Image Segmentation of Tooth and Alveolar Bone with the Level Set Model

doi:10.11938/cjmr20202827

Abstract

Abstract:

Segmentation of tooth and alveolar bone from the cone beam computed tomography (CBCT) images provides the basic data for the three-dimensional reconstruction and visualization of bone structure. In this paper, according to the characteristics of tooth and alveolar bone, an improved potential well function was combined with the level set model for segmentation of tooth and alveolar bone, overcoming the defects of 'stop evolution' or 'too fast evolution' that might occur with the use of conventional potential well functions. Since it is difficult to effectively filter out the noises in CBCT image with the single variance Gaussian filter, a multiple small variance Gaussian filter stack was used to preprocess the image. As the contours of the same tooth in adjacent images of the image sequence showed only little changes, the segmentation result of the current layer was taken as the initial contour of the curve evolution for the next layer to reduce the times of iteration and increase the speed of segmentation. In addition, the algorithm is also used to segment a single tooth in magnetic resonance image of oral cavity successfully.

Key words: level set, potential well function, image segmentation, tooth and alveolar bone

CLC Number:

TP391.3

Qin-yi SHI,Fang YAN,Yang YANG,Yue-fu CHEN,Xiao-lang LIN,Yuan-jun WANG. Image Segmentation of Tooth and Alveolar Bone with the Level Set Model[J]. Chinese Journal of Magnetic Resonance, 2021, 38(2): 182-193.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 1

Fig.8

Fig.9

Fig.10

References 17

1	OSHER S , SETHIAN J . Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulations[J]. Comput Phys, 1988, 79 (1): 12- 49. doi: 10.1016/0021-9991(88)90002-2
2	GAO H , CHAE O . Individual tooth segmentation from CT images using level set method with shape and intensity prior[J]. Pattern Recogn, 2010, 43 (7): 2407- 2417.
3	ZHANG K H , SONG H H , ZHANG L . Active contours driven by local image fitting energy[J]. Pattern Recogn, 2010, 43 (4): 1199- 1206. doi: 10.1016/j.patcog.2009.10.010
4	WANG Y J , LIU S W , WANG G , et al. Accurate tooth segmentation with improved hybrid active contour model[J]. Phys Med Biol, 2018, 64 (1): 015012. doi: 10.1088/1361-6560/aaf441
5	LI C M , XU C Y , GUI C F , et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Trans Image Process, 2010, 19 (12): 3243- 3254. doi: 10.1109/TIP.2010.2069690
6	WANG G , WANG Y J . Development of teeth segmentation from computed tomography images using level set method[J]. Journal of Computer Applications, 2016, 36 (3): 827- 832. doi: 10.3969/j.issn.1001-3695.2016.03.042
	汪葛, 王远军. 基于水平集的牙齿CT图像分割技术[J]. 计算机应用, 2016, 36 (3): 827- 832. doi: 10.3969/j.issn.1001-3695.2016.03.042
7	GAO H , OKSAM CHAE O . Individual tooth segmentation from CT images using level set method with shape and intensity prior[J]. Pattern Recogn, 2010, 43 (7): 2406- 2417. doi: 10.1016/j.patcog.2010.01.010
8	RAN D M , YAN J Y , CUI Y Y , et al. Ultrasound image segmentation of thyroid gland based on bilateral filters-distance regularized level[J]. Journal of Biomedical Engineering Research, 2019, 38 (2): 170- 175.
	冉冬梅, 严加勇, 崔崤峣, 等. 基于双边滤波-距离正则化水平集演化算法的甲状腺超声图像分割[J]. 生物医学工程研究, 2019, 38 (2): 170- 175.
9	SUN C , XU Y L , BI D Y , et al. Distance regularised level set method using v-potential well function[J]. Computer Applications and Software, 2013, 30 (4): 271- 274. doi: 10.3969/j.issn.1000-386x.2013.04.078
	孙超, 许悦雷, 毕笃彦, 等. 采用V势阱函数的距离归一化水平集算法[J]. 计算机应用与软件, 2013, 30 (4): 271- 274. doi: 10.3969/j.issn.1000-386x.2013.04.078
10	WANG D , HE K , ZHANG X . The level set image segmentation on sequential filtering[J]. Journal of Sichuan University (Natural Science Edition), 2016, 53 (3): 518- 525.
	王丹, 何坤, 张旭. 基于序贯滤波的水平集图像分割[J]. 四川大学学报(自然科版), 2016, 53 (3): 518- 525.
11	ZHONG L , ZHOU Y F , ZHANG X F , et al. Image segmentation by level set evolution with region consistency constraint[J]. Applied Mathematics: A Journal of Chinese Universities, 2017, 32 (4): 422- 442. doi: 10.1007/s11766-017-3534-0
12	WEI C C , YI X M . An improved method for image segmentation based on DRLSE level set[J]. Journal of Graphics, 2019, 40 (5): 885- 891.
	魏晨晨, 羿旭明. 基于改进DRLSE水平集模型的图像分割[J]. 图学学报, 2019, 40 (5): 885- 891.
13	WENG G R , HE Z Y . Active contour model based on adaptive sign function[J]. Journal of Software, 2019, 30 (12): 3892- 3906.
	翁桂荣, 何志勇. 基于自适应符号函数的主动轮廓模型[J]. 软件学报, 2019, 30 (12): 3892- 3906.
14	CHEN Y M , TAGARE H D , THIRUVENKADAM S , et al. Using prior shapes in geometric active contours in a variational framework[J]. Int J Comput Vision, 2002, 50 (3): 315- 328. doi: 10.1023/A:1020878408985
15	SAHOO P K , SOLTANI S , WONG A K C , et al. A survey ofthresholding techniques[J]. Computer Vision, Grapgics, and Image Processing, 1988, 41 (2): 233- 260. doi: 10.1016/0734-189X(88)90022-9
16	WANG G , WANG Y J , LIU Y , et al. Fast and robust segmentation of individual tooth crown from cone beam computed tomography images[J]. J Med Imag Health In, 2017, 7 (2): 355- 363.
17	HEIMANN T , VAN G B , STYNER M A , et al. Comparison and evaluation of methods for liver segmentation from CT datasets[J]. IEEE Trans Med Imaging, 2009, 28 (8): 1251- 1265. doi: 10.1109/TMI.2009.2013851

	组别	1	2	3	4	5	6	7	8	9	10	平均值	标准差
本文算法	VOE/%	8.84	8.36	9.42	8.41	8.77	8.01	6.13	10.32	9.57	8.23	8.61	1.06
	运算时间/s	15.32	15.04	14.33	14.34	15.30	14.68	15.92	14.88	14.23	14.28	14.83	0.54
DRLSE	VOE/%	16.02	16.88	18.32	15.60	9.66	15.50	8.73	18.23	16.53	13.77	14.92	3.13
	运算时间/s	16.65	16.23	15.99	16.77	15.34	14.67	15.66	17.33	18.19	14.83	16.16	1.05

[1]	Ying LIU,Yi-yun GUO,Jing-cong CHEN,Hao-wei ZHANG. Automatic Precise Segmentation of Cerebellopontine Angle Tumor Based on Faster-RCNN and Level-Set Method [J]. Chinese Journal of Magnetic Resonance, 2021, 38(3): 381-391.
[2]	Shi-ju YAN,Yong-sen HAN,Guang-yu TANG. An Improved Level Set Algorithm for Prostate Region Segmentation [J]. Chinese Journal of Magnetic Resonance, 2021, 38(3): 356-366.
[3]	ZHU Ze-hua, YAN Shi-ju, RUAN Yuan, HAN Bang-min. Segmentation of Prostate Magnetic Resonance Images Based on an Improved Distance Regularized Level Set Evolution (DRLSE) Model [J]. Chinese Journal of Magnetic Resonance, 2020, 37(4): 447-455.
[4]	GONG Jin-chang, WANG Yu, WANG Yuan-jun. A Method for Segmentation of Glioma on Multimodal Magnetic Resonance Images Based on Wavelet Fusion and Deep Learning [J]. Chinese Journal of Magnetic Resonance, 2020, 37(2): 131-143.
[5]	XIAO Liang, LOU Yu-kun, ZHOU Hang-yu. A U-Net Network-Based Rapid Construction of Knee Models for Specific Absorption Rate Estimation [J]. Chinese Journal of Magnetic Resonance, 2020, 37(2): 144-151.
[6]	ZHANG Xue-ying, WANG Cheng-long, XIE Hai-bin, ZHANG Cheng-xiu, MA Chao, LU Jian-ping, YANG Guang. Parallel Segmentation and Tracking Algorithm for Magnetic Resonance Angiography Images Based on GPU [J]. Chinese Journal of Magnetic Resonance, 2016, 33(4): 570-580.