Segmentation of dental cone-beam CT scans affected by metal artifacts using a mixed-scale dense convolutional neural network

J. Minnema, M. van Eijnatten, A.A. Hendriksen, N. Liberton, D.M. Pelt, K.J. Batenburg, T. Forouzanfar, J. Wolff

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Purpose: In order to attain anatomical models, surgical guides and implants for computer-assisted surgery, accurate segmentation of bony structures in cone-beam computed tomography (CBCT) scans is required. However, this image segmentation step is often impeded by metal artifacts. Therefore, this study aimed to develop a mixed-scale dense convolutional neural network (MS-D network) for bone segmentation in CBCT scans affected by metal artifacts.
Method: Training data were acquired from 20 dental CBCT scans affected by metal artifacts. An experienced medical engineer segmented the bony structures in all CBCT scans using global thresholding and manually removed all remaining noise and metal artifacts. The resulting gold standard segmentations were used to train an MS-D network comprising 100 convolutional layers using far fewer trainable parameters than alternative convolutional neural network (CNN) architectures. The bone segmentation performance of the MS-D network was evaluated using a leave-2-out scheme and compared with a clinical snake evolution algorithm and two state-of-the-art CNN architectures (U-Net and ResNet). All segmented CBCT scans were subsequently converted into standard tessellation language (STL) models and geometrically compared with the gold standard.
Results: CBCT scans segmented using the MS-D network, U-Net, ResNet and the snake evolution algorithm demonstrated mean Dice similarity coefficients of 0.87 ± 0.06, 0.87 ± 0.07, 0.86 ± 0.05, and 0.78 ± 0.07, respectively. The STL models acquired using the MS-D network, U-Net, ResNet and the snake evolution algorithm demonstrated mean absolute deviations of 0.44 mm ± 0.13 mm, 0.43 mm ± 0.16 mm, 0.40 mm ± 0.12 mm and 0.57 mm ± 0.22 mm, respectively. In contrast to the MS-D network, the ResNet introduced wave-like artifacts in the STL models, whereas the U-Net incorrectly labeled background voxels as bone around the vertebrae in 4 of the 9 CBCT scans containing vertebrae. Conclusion: The MS-D network was able to accurately segment bony structures in CBCT scans affected by metal artifacts.
Original languageEnglish
Pages (from-to)5027-5035
JournalMedical Physics
Volume46
Issue number11
DOIs
Publication statusPublished - Nov 2019

Funding

MvE and KJB acknowledge financial support from the Netherlands Organisation for Scientific Research (NWO), project number 639.073.506.

FundersFunder number
Nederlandse Organisatie voor Wetenschappelijk Onderzoek639.073.506

    Fingerprint

    Dive into the research topics of 'Segmentation of dental cone-beam CT scans affected by metal artifacts using a mixed-scale dense convolutional neural network'. Together they form a unique fingerprint.

    Cite this