Department of Radiology and Biomedical Imaging, Musculoskeletal and Quantitative Imaging Research Group (MQIR), University of California, San Francisco, California 94158, USA.
Med Phys. 2010 Jan;37(1):295-302. doi: 10.1118/1.3264615.
Segmentation of trabecular bone from magnetic resonance (MR) images is a challenging task due to spatial resolution limitations, signal-to-noise ratio constraints, and signal intensity inhomogeneities. This article examines an alternative approach to trabecular bone segmentation using partial membership segmentation termed fuzzy C-means clustering incorporating local second order features for bone enhancement (BE-FCM) at multiple scales. This approach is meant to allow for a soft segmentation that accounts for partial volume effects while suppressing the influence of noise.
A soft segmentation method was developed and evaluated on three different sets of data; interscan reproducibility was evaluated on six test-retest in vivo MR scans of the proximal femur, correlation between MR and HR-pQCT measurements was evaluated on 49 in vivo scans from the distal tibia, and the potential for fracture discrimination was evaluated using MR scans of calcaneus specimens from 15 participants with and 15 participants without vertebral fracture. The algorithm was compared to fuzzy clustering using the intensity as the only feature (I-FCM) and a dual thresholding algorithm. The metric evaluated was bone volume over total volume (BV/TV) within user-defined regions of interest.
BE-FCM had a higher interscan reproducibility (rms CV: 2.0%) compared to I-FCM (5.6%) and thresholding (4.2%), and expressed higher correlation to HR-pQCT data (r = 0.79, p < 10(-11)) compared to I-FCM (r = 0.74, p < 10(-8)) and thresholding (r = 0.70, p < 10(-6)). BE-FCM was also the method that was best able to differentiate between a control and a vertebral fracture group at a 95% significance level.
The results suggest that trabecular bone segmentation by BE-FCM can provide a precise BV/TV measurement that is sensitive to pathology. The segmentation method may become useful in MR imaging-based quantification of bone microarchitecture.
由于空间分辨率限制、信噪比约束以及信号强度不均匀性，从磁共振（MR）图像中分割出小梁骨是一项具有挑战性的任务。本文研究了一种替代方法，即使用部分隶属度分割，称为模糊 C-均值聚类，结合局部二阶特征进行骨增强（BE-FCM），以实现多尺度的小梁骨分割。这种方法旨在实现软分割，以考虑部分容积效应，同时抑制噪声的影响。
开发了一种软分割方法，并在三组不同的数据上进行了评估；在六次对活体股骨近端的扫描中评估了扫描间的可重复性，在 49 次对活体胫骨远端的扫描中评估了与 HR-pQCT 测量的相关性，在 15 名有和 15 名无椎体骨折的参与者的跟骨标本的 MR 扫描中评估了骨折鉴别能力。将该算法与仅使用强度作为唯一特征的模糊聚类（I-FCM）和双阈值算法进行了比较。评估的指标是用户定义的感兴趣区域内的骨体积与总体积（BV/TV）之比。
BE-FCM 的扫描间可重复性更高（均方根 CV：2.0%），优于 I-FCM（5.6%）和阈值（4.2%），与 HR-pQCT 数据的相关性也更高（r = 0.79，p < 10(-11)），优于 I-FCM（r = 0.74，p < 10(-8)）和阈值（r = 0.70，p < 10(-6)）。BE-FCM 也是能够以 95%的显著水平区分对照组和椎体骨折组的最佳方法。
结果表明，BE-FCM 对小梁骨的分割可以提供对病理敏感的精确 BV/TV 测量。该分割方法可能成为基于磁共振成像的骨微观结构定量分析的有用方法。
