In this work, we focused on deep learning image processing in the context of oral rare diseases, which pose challenges due to limited data availability. A crucial step involves teeth detection, segmentation and numbering in panoramic radiographs. To this end, we used a dataset consisting of 156 pano...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-02
Main Authors: Kadi, Hocine, Sourget, Théo, Kawczynski, Marzena, Bendjama, Sara, Grollemund, Bruno, Bloch-Zupan, Agnès
Format: Article
Language:English
Subjects:
Data augmentation
Geometric transformation
Image processing
Machine learning
Neural networks
Radiographs
Rare diseases
Transformers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we focused on deep learning image processing in the context of oral rare diseases, which pose challenges due to limited data availability. A crucial step involves teeth detection, segmentation and numbering in panoramic radiographs. To this end, we used a dataset consisting of 156 panoramic radiographs from individuals with rare oral diseases and labeled by experts. We trained the Detection Transformer (DETR) neural network for teeth detection, segmentation, and numbering the 52 teeth classes. In addition, we used data augmentation techniques, including geometric transformations. Finally, we generated new panoramic images using inpainting techniques with stable diffusion, by removing teeth from a panoramic radiograph and integrating teeth into it. The results showed a mAP exceeding 0,69 for DETR without data augmentation. The mAP was improved to 0,82 when data augmentation techniques are used. Furthermore, we observed promising performances when using new panoramic radiographs generated with inpainting technique, with mAP of 0,76.
ISSN:2331-8422