Guillemaud R, Brady M
Clinical Neurology Department, Radcliffe Infirmary, University of Oxford, UK.
IEEE Trans Med Imaging. 1997 Jun;16(3):238-51. doi: 10.1109/42.585758.
We propose a modification of Wells et al. technique for bias field estimation and segmentation of magnetic resonance (MR) images. We show that replacing the class other, which includes all tissue not modeled explicitly by Gaussians with small variance, by a uniform probability density, and amending the expectation-maximization (EM) algorithm appropriately, gives significantly better results. We next consider the estimation and filtering of high-frequency information in MR images, comprising noise, intertissue boundaries, and within tissue microstructures. We conclude that post-filtering is preferable to the prefiltering that has been proposed previously. We observe that the performance of any segmentation algorithm, in particular that of Wells et al. (and our refinements of it) is affected substantially by the number and selection of the tissue classes that are modeled explicitly, the corresponding defining parameters and, critically, the spatial distribution of tissues in the image. We present an initial exploration to choose automatically the number of classes and the associated parameters that give the best output. This requires us to define what is meant by "best output" and for this we propose the application of minimum entropy. The methods developed have been implemented and are illustrated throughout on simulated and real data (brain and breast MR).
我们提出了一种对Wells等人用于磁共振（MR）图像偏差场估计和分割技术的改进方法。我们表明，用均匀概率密度取代包含所有未由小方差高斯模型明确建模的组织的“其他”类别，并适当修正期望最大化（EM）算法，能显著提高结果。接下来，我们考虑MR图像中高频信息的估计和滤波，包括噪声、组织间边界和组织内微观结构。我们得出结论，后滤波比先前提出的预滤波更可取。我们观察到，任何分割算法的性能，特别是Wells等人的算法（以及我们对其的改进），会受到明确建模的组织类别的数量和选择、相应的定义参数，以及关键的图像中组织的空间分布的显著影响。我们进行了初步探索，以自动选择能给出最佳输出的类别数量和相关参数。这要求我们定义“最佳输出”的含义，为此我们提出应用最小熵。所开发的方法已得到实现，并在模拟和真实数据（脑部和乳腺MR）中进行了全面展示。
