A study on tooth segmentation and numbering using end-to-end deep neural networks

Abstract

Shape, number, and position of teeth are the main targets of a dentist when screening for patient’s problems on X-rays. Rather than solely relying on the trained eyes of the dentists, computational tools have been proposed to aid specialists as decision supporter for better diagnoses. When applied to X-rays, these tools are specially grounded on object segmentation and detection. In fact, the very first goal of segmenting and detecting the teeth in the images is to facilitate other automatic methods in further processing steps. Although researches over tooth segmentation and detection are not recent, the application of deep learning techniques in the field is new and has not reached maturity yet. To fill some gaps in the area of dental image analysis, we bring a thorough study on tooth segmentation and numbering on panoramic X-ray images by means of end-to-end deep neural networks. For that, we analyze the performance of four network architectures, namely, Mask R-CNN, PANet, HTC, and ResNeSt, over a challenging data set. The choice of these networks was made upon their high performance over other data sets for instance segmentation and detection. To the best of our knowledge, this is the first study on instance segmentation, detection, and numbering of teeth on panoramic dental X-rays. We found that (i) it is completely feasible to detect, to segment, and to number teeth by through any of the analyzed architectures, (ii) performance can be significantly boosted with the proper choice of neural network architecture, and (iii) the PANet had the best results on our evaluations with an mAP of 71.3% on segmentation and 74.0% on numbering, raising 4.9 and 3.5 percentage points the results obtained with Mask R-CNN.