Deep Learning-Based Detection of Impacted Teeth on Panoramic Radiographs.

Biomed Eng Comput Biol

School of Computer and Information Technology, Beijing Jiaotong University, Beijing, PR China.

Published: October 2024

AI Article Synopsis

  • The study aims to improve the detection of impacted teeth using a refined version of the MedSAM model, trained on 1,016 X-ray images.
  • The dataset was divided into training, validation, and testing sets, with the model focusing on tooth centers to enhance segmentation accuracy.
  • Results showed the model achieving an accuracy of 86.73% and highlighted the need for further enhancements to improve diagnostic capabilities for dental practitioners.

Article Abstract

Objective: The aim is to detect impacted teeth in panoramic radiology by refining the pretrained MedSAM model.

Study Design: Impacted teeth are dental issues that can cause complications and are diagnosed via radiographs. We modified SAM model for individual tooth segmentation using 1016 X-ray images. The dataset was split into training, validation, and testing sets, with a ratio of 16:3:1. We enhanced the SAM model to automatically detect impacted teeth by focusing on the tooth's center for more accurate results.

Results: With 200 epochs, batch size equals to 1, and a learning rate of 0.001, random images trained the model. Results on the test set showcased performance up to an accuracy of 86.73%, F1-score of 0.5350, and IoU of 0.3652 on SAM-related models.

Conclusion: This study fine-tunes MedSAM for impacted tooth segmentation in X-ray images, aiding dental diagnoses. Further improvements on model accuracy and selection are essential for enhancing dental practitioners' diagnostic capabilities.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11456186PMC
http://dx.doi.org/10.1177/11795972241288319DOI Listing

Publication Analysis

Top Keywords

impacted teeth
16
teeth panoramic
8
detect impacted
8
sam model
8
tooth segmentation
8
x-ray images
8
impacted
5
deep learning-based
4
learning-based detection
4
detection impacted
4

Similar Publications

Objective: The aim of this study is to determine the contact relationship and position of impacted mandibular third molar teeth (IMM) with the mandibular canal (MC) in panoramic radiography (PR) images using deep learning (DL) models trained with the help of cone beam computed tomography (CBCT) and DL to compare the performances of the architectures.

Methods: In this study, a total of 546 IMMs from 290 patients with CBCT and PR images were included. The performances of SqueezeNet, GoogLeNet, and Inception-v3 architectures in solving four problems on two different regions of interest (RoI) were evaluated.

View Article and Find Full Text PDF

: Impacted third molar extraction with a scalpel and rotary instruments is one of the most traumatic surgeries in dentistry. Therefore, it is necessary to discover less traumatic methods and instruments to reduce the risk of postoperative complications. : This study is reported in accordance with the CONSORT guidelines.

View Article and Find Full Text PDF

Transmigration of an impacted mandibular canine is a rare entity. Published cases are scarce. The etiology and pathogenesis remain unclear.

View Article and Find Full Text PDF

Purpose: To investigate the changes of root development before and after orthodontic traction of maxillary inverted impacted central incisors using CBCT and Mimics software.

Methods: Ten patients, who had a maxillary inverted impacted central incisor, were treated using a modified movable retractor combined with surgical eruption. Cone-beam computed tomography(CBCT) was taken before and after treatment.

View Article and Find Full Text PDF

Purpose: To analyze the safety of closed traction appliance in the treatment of impacted anterior teeth and its effect on pulp blood flow and masticatory function.

Methods: A total of 80 patients with impacted anterior teeth who received treatment from January 2017 to December 2022 were selected, and randomly divided into experimental group and control group with 40 cases in each group. The two groups of patients were treated with occlusion adjustment and orthodontic traction.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!