Markov random field modeling in posteroanterior chest radiograph segmentation.
Markov random field modeling in posteroanterior chest radiograph segmentation.
复制标题
后前胸片分割中的马尔可夫随机场建模。
DOI：
10.1118/1.598673
复制
发表时间：
1999
期刊：
影响因子：
3.8
通讯作者：
FloydJr,CE
中科院分区：
文献类型：
--
作者：
Vittitoe,NF;Vargas-Voracek,R;FloydJr,CE
此前，作者提出了一种算法，通过将每个像素标记为肺或非肺来识别数字化后前位胸片 (DCR) 中的肺部区域。在这份手稿中，该算法的固有灵活性得到了证明，因为该算法被推广到识别 DCR 中的多个解剖区域。具体来说，每个像素被分类为属于六种解剖区域类型之一：肺、膈下、心脏、纵隔、身体或背景。对于给定的一组 DCR 像素灰度值，该算法通过概率方法确定最佳的像素分类集，该概率方法定义为最大化条件分布的特定分割。使用空间变化的马尔可夫随机场 (MRF) 模型，该模型结合了每种可能区域类型的空间和纹理信息。 MRF 建模提供了 的形式，并且迭代条件模式用于收敛到分布最大值，从而获得给定 DCR 的最佳分割。结果表明，该算法能够正确分类 DCR 中 90.0%±3.4% 的像素。
Previously, the authors presented an algorithm that identifies lung regions in a digitized posteroanterior chest radiograph (DCR) by labeling each pixel as either lung or nonlung. In this manuscript, the inherent flexibility of this algorithm is demonstrated as the algorithm is generalized to identify multiple anatomical regions in a DCR. Specifically, each pixel is classified as belonging to one of six anatomical region types: lung, subdiaphragm, heart, mediastinum, body, or background. The algorithm determines the optimal set of pixel classifications, for a given set of DCR pixel gray level valuesyvia a probabilistic approach that defines as the particular segmentation that maximizes the conditional distribution A spatially varying Markov random field (MRF) model is used that incorporates spatial and textural information of each possible region type. MRF modeling provides the form of and Iterated Conditional Modes is used to converge to the distribution maximum of thus obtaining the optimal segmentation for a given DCR. Results show the algorithm being able to correctly classify 90.0%±3.4% of the pixels in a DCR.