TY -的A2周Yi-Hong盟,山崎裕行长盟——陈Tsuhan盟,平井伯昌Toshinori盟——村上Ryuji PY - 2013 DA - 2013/06/06 TI -脑淋巴瘤和恶性胶质瘤分类亮度分布分析SP - 619658六世- 2013 AB -区分淋巴瘤和恶性胶质瘤对适当的treatmentplanning很重要。许多作品被提出,但仍存在一些问题。例如,许多作品依赖阈值一个特征值,即tonoise敏感。在其他情况下,有经验的观察者需要提取特征值,或者提供一些与系统的交互。即使专家参与,interobservervariance变成了另一个问题。另外,大多数的作品使用只有一个或fewslice (s)因为3 d肿瘤分割是耗费时间。在本文中,我们提出一个肿瘤分类系统,分析了luminancedistribution整个肿瘤区域。典型案例进行分类亮度rangethresholding和表观扩散系数(ADC)的阈值。历史进程casesare分类的支持向量机(SVM)。大多数aresemiautomatic处理元素。 Therefore, even novice users can use the system easily and get the sameresults as experts. The experiments were conducted using 40 MRI datasets. The classification accuracyof the proposed method was 91.1% without the ADC thresholding and 95.4% with the ADCthresholding. On the other hand, the baseline method, the conventional ADC thresholding,yielded only 67.5% accuracy. SN - 1748-670X UR - https://doi.org/10.1155/2013/619658 DO - 10.1155/2013/619658 JF - Computational and Mathematical Methods in Medicine PB - Hindawi Publishing Corporation KW - ER -