Ventilation-Based Segmentation of the Lungs Using Hyperpolarized 3He MRI
Ventilation-Based Segmentation of the Lungs Using Hyperpolarized 3He MRI
复制标题
DOI：
10.1002/jmri.22738
复制
发表时间：
2011-10-01
影响因子：
4.4
通讯作者：
Gee, James C.
中科院分区：
文献类型：
--
作者：
Tustison, Nicholas J.;Avants, Brian B.;Gee, James C.
目的：建立He-3磁共振成像（MRI）通气肺容量自动分割方法。材料与方法：每个受试者的计算处理（CP）包括以下三个基本步骤：1)非均匀性偏差校正，2)全肺分割，3)肺分割细分为相似通气区域。评估包括两个比较分析：i)比较43名受试者中两名人类读者评分的缺陷数量，ii)同时真实性和性能水平估计（STAPLE）在18名受试者中，由四名人类读者手动分割通风缺陷。结果：CP与1号读写器、CP与2号读写器的通气缺陷数（ICC = 0.86）、CP与2号读写器的通气缺陷数（ICC = 0.85）、CP与2号读写器的通气缺陷数（ICC = 0.97）均有极好的相关性。第二次分析的STAPLE结果得出以下敏感性/特异性数字：CP（0.898/0.905）、放射科医师1号（0.743/0.897）、放射科医师2号（0.501/0.985）、放射科医师3号（0.898/0.848）和第一作者（0.600/0.984）。结论：我们开发并评估了一种自动量化3He MRI通气肺体积的方法。研究结果强烈表明，我们提出的算法处理可能是一种可靠的、自动的定量通风缺陷的方法。
Purpose: To develop an automated segmentation method to differentiate the ventilated lung volume on He-3 magnetic resonance imaging (MRI).Materials and Methods: Computational processing (CP) for each subject consisted of the following three essential steps: 1) inhomogeneity bias correction, 2) whole lung segmentation, and 3) subdivision of the lung segmentation into regions of similar ventilation. Evaluation consisted of two comparative analyses: i) comparison of the number of defects scored by two human readers in 43 subjects, and ii) simultaneous truth and performance level estimation (STAPLE) in 18 subjects in which the ventilation defects were manually segmented by four human readers.Results: There was excellent correlation between the number of ventilation defects tabulated by CP and reader #1 (intraclass correlation coefficient [ICC] = 0.86), CP and reader #2 (ICC = 0.85), and between the two readers (ICC = 0.97). The STAPLE results from the second analysis yielded the following sensitivity/specificity numbers: CP (0.898/0.905), radiologist #1 (0.743/0.897), radiologist #2 (0.501/0.985), radiologist #3 (0.898/0.848), and the first author (0.600/0.984).Conclusion: We developed and evaluated an automated method for quantifying the ventilated lung volume on 3He MRI. The findings strongly indicate that our proposed algorithmic processing may be a reliable, automatic method for quantitating ventilation defects.