標題: Automated Segmentation of Dental Calculus in Optical Coherence Tomography Images
作者: Lee, Chia-Yen
Chuang, Ching-Cheng
Chen, Guan-Jie
Huang, Chih-Chia
Lee, Shyh-Yuan
Lin, Yu-Hsien
分子醫學與生物工程研究所
Institute of Molecular Medicine and Bioengineering
關鍵字: optical coherence tomography (OCT);image analysis;segmentation;dental calculus
公開日期: 1-Jan-2018
摘要: The presence of dental calculus is highly correlated with the formation and advancement of periodontal disease. The occurrence and relapse of periodontal disease can be prevented only if dental calculus is completely removed. In this study, optical coherence tomography (OCT) is used to obtain two-dimensional cross-sectional images of tooth samples, in conjunction with a segmentation technique that enables automatic identification of dental calculus. We propose the vertical intensity transform function to correct the nonuniform instrument signal intensity caused by OCT. Afterwards, the detection ranges are defined by K-means or the Markov random field (MRF), and the candidate range is selected on the basis of mathematical morphology (MM). Finally, the features (thickness gradient, texture, and tooth surface slope) are quantified, and dental calculus is recognized and segmented. In the preliminary result, the sensitivity is 87.5%. The mean distance between the boundaries generated by the proposed algorithm and the corresponding manually delineated boundaries is 2.52 +/- 3.54 pixels. Our proposed algorithm assists physicians to determine dental calculus more easily. Doctors no longer need to rely solely on their experiences to recognize dental calculus, but can refer to specific data to assist in diagnosis.
URI: http://dx.doi.org/10.18494/SAM.2018.2053
http://hdl.handle.net/11536/148491
ISSN: 0914-4935
DOI: 10.18494/SAM.2018.2053
期刊: SENSORS AND MATERIALS
Volume: 30
起始頁: 2517
結束頁: 2529
Appears in Collections:Articles