Tooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological Processing

TL;DR

This paper introduces a novel post-processing approach combined with U-Net for accurate tooth instance segmentation in panoramic dental X-rays, achieving state-of-the-art results with limited training data.

Contribution

It presents a new morphological post-processing technique that significantly improves tooth segmentation and counting accuracy in dental radiographs using a small dataset.

Findings

Achieved 95.4% dice overlap score in teeth segmentation.

Reduced mean tooth count error from 26.81% to 6.15%.

Performed better than existing methods with fewer training images.

Abstract

Automatic teeth segmentation in panoramic x-ray images is an important research subject of the image analysis in dentistry. In this study, we propose a post-processing stage to obtain a segmentation map in which the objects in the image are separated, and apply this technique to tooth instance segmentation with U-Net network. The post-processing consists of grayscale morphological and filtering operations, which are applied to the sigmoid output of the network before binarization. A dice overlap score of 95.4 - 0.3% is obtained in overall teeth segmentation. The proposed post-processing stages reduce the mean error of tooth count to 6.15%, whereas the error without post-processing is 26.81%. The performances of both segmentation and tooth counting are the highest in the literature, to our knowledge. Moreover, this is achieved by using a relatively small training dataset, which consists of 105 images. Although the aim in this study is to segment tooth instances, the presented method is applicable to similar problems in other domains, such as separating the cell instances