Literature DB >> 34425172

Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography.

Pieter-Jan Verhelst1, Andreas Smolders2, Thomas Beznik2, Jeroen Meewis3, Arne Vandemeulebroucke4, Eman Shaheen3, Adriaan Van Gerven2, Holger Willems2, Constantinus Politis3, Reinhilde Jacobs5.   

Abstract

OBJECTIVE: To develop and validate a layered deep learning algorithm which automatically creates three-dimensional (3D) surface models of the human mandible out of cone-beam computed tomography (CBCT) imaging. MATERIALS &
METHODS: Two convolutional networks using a 3D U-Net architecture were combined and deployed in a cloud-based artificial intelligence (AI) model. The AI model was trained in two phases and iteratively improved to optimize the segmentation result using 160 anonymized full skull CBCT scans of orthognathic surgery patients (70 preoperative scans and 90 postoperative scans). Finally, the final AI model was tested by assessing timing, consistency, and accuracy on a separate testing dataset of 15 pre- and 15 postoperative full skull CBCT scans. The AI model was compared to user refined AI segmentations (RAI) and to semi-automatic segmentation (SA), which is the current clinical standard. The time needed for segmentation was measured in seconds. Intra- and inter-operator consistency were assessed to check if the segmentation protocols delivered reproducible results. The following consistency metrics were used: intersection over union (IoU), dice similarity coefficient (DSC), Hausdorff distance (HD), absolute volume difference and root mean square (RMS) distance. To evaluate the match of the AI and RAI results to those of the SA method, their accuracy was measured using IoU, DSC, HD, absolute volume difference and RMS distance.
RESULTS: On average, SA took 1218.4s. RAI showed a significant drop (p<0.0001) in timing to 456.5s (2.7-fold decrease). The AI method only took 17s (71.3-fold decrease). The average intra-operator IoU for RAI was 99.5% compared to 96.9% for SA. For inter-operator consistency, RAI scored an IoU of 99.6% compared to 94.6% for SA. The AI method was always consistent by default. In both the intra- and inter-operator consistency assessments, RAI outperformed SA on all metrics indicative of better consistency. With SA as the ground truth, AI and RAI scored an IoU of 94.6% and 94.4%, respectively. All accuracy metrics were similar for AI and RAI, meaning that both methods produce 3D models that closely match those produced by SA.
CONCLUSION: A layered 3D U-Net architecture deep learning algorithm, with and without additional user refinements, improves time-efficiency, reduces operator error, and provides excellent accuracy when benchmarked against the clinical standard. CLINICAL SIGNIFICANCE: Semi-automatic segmentation in CBCT imaging is time-consuming and allows user-induced errors. Layered convolutional neural networks using a 3D U-Net architecture allow direct segmentation of high-resolution CBCT images. This approach creates 3D mandibular models in a more time-efficient and consistent way. It is accurate when benchmarked to semi-automatic segmentation.
Copyright © 2021. Published by Elsevier Ltd.

Entities:  

Keywords:  Artificial Intelligence; Computer-generated 3D imaging; Cone-beam computed tomography; Mandible; Neural Network Models

Mesh:

Year:  2021        PMID: 34425172     DOI: 10.1016/j.jdent.2021.103786

Source DB:  PubMed          Journal:  J Dent        ISSN: 0300-5712            Impact factor:   4.379


  7 in total

1.  Three-dimensional maxillary virtual patient creation by convolutional neural network-based segmentation on cone-beam computed tomography images.

Authors:  Fernanda Nogueira-Reis; Nermin Morgan; Stefanos Nomidis; Adriaan Van Gerven; Nicolly Oliveira-Santos; Reinhilde Jacobs; Cinthia Pereira Machado Tabchoury
Journal:  Clin Oral Investig       Date:  2022-09-17       Impact factor: 3.606

2.  Comparison of surface- and voxel-based registration on the mandibular ramus for long-term three-dimensional assessment of condylar remodelling following orthognathic surgery.

Authors:  Michael Boelstoft Holte; Henrik Sæderup; Else Marie Pinholt
Journal:  Dentomaxillofac Radiol       Date:  2022-02-25       Impact factor: 3.525

3.  Three-dimensional quantification of skeletal midfacial complex symmetry.

Authors:  Nermin Morgan; Sohaib Shujaat; Omid Jazil; Reinhilde Jacobs
Journal:  Int J Comput Assist Radiol Surg       Date:  2022-10-22       Impact factor: 3.421

Review 4.  Personalized workflows in reconstructive dentistry-current possibilities and future opportunities.

Authors:  Tim Joda; Nicola U Zitzmann
Journal:  Clin Oral Investig       Date:  2022-03-30       Impact factor: 3.606

5.  A fully automatic AI system for tooth and alveolar bone segmentation from cone-beam CT images.

Authors:  Zhiming Cui; Yu Fang; Lanzhuju Mei; Bojun Zhang; Bo Yu; Jiameng Liu; Caiwen Jiang; Yuhang Sun; Lei Ma; Jiawei Huang; Yang Liu; Yue Zhao; Chunfeng Lian; Zhongxiang Ding; Min Zhu; Dinggang Shen
Journal:  Nat Commun       Date:  2022-04-19       Impact factor: 17.694

6.  Effect of voxel size in cone-beam computed tomography on surface area measurements of dehiscences and fenestrations in the lower anterior buccal region.

Authors:  B J van Leeuwen; P U Dijkstra; J A Dieters; H P J Verbeek; A M Kuijpers-Jagtman; Y Ren
Journal:  Clin Oral Investig       Date:  2022-05-05       Impact factor: 3.606

7.  Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.

Authors:  Maxime Gillot; Baptiste Baquero; Celia Le; Romain Deleat-Besson; Jonas Bianchi; Antonio Ruellas; Marcela Gurgel; Marilia Yatabe; Najla Al Turkestani; Kayvan Najarian; Reza Soroushmehr; Steve Pieper; Ron Kikinis; Beatriz Paniagua; Jonathan Gryak; Marcos Ioshida; Camila Massaro; Liliane Gomes; Heesoo Oh; Karine Evangelista; Cauby Maia Chaves Junior; Daniela Garib; Fábio Costa; Erika Benavides; Fabiana Soki; Jean-Christophe Fillion-Robin; Hina Joshi; Lucia Cevidanes; Juan Carlos Prieto
Journal:  PLoS One       Date:  2022-10-12       Impact factor: 3.752

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.