Abstract：Along with the rapid development of imaging techniques for small animals, more and more images obtained from small animals need to be analyzed per day, therefore automated image analysis method has become an urgent demand. For mice images, the significant inter-subject posture variations become a major difficulty for automated image analysis. In this paper, an automatic bone joint localization method was developed for mouse micro-CT images, so as to help with posture identification of mouse body. The proposed method was composed of three steps: (1) classification random forests for rough joint localization, (2) aggregating the results of classification through regression forest, and (3) picking up landmarks in the right position by the mapping graph. The method achieved automatic bone joint localization for 49 test images of different body postures. The median localization error of the whole body CT images was 0.68 mm. The success rate of localization was 98.27%. We also demonstrated the necessity of combining classification and regression random forest and discussed the influence on localization with different number of training data. With this new method for mouse micro-CT posture identification was expected to provide helpful information for the subsequent image registration, segmentation and measurements.
屠睿博, 陈中华, 王洪凯. 基于随机森林算法的小鼠micro-CT影像中骨骼关节特征点定位[J]. 中国生物医学工程学报, 2017, 36(3): 257-266.
Tu Ruibo, Chen Zhonghua, Wang Hongkai. Bone Joints Localization in Mouse Micro-CT Images Using Random Forests Algorithm. Chinese Journal of Biomedical Engineering, 2017, 36(3): 257-266.
[1] Zhang Guanglei, Liu Fei, Pu Huangsheng, et al. Adirect method with structural priors for imaging pharmacokinetic parameters in dynamic fluorescence molecular tomography [J]. IEEE Transactions on Biomedical Engineering, 2014, 61(3): 986-990. [2] Wang Luyao, Zhu Jun, Liang Xiao, et al.Performance evaluation of the Trans-PET BioCaliburn LH system: A large FOV small-animal PET system [J]. Physics in Medicine and Biology, 2015, 60(1): 137-50. [3] Wang Huina, Liu Chengbo, Gong Xiaojing, et al. In vivo photoacoustic molecular imaging of breast carcinoma with folate receptor-targeted indocyanine green nanoprobes [J]. Nanoscale, 2014, 6(23): 14270-14279. [4] 杨昆, 李真, 杨永鑫. 小动物正电子发射断层成像仪探测器发展 [J]. 中国生物医学工程学报, 2014, 33(2): 218-226. [5] Kesner AL, Dahlbom M, Huang SC, et al. Semiautomated analysis of small-animal PET data [J]. Journal of Nuclear Medicine, 2006, 47(7): 1181-1186. [6] Baiker M, Vastenhouw B, Branderhorst W, et al. Atlas-driven scan planning for high-resolution micro-SPECT data acquisition based on multi-view photographs: a pilot study [C]// Michael IM, Kenneth HW, eds. SPIE Medical Imaging 2009: Visualization, Image-Guided Procedures, and Modeling. Lake Buena Vista: SPIE, 2009: 72611L1-72611L8. [7] Baiker M, Staring M, Löwik CWGM, et al. Automated Registration of whole-body follow-upmicro CT data of mice [C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2011.Berlin: Springer Berlin Heidelberg, 2011: 516-523. [8] Baiker M, Milles J, Dijkstra J, et al. Atlas-based whole-body segmentation of mice from low-contrast Micro-CT data [J]. Med Image Anal, 2010, 14(6): 723-737. [9] Wang H, Stout DB, Chatziioannou AF. A method of 2D/3D registration of a statistical mouse atlas with a planar X-ray projection and an optical photo [J]. Med Image Anal, 2013, 17(4): 401-416. [10] Wang H, Stout DB, Chatziioannou AF. Estimation of mouse organ locations through registration of a statistical mouse atlas with micro-CT images [J]. IEEE Trans Med Imaging, 2012, 31(1): 88-102. [11] Shotton J, Sharp T, Kipman AA, et al. Real-time human pose recognition in parts from single depth images [J]. Communications of the ACM, 2013, 56(1): 116-124. [12] Donner R, Menze BH, Bischof H, et al. Global localization of 3D anatomical structures by pre-filtered Hough forests and discrete optimization [J]. Med Image Anal, 2013, 17(8): 1304-1314. [13] 林修煅. Micro-CT成像系统及其应用研究 [D].西安:西安电子科技大学,2012. [14] 方匡南,吴见彬,朱建平,等. 随机森林方法研究综述 [J].统计与信息论坛, 2011, 26(3):32-38. [15] Van Ryzin J, Breiman L, Friedman JH, et al. Classification and Regression Trees [J]. Journal of the American Statistical Association, 1986,33(1):128-128. [16] Schapire RE. The strength of weak learnability[J].Machine Learning, 1990, 5(2): 197–227. [17] Amit Y, Geman D. Shape quantization and recognition with randomized trees [J]. Neural Computation, 1997, 9(7): 1545-1588. [18] Breiman L. Random forests [J]. Machine Learning, 2001, 45(1): 5-32. [19] 李欣海. 随机森林模型在分类与回归分析中的应用 [J]. 应用昆虫学报, 2013, 50(4): 1190-1197. [20] Criminisi A, Jamie Shotton. Decision Forests for Computer Vision and Medical Image Analysis[M].Berlin: Springer Science & Business Media, 2013:340-366. [21] Pushmeet K, Philip HST. Efficiently solving dynamic markov random fields using graph cuts [C]// IEEE International Conference on Computer Vision (ICCV 05). Beijing: IEEE, 2005: 922-929.. [22] Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2001, 23(11):1222-1239.
