Jha Abhinav K, Rodríguez Jeffrey J, Stephen Renu M, Stopeck Alison T
College of Optical Sciences, University of Arizona, Tucson, AZ, USA.
Proc IEEE Southwest Symp Image Anal Interpret. 2010 May 23;2010:93-96. doi: 10.1109/SSIAI.2010.5483911.
In diffusion-weighted magnetic resonance imaging, accurate segmentation of liver lesions in the diffusion-weighted images is required for computation of the apparent diffusion coefficient (ADC) of the lesion, the parameter that serves as an indicator of lesion response to therapy. However, the segmentation problem is challenging due to low SNR, fuzzy boundaries and speckle and motion artifacts. We propose a clustering algorithm that incorporates spatial information and a geometric constraint to solve this issue. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.
在扩散加权磁共振成像中，为了计算病变的表观扩散系数（ADC）（该参数可作为病变对治疗反应的指标），需要在扩散加权图像中准确分割肝脏病变。然而，由于信噪比低、边界模糊以及斑点和运动伪影，分割问题具有挑战性。我们提出了一种结合空间信息和几何约束的聚类算法来解决这个问题。我们表明，与现有的分割算法相比，我们的算法具有更高的准确性。
