Velthuizen R P, Clarke L P, Phuphanich S, Hall L O, Bensaid A M, Arrington J A, Greenberg H M, Silbiger M L
Department of Radiology, University of South Florida, Tampa 33624, USA.
J Magn Reson Imaging. 1995 Sep-Oct;5(5):594-605. doi: 10.1002/jmri.1880050520.
We examined unsupervised methods of segmentation of MR images of the brain for measuring tumor volume in response to treatment. Two clustering methods were used: fuzzy c-means and a nonfuzzy clustering algorithm. Results were compared with volume segmentations by two supervised methods, k-nearest neighbors and region growing, and all results were compared with manual labelings. Results of individual segmentations are presented as well as comparisons on the application of the different methods with 10 data sets of patients with brain tumors. Unsupervised segmentation is preferred for measuring tumor volumes in response to treatment, as it eliminates operator dependency and may be adequate for delineation of the target volume in radiation therapy. Some obstacles need to be overcome, in particular regarding the detection of anatomically relevant tissue classes. This study shows that these improvements are possible.
我们研究了用于测量脑肿瘤治疗反应中肿瘤体积的磁共振成像（MR）图像的无监督分割方法。使用了两种聚类方法：模糊c均值和非模糊聚类算法。将结果与两种监督方法（k近邻和区域生长）的体积分割结果进行比较，并将所有结果与手动标注进行比较。展示了各个分割的结果以及不同方法在10个脑肿瘤患者数据集上应用的比较情况。无监督分割在测量治疗反应中的肿瘤体积方面更受青睐，因为它消除了操作者依赖性，并且可能足以在放射治疗中勾勒靶体积。需要克服一些障碍，特别是在解剖学相关组织类别的检测方面。本研究表明这些改进是可能的。
