A Sequential Framework for Detection and Classification of Abnormal Teeth in Panoramic X-rays

TL;DR

This paper presents a multi-stage deep learning framework for detecting and classifying abnormal teeth in panoramic X-rays, achieving notable accuracy in dental lesion detection and disease classification.

Contribution

The authors developed a sequential framework combining Faster-RCNN and a hybrid U-net/Vgg16 model for improved dental abnormality detection and classification.

Findings

Dental instance detection AP score of 0.49

Healthy teeth filtering F1 score of 0.71

Disease classification F1 score of 0.76

Abstract

This paper describes our solution for the Dental Enumeration and Diagnosis on Panoramic X-rays Challenge at MICCAI 2023. Our approach consists of a multi-step framework tailored to the task of detecting and classifying abnormal teeth. The solution includes three sequential stages: dental instance detection, healthy instance filtering, and abnormal instance classification. In the first stage, we employed a Faster-RCNN model for detecting and identifying teeth. In subsequent stages, we designed a model that merged the encoding pathway of a pretrained U-net, optimized for dental lesion detection, with the Vgg16 architecture. The resulting model was first used for filtering out healthy teeth. Then, any identified abnormal teeth were categorized, potentially falling into one or more of the following conditions: embedded, periapical lesion, caries, deep caries. The model performing dental instance detection achieved an AP score of 0.49. The model responsible for identifying healthy teeth attained an F1 score of 0.71. Meanwhile, the model trained for multi-label dental disease classification achieved an F1 score of 0.76. The code is available at https://github.com/tudordascalu/2d-teeth-detection-challenge.