基于双层回归森林模型的头影测量图像结构特征点自动定位

doi:10.3969/j.issn.0255-8297.2019.04.005

应用科学学报 ›› 2019, Vol. 37 ›› Issue (4): 481-489.doi: 10.3969/j.issn.0255-8297.2019.04.005

基于双层回归森林模型的头影测量图像结构特征点自动定位

秦臻¹, 戴修斌², 谢理哲³

1. 南京邮电大学通信与信息工程学院, 南京 210003;
2. 南京邮电大学地理与生物信息学院, 南京 210023;
3. 南京医科大学口腔疾病江苏省重点实验室, 南京 210096

收稿日期:2018-06-14 修回日期:2018-12-24 出版日期:2019-07-31 发布日期:2019-10-11
通信作者: 戴修斌,副教授,研究方向:医学图像处理,E-mail:daixb@njupt.edu.cn E-mail:daixb@njupt.edu.cn
基金资助:
国家自然科学基金（No.31671006，No.61671255）；江苏省青蓝工程计划基金；江苏省六大人才高峰项目基金（No.Grant JY-058）；南京邮电大学1311人才项目基金资助

Anatomical Landmark Localization in Lateral Cephalograms by Using Two-Layer Regression Forests

QIN Zhen¹, DAI Xiubin², XIE Lizhe³

1. College of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;
2. College of Geographic and Biologic Information, Nanjing University of Posts and Telecommunications, Nanjing 210023, China;
3. Jiangsu Province Key Laboratory of Oral Disease, Nanjing Medical University, Nanjing 210096, China

Received:2018-06-14 Revised:2018-12-24 Online:2019-07-31 Published:2019-10-11

摘要/Abstract

摘要： 为了实现X射线头影测量图像中结构特征点的自动定位，提出一种基于双层回归森林模型的头影测量图像结构特征点自动定位方法.首先从图像中提取外观特征训练第1层回归森林模型，通过该模型生成针对当前特征点位置的偏移距离图；然后从偏移距离图中提取上下文特征，并结合外观特征训练第2层回归森林模型；接着将双层回归森林模型用于待检测的X射线头影测量图像，预测出图像中每个像素关于目标特征点的偏移距离；最后根据回归投票方法求得结构特征点位置.实验结果表明，基于双层回归森林模型的自动定位方法能较准确地获得头影测量图像中结构特征点的位置.

关键词: 头影测量图像, 结构特征点检测, 上下文特征, 回归森林

Abstract: To automatically detect anatomical landmarks in cephalometric X-Ray images, a context-aware landmark detection method using two-layer regression forest models is proposed. First, it extracts appearance features from images to train the first-layer regression forest model, which can be used to generate a displacement map for each landmark per training image. Second, from the displacement maps, the context features are computed and combined with appearance features to train the second-layer regression forest. Then, by exerting the trained two-layer regression forest model on the new cephalometric X-Ray images to be processed, the displacement vectors of all pixels to each target landmark will be produced. Finally, the proposed method uses regression voting to acquire the landmark position in the testing image. Experimental results show that the proposed method has good performance in the detection of cephalometric landmarks in dental X-Ray images.

Key words: lateral cephalogram, anatomical landmark detection, context feature, regression forest

中图分类号:

TP391

秦臻, 戴修斌, 谢理哲. 基于双层回归森林模型的头影测量图像结构特征点自动定位[J]. 应用科学学报, 2019, 37(4): 481-489.

QIN Zhen, DAI Xiubin, XIE Lizhe. Anatomical Landmark Localization in Lateral Cephalograms by Using Two-Layer Regression Forests[J]. Journal of Applied Sciences, 2019, 37(4): 481-489.

参考文献

[1] Codari M, Caffini M, Tartaglia G M, Sforza C, Baselli G. Computer-aided cephalometric landmark annotation for CBCT data[J]. International Journal of Computer Assisted Radiology and Surgery, 2017, 12(1):113-121.
[2] Chen C, Xie W, Franke J, Grutzner P A, Nolte L P, Zheng G. Automatic X-Ray landmark detection and shape segmentation via data-driven joint estimation of image displacements[J]. Medical Image Analysis, 2014, 18(3):487-499.
[3] Gayathri V, Menon H P. Challenges in edge extraction of dental X-Ray images using image processing algorithms-a review[J]. International Journal of Computer Science & Information Technology, 2014, 5(4):5355-5358.
[4] Huh J, Nam H, Kim J, Park J, Shin S. Studies of automatic dental cavity detection system as an auxiliary tool for diagnosis of dental caries in digital X-Ray image[J]. Progress in Medical Physics, 2015, 25(1):52-58.
[5] Kaur A, Singh C. Automatic cephalometric landmark detection using Zernike moments and template matching[J]. Signal, Image and Video Processing, 2015, 9(1):117-132.
[6] Seres L, Varga E Jr, Kocsis A, Rasko Z, Bago B, Varga E, Piffko J. Correction of a severe facial asymmetry with computerized planning and with the use of a rapid prototyped surgical template:a case report/technique article[J]. Head Face Medicine, 2014, 10(1):27-36.
[7] Sari I P, Widayati R, Priaminiarti M, Danudirdjo D, Mengko T L. Initial estimation of landmark location for automated cephalometric analysis using template matching method[C]//International Conference on Instrumentation, 2016:159-162.
[8] Mirzaalian H, Hamarneh G. Automatic globally-optimal pictorial structures with random decision forest based likelihoods for cephalometric X-Ray landmark detection[C]//International Symposium on Biomedical Imaging 2014:Automatic Cephalometric X-Ray Landmark Detection Challenge, 2014:1-12.
[9] Ibragimov B, Likar B, Pernus F, Vrtovec T. Shape representation for efficient landmarkbased segmentation in 3-D[J]. IEEE Transactions on Medical Imaging, 2014, 33(4):861-874.
[10] Chu C, Chen C, Nolte L P, Zheng G. Fully automatic cephalometric X-Ray landmark detection using random forest regression and sparse shape composition[C]//International Symposium on Biomedical Imaging 2014:Automatic Cephalometric X-Ray Landmark Detection Challenge, 2014:13-18.
[11] Lindner C, Wang C W, Huang C T, Li C H, Chang S W, Cootes T F. Fully automatic system for accurate localization and analysis of cephalometric landmarks in lateral cephalograms[J]. Scientific Reports, 2016, 6:33581.
[12] Gao Y, Wang L, Shao Y, Shen D. Learning distance transform for boundary detection and deformable segmentation in CT prostate images[C]//International Workshop on Machine Learning in Medical Imaging, 2014:93-100.
[13] Dai X, Gao Y, Shen D. Online updating of context-aware landmark detectors for prostate localization in daily treatment CT images[J]. Medical Physics, 2015, 42(5):2594-2606.
[14] Wang C W, Huang C T, Lee J H. A benchmark for comparison of dental radiography analysis algorithms[J]. Medical Image Analysis, 2016, 31(6):63-76.
[15] Wang C W, Huang C T, Hsieh M C. Evaluation and comparison of anatomical landmark detection methods for cephalometric X-Ray images:a grand challenge[J]. IEEE Transactions on Medical Imaging, 2015, 34(9):1890-1900.
[16] Chen C, Zheng G. Automatic X-Ray landmark detection and shape segmentation via datadriven joint estimation of image displacements[J]. Medical Image Analysis, 2014, 18(3):1-24.

基于双层回归森林模型的头影测量图像结构特征点自动定位

Anatomical Landmark Localization in Lateral Cephalograms by Using Two-Layer Regression Forests

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	姚汝婧, 杨磊, 杨涛, 胡应鑫, 田强, 吴偶. 基于改进Ising模型的心理量表大数据分析[J]. 应用科学学报, 2020, 38(3): 339-352.
[2]	蒋沁吟, 张熙. 基于特定主题的社交网络影响力评估方法[J]. 应用科学学报, 2020, 38(3): 353-366.
[3]	张彤彤, 董军宇, 赵浩然, 李琼, 孙鑫. 基于知识蒸馏的轻量型浮游植物检测网络[J]. 应用科学学报, 2020, 38(3): 367-376.
[4]	魏子洋, 赵志宏, 赵敬娇. 改进Faster R-CNN算法及其在车辆检测中的应用[J]. 应用科学学报, 2020, 38(3): 377-387.
[5]	孙容海, 施林甫, 俞春强, 劳欢, 唐振军. 面向密文图像信息隐藏的随机插值方法[J]. 应用科学学报, 2020, 38(3): 419-430.
[6]	王大千, 崔荣一, 金璟璇. 基于视觉关注模型与多尺度MSER的自然场景文本检测[J]. 应用科学学报, 2020, 38(3): 496-506.
[7]	杨高强, 李晟, 张新鹏. 基于方向场的形变指纹检测[J]. 应用科学学报, 2019, 37(6): 775-782.
[8]	余淑真, 欧巧凤, 熊邦书, 陈垚锋. 基于散焦图像的大视场立体视觉标定方法[J]. 应用科学学报, 2019, 37(6): 795-805.
[9]	崔三帅, 毛毛雨, 林晓丹, 康显桂. 图像视频中ENF信号的分析及应用综述[J]. 应用科学学报, 2019, 37(5): 573-589.
[10]	刘伟, 章琬苓, 项世军. 基于LBP-MDCT和CNN的人脸活体检测算法[J]. 应用科学学报, 2019, 37(5): 609-617.
[11]	屈凌峰, 陈帆, 和红杰, 袁源. 基于位平面-块置乱的图像加密算法安全性分析[J]. 应用科学学报, 2019, 37(5): 631-642.
[12]	赵琰, 周晓炜, 沈麒. 基于对立色与显著区域的紧凑图像哈希算法[J]. 应用科学学报, 2019, 37(5): 691-703.
[13]	张永胜, 田华伟, 肖延辉, 郝昕泽, 张明旺. 基于三方加权稀疏编码模型的PRNU提取算法[J]. 应用科学学报, 2019, 37(5): 704-710.
[14]	朱翌明, 陈帆, 和红杰, 陈鸿佑. 基于秘密信息驱动的正交GAN信息隐藏模型[J]. 应用科学学报, 2019, 37(5): 721-732.
[15]	王俊祥, 毛宁雄, 赵怡, 王春桃. 面向全容量的高性能彩色图像可逆信息隐藏算法[J]. 应用科学学报, 2019, 37(5): 744-760.