A novel artificial intelligence-powered tool for automated root canal segmentation in single-rooted teeth on cone-beam computed tomography

IF 5.4 1区医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE

International endodontic journal Pub Date : 2025-01-28 DOI:10.1111/iej.14200

Airton Oliveira Santos-Junior, Rocharles Cavalcante Fontenele, Frederico Sampaio Neves, Mário Tanomaru-Filho, Reinhilde Jacobs

{"title":"A novel artificial intelligence-powered tool for automated root canal segmentation in single-rooted teeth on cone-beam computed tomography","authors":"Airton Oliveira Santos-Junior, Rocharles Cavalcante Fontenele, Frederico Sampaio Neves, Mário Tanomaru-Filho, Reinhilde Jacobs","doi":"10.1111/iej.14200","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Aim</h3>\n \n <p>To develop and validate an artificial intelligence (AI)-powered tool based on convolutional neural network (CNN) for automatic segmentation of root canals in single-rooted teeth using cone-beam computed tomography (CBCT).</p>\n </section>\n \n <section>\n \n <h3> Methodology</h3>\n \n <p>A total of 69 CBCT scans were retrospectively recruited from a hospital database and acquired from two devices with varying protocols. These scans were randomly assigned to the training (<i>n</i> = 31, 88 teeth), validation (<i>n</i> = 8, 15 teeth) and testing (<i>n</i> = 30, 120 teeth) sets. For the training and validation data sets, each CBCT scan was imported to the Virtual Patient Creator platform, where manual segmentation of root canals was performed by two operators, establishing the ground truth. Subsequently, the AI model was tested on 30 CBCT scans (120 teeth), and the AI-generated three-dimensional (3D) virtual models were exported in standard triangle language (STL) format. Importantly, the testing data set encompassed different types of single-rooted teeth. An experienced operator evaluated the automated segmentation, and manual refinements were made to create refined 3D models (R-AI). The AI and R-AI models were compared for performance evaluation. Additionally, 30% of the testing sample was manually segmented at two different times to compare AI-based and human segmentation methods. The time taken by each segmentation method to obtain 3D models was recorded in seconds(s) for further comparison.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The AI-driven tool demonstrated highly accurate segmentation of single-rooted teeth (Dice similarity coefficient [DSC] ranging from 89% to 93%; 95% Hausdorff distance [HD] ranging from 0.10 to 0.13 mm), with no significant impact of tooth type on accuracy metrics (<i>p</i> > .05). The AI approach outperformed the manual method (<i>p</i> < .05), showing higher DSC and lower 95% HD values. In terms of time efficiency, manual segmentation required significantly more time (2262.4 ± 679.1 s) compared to R-AI (94 ± 64.7 s) and AI (41.8 ± 12.2 s) methods (<i>p</i> < .05), representing a 54-fold decrease.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>The novel AI-based tool exhibited highly accurate and time-efficient performance in the automatic root canal segmentation on CBCT, surpassing the human performance.</p>\n </section>\n </div>","PeriodicalId":13724,"journal":{"name":"International endodontic journal","volume":"58 4","pages":"658-671"},"PeriodicalIF":5.4000,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/iej.14200","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International endodontic journal","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/iej.14200","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

Abstract

Aim

To develop and validate an artificial intelligence (AI)-powered tool based on convolutional neural network (CNN) for automatic segmentation of root canals in single-rooted teeth using cone-beam computed tomography (CBCT).

Methodology

A total of 69 CBCT scans were retrospectively recruited from a hospital database and acquired from two devices with varying protocols. These scans were randomly assigned to the training (n = 31, 88 teeth), validation (n = 8, 15 teeth) and testing (n = 30, 120 teeth) sets. For the training and validation data sets, each CBCT scan was imported to the Virtual Patient Creator platform, where manual segmentation of root canals was performed by two operators, establishing the ground truth. Subsequently, the AI model was tested on 30 CBCT scans (120 teeth), and the AI-generated three-dimensional (3D) virtual models were exported in standard triangle language (STL) format. Importantly, the testing data set encompassed different types of single-rooted teeth. An experienced operator evaluated the automated segmentation, and manual refinements were made to create refined 3D models (R-AI). The AI and R-AI models were compared for performance evaluation. Additionally, 30% of the testing sample was manually segmented at two different times to compare AI-based and human segmentation methods. The time taken by each segmentation method to obtain 3D models was recorded in seconds(s) for further comparison.

Results

The AI-driven tool demonstrated highly accurate segmentation of single-rooted teeth (Dice similarity coefficient [DSC] ranging from 89% to 93%; 95% Hausdorff distance [HD] ranging from 0.10 to 0.13 mm), with no significant impact of tooth type on accuracy metrics (p > .05). The AI approach outperformed the manual method (p < .05), showing higher DSC and lower 95% HD values. In terms of time efficiency, manual segmentation required significantly more time (2262.4 ± 679.1 s) compared to R-AI (94 ± 64.7 s) and AI (41.8 ± 12.2 s) methods (p < .05), representing a 54-fold decrease.

Conclusions

The novel AI-based tool exhibited highly accurate and time-efficient performance in the automatic root canal segmentation on CBCT, surpassing the human performance.

Abstract Image

查看原文本刊更多论文

一种新的人工智能驱动的工具，用于在锥束计算机断层上对单根牙进行自动根管分割。

目的：开发并验证一种基于卷积神经网络（CNN）的人工智能（AI）工具，用于锥形束计算机断层扫描（CBCT）对单根牙根管的自动分割。方法：回顾性地从医院数据库中招募了69个CBCT扫描，并从两种不同方案的设备中获得。这些扫描被随机分配到训练组（n = 31,88颗牙齿）、验证组（n = 8,15颗牙齿）和测试组（n = 30,120颗牙齿）。对于训练和验证数据集，每个CBCT扫描被导入到Virtual Patient Creator平台，在该平台上，由两名操作员手动进行根管分割，建立基础真相。随后，对人工智能模型进行30次CBCT扫描（120颗牙齿）测试，并以标准三角语言（STL）格式导出人工智能生成的三维（3D）虚拟模型。重要的是，测试数据集包含了不同类型的单根牙齿。一名经验丰富的操作员评估了自动分割，并进行了手动细化，以创建精细的3D模型（R-AI）。比较AI和R-AI模型的性能评价。此外，在两个不同的时间对30%的测试样本进行人工分割，以比较人工智能和人工分割方法。以秒为单位记录每种分割方法获得三维模型所需的时间，以便进一步比较。结果：人工智能驱动的工具显示出高度准确的单根牙齿分割(Dice相似系数[DSC]在89%至93%之间；95% Hausdorff距离[HD]范围为0.10至0.13 mm)，齿型对精度指标无显著影响（p < 0.05）。结论：基于人工智能的工具在CBCT自动根管分割中表现出高度的准确性和时间效率，超过了人类的表现。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International endodontic journal 医学-牙科与口腔外科

CiteScore

10.20

自引率

28.00%

发文量

195

审稿时长

4-8 weeks

期刊介绍： The International Endodontic Journal is published monthly and strives to publish original articles of the highest quality to disseminate scientific and clinical knowledge; all manuscripts are subjected to peer review. Original scientific articles are published in the areas of biomedical science, applied materials science, bioengineering, epidemiology and social science relevant to endodontic disease and its management, and to the restoration of root-treated teeth. In addition, review articles, reports of clinical cases, book reviews, summaries and abstracts of scientific meetings and news items are accepted. The International Endodontic Journal is essential reading for general dental practitioners, specialist endodontists, research, scientists and dental teachers.