Vansteenkiste Ewout, Govaert Paul, Conneman Nikk, Lequin Maarten, Philips Wilfried
Department of Telecommunications and Information Processing (TELIN), Ghent University, Ghent, Belgium.
Ultrasound Med Biol. 2009 Jun;35(6):991-1004. doi: 10.1016/j.ultrasmedbio.2008.12.009. Epub 2009 Feb 28.
In this article, we present an interactive algorithm segmenting white brain matter, visible as hyperechoic flaring areas in ultrasound (US) images of preterm infants with periventricular leukomalacia (PVL). The algorithm combines both the textural properties of pathological brain tissue and mathematical morphology operations. An initial flaring area estimate is derived from a multifeature multiclassifier tissue texture classifier. This area is refined based on the structural properties of the choroid plexus, a brain feature known to have characteristics similar to flaring. Subsequently, a combination of a morphological closing, gradient and opening by reconstruction operation determines the final flaring area boundaries. Experimental results are compared with a gold standard constructed from manual flaring area delineations of 12 medical experts. In addition, we compared our algorithm to an existing active contour method. The results show our technique agrees to the gold standard with statistical significance and outperforms the existing method in accuracy. Finally, using the flaring area as a criterion we improve the sensitivity of PVL detection up to 98% as compared with the state of the art.
在本文中，我们提出了一种交互式算法，用于分割脑白质，在患有脑室周围白质软化症（PVL）的早产儿的超声（US）图像中，脑白质表现为高回声耀斑区域。该算法结合了病理性脑组织的纹理特性和数学形态学运算。初始耀斑区域估计值来自多特征多分类器组织纹理分类器。基于脉络丛的结构特性对该区域进行细化，脉络丛是一种已知具有与耀斑相似特征的脑特征。随后，形态学闭运算、梯度运算和重建开运算的组合确定了最终的耀斑区域边界。将实验结果与由12位医学专家手动绘制的耀斑区域轮廓构建的金标准进行比较。此外，我们将我们的算法与现有的主动轮廓法进行了比较。结果表明，我们的技术与金标准具有统计学意义上的一致性，并且在准确性方面优于现有方法。最后，以耀斑区域为标准，与现有技术相比，我们将PVL检测的灵敏度提高到了98%。
