Van Leemput Koen
Helsinki Medical Imaging Center, Helsinki University Central Hospital, Finland.
Med Image Comput Comput Assist Interv. 2006;9(Pt 1):704-11. doi: 10.1007/11866565_86.
This paper addresses the problem of creating probabilistic brain atlases from manually labeled training data. We propose a general mesh-based atlas representation, and compare different atlas models by evaluating their posterior probabilities and the posterior probabilities of their parameters. Using such a Baysian framework, we show that the widely used "average" brain atlases constitute relatively poor priors, partly because they tend to overfit the training data, and partly because they do not allow to align corresponding anatomical features across datasets. We also demonstrate that much more powerful representations can be built using content-adaptive meshes that incorporate non-rigid deformation field models. We believe extracting optimal prior probability distributions from training data is crucial in light of the central role priors play in many automated brain MRI analysis techniques.
本文探讨了从手动标注的训练数据创建概率性脑图谱的问题。我们提出了一种基于网格的通用图谱表示方法，并通过评估不同图谱模型的后验概率及其参数的后验概率来比较这些模型。使用这样的贝叶斯框架，我们表明广泛使用的“平均”脑图谱构成的先验相对较差，部分原因是它们往往过度拟合训练数据，部分原因是它们不允许跨数据集对齐相应的解剖特征。我们还证明，使用包含非刚性变形场模型的内容自适应网格可以构建更强大的表示。鉴于先验在许多自动脑MRI分析技术中所起的核心作用，我们认为从训练数据中提取最优先验概率分布至关重要。
