Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN
Accurate and automatic segmentation of individual tooth is critical for computer-aided analysis towards clinical decision support and treatment planning. Three-dimensional reconstruction of individual tooth after the segmentation also plays an important role in simulation in digital orthodontics. Ho...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9083982/ |
id |
doaj-f6bdfc8d663b4777a2807a5bd607ba65 |
---|---|
record_format |
Article |
spelling |
doaj-f6bdfc8d663b4777a2807a5bd607ba652021-03-30T02:15:12ZengIEEEIEEE Access2169-35362020-01-018972969730910.1109/ACCESS.2020.29917999083982Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCNYanlin Chen0https://orcid.org/0000-0003-1016-3535Haiyan Du1https://orcid.org/0000-0001-5781-7941Zhaoqiang Yun2https://orcid.org/0000-0002-6367-4403Shuo Yang3https://orcid.org/0000-0003-2792-4708Zhenhui Dai4https://orcid.org/0000-0002-8711-6502Liming Zhong5https://orcid.org/0000-0002-0048-7838Qianjin Feng6https://orcid.org/0000-0003-0770-9189Wei Yang7https://orcid.org/0000-0002-2161-3231School of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaStomatological Hospital, Southern Medical University, Guangzhou, ChinaDepartment of Radiotherapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaAccurate and automatic segmentation of individual tooth is critical for computer-aided analysis towards clinical decision support and treatment planning. Three-dimensional reconstruction of individual tooth after the segmentation also plays an important role in simulation in digital orthodontics. However, it is difficult to automatically segment individual tooth in cone beam computed tomography (CBCT) images due to the blurring boundaries of neighboring teeth and the similar intensities between teeth and mandible bone. In this work, we propose the use of a multi-task 3D fully convolutional network (FCN) and marker-controlled watershed transform (MWT) to segment individual tooth. The multi-task FCN learns to simultaneously predict the probability of tooth region and the probability of tooth surface. Through the combination of the tooth probability gradient map and the surface probability map as the input image, MWT is used to automatically separate and segment individual tooth. Twenty-five dental CBCT scans are used in the study. The average Dice similarity coefficient, Jaccard index, and relative volume difference are 0.936 (±0.012), 0.881 (±0.019), and 0.072 (±0.027), respectively, and the average symmetric surface distance is 0.363 (±0.145) mm for our method. The experimental results demonstrate that the multi-task 3D FCN combined with MWT can segment individual tooth of various types in dental CBCT images.https://ieeexplore.ieee.org/document/9083982/Individual tooth segmentationdental CBCTdeep learningmarker-controlled watershed transform |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yanlin Chen Haiyan Du Zhaoqiang Yun Shuo Yang Zhenhui Dai Liming Zhong Qianjin Feng Wei Yang |
spellingShingle |
Yanlin Chen Haiyan Du Zhaoqiang Yun Shuo Yang Zhenhui Dai Liming Zhong Qianjin Feng Wei Yang Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN IEEE Access Individual tooth segmentation dental CBCT deep learning marker-controlled watershed transform |
author_facet |
Yanlin Chen Haiyan Du Zhaoqiang Yun Shuo Yang Zhenhui Dai Liming Zhong Qianjin Feng Wei Yang |
author_sort |
Yanlin Chen |
title |
Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN |
title_short |
Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN |
title_full |
Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN |
title_fullStr |
Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN |
title_full_unstemmed |
Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN |
title_sort |
automatic segmentation of individual tooth in dental cbct images from tooth surface map by a multi-task fcn |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Accurate and automatic segmentation of individual tooth is critical for computer-aided analysis towards clinical decision support and treatment planning. Three-dimensional reconstruction of individual tooth after the segmentation also plays an important role in simulation in digital orthodontics. However, it is difficult to automatically segment individual tooth in cone beam computed tomography (CBCT) images due to the blurring boundaries of neighboring teeth and the similar intensities between teeth and mandible bone. In this work, we propose the use of a multi-task 3D fully convolutional network (FCN) and marker-controlled watershed transform (MWT) to segment individual tooth. The multi-task FCN learns to simultaneously predict the probability of tooth region and the probability of tooth surface. Through the combination of the tooth probability gradient map and the surface probability map as the input image, MWT is used to automatically separate and segment individual tooth. Twenty-five dental CBCT scans are used in the study. The average Dice similarity coefficient, Jaccard index, and relative volume difference are 0.936 (±0.012), 0.881 (±0.019), and 0.072 (±0.027), respectively, and the average symmetric surface distance is 0.363 (±0.145) mm for our method. The experimental results demonstrate that the multi-task 3D FCN combined with MWT can segment individual tooth of various types in dental CBCT images. |
topic |
Individual tooth segmentation dental CBCT deep learning marker-controlled watershed transform |
url |
https://ieeexplore.ieee.org/document/9083982/ |
work_keys_str_mv |
AT yanlinchen automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT haiyandu automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT zhaoqiangyun automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT shuoyang automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT zhenhuidai automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT limingzhong automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT qianjinfeng automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn AT weiyang automaticsegmentationofindividualtoothindentalcbctimagesfromtoothsurfacemapbyamultitaskfcn |
_version_ |
1724185588250181632 |