Roberts M G, Pacheco E M B, Mohankumar R, Cootes T F, Adams J E
Imaging Science and Biomedical Engineering, University of Manchester, Stopford Building, Oxford Road, Manchester, M13 9PT, UK.
Osteoporos Int. 2010 Dec;21(12):2037-46. doi: 10.1007/s00198-009-1169-6. Epub 2010 Feb 5.
Morphometric methods of vertebral fracture diagnosis lack specificity. We used detailed shape and image texture model parameters to improve the specificity of quantitative fracture identification. Two radiologists visually classified all vertebrae for system training and evaluation. The vertebral endplates were located by a semi-automatic segmentation method to obtain classifier inputs.
Vertebral fractures are common osteoporotic fractures, but current quantitative detection methods (morphometry) lack specificity. We used detailed shape and texture information to develop more specific quantitative classifiers of vertebral fracture to improve the objectivity of vertebral fracture diagnosis. These classifiers require a detailed segmentation of the vertebral endplate, and so we investigated the use of semi-automated segmentation methods as part of the diagnosis.
The vertebrae in a training set of 360 dual energy X-ray absorptiometry images were manually segmented. The shape and image texture of vertebrae were statistically modelled using Appearance Models. The vertebrae were given a gold standard classification by two radiologists. Linear discriminant classifiers to detect fractures were trained on the vertebral appearance model parameters. Classifier performance was evaluated by cross-validation for manual and semi-automatic segmentations, the latter derived using Active Appearance Models (AAM). Results were compared with a morphometric algorithm using the signs test.
With manual segmentation, the false positive rates (FPR) at 95% sensitivity were: 5% (appearance) and 18% (morphometry). With semi-automatic segmentations the sensitivities at 5% FPR were: 88% (appearance) and 79% (morphometry).
Specificity and sensitivity are improved by using an appearance-based classifier compared to standard height ratio morphometry. An overall sensitivity loss of 7% occurs (at 95% specificity) when using a semi-automatic (AAM) segmentation compared to expert annotation, due to segmentation error. However, the classifier sensitivity is still adequate for a computer-assisted diagnosis system for vertebral fracture, especially if used in a triage approach.
椎体骨折诊断的形态测量方法缺乏特异性。我们使用详细的形状和图像纹理模型参数来提高定量骨折识别的特异性。两名放射科医生对所有椎体进行视觉分类以进行系统训练和评估。通过半自动分割方法定位椎体终板以获得分类器输入。
椎体骨折是常见的骨质疏松性骨折，但目前的定量检测方法（形态测量）缺乏特异性。我们使用详细的形状和纹理信息来开发更具特异性的椎体骨折定量分类器，以提高椎体骨折诊断的客观性。这些分类器需要对椎体终板进行详细分割，因此我们研究了使用半自动分割方法作为诊断的一部分。
对360张双能X线吸收测定图像训练集中的椎体进行手动分割。使用外观模型对椎体的形状和图像纹理进行统计建模。两名放射科医生对椎体进行金标准分类。在椎体外观模型参数上训练用于检测骨折的线性判别分类器。通过交叉验证评估手动和半自动分割的分类器性能，后者使用主动外观模型（AAM）得出。使用符号检验将结果与形态测量算法进行比较。
采用手动分割时，在95%灵敏度下的假阳性率（FPR）为：5%（外观）和18%（形态测量）。采用半自动分割时，在5%FPR下的灵敏度为：88%（外观）和79%（形态测量）。
与标准高度比形态测量相比，使用基于外观的分类器可提高特异性和灵敏度。与专家标注相比，使用半自动（AAM）分割时（在95%特异性下）总体灵敏度损失7%，这是由于分割误差所致。然而，分类器灵敏度对于椎体骨折的计算机辅助诊断系统仍然足够，特别是如果用于分诊方法。
