Non-Hodgkin lymphoma response evaluation with MRI texture classification
Non-Hodgkin lymphoma response evaluation with MRI texture classification
复制标题
DOI：
10.1186/1756-9966-28-87
复制
发表时间：
2009-06-22
影响因子：
11.3
通讯作者：
Dastidar, Prasun
中科院分区：
文献类型：
--
作者：
Harrison, Lara C. V.;Luukkaala, Tiina;Dastidar, Prasun
背景：通过定量体积分析控制反应，显示非霍奇金淋巴瘤(NHL)治疗过程中磁共振成像(MRI)纹理形态的变化。方法：在临床治疗评价期间，使用1.5T设备对19例NHL患者进行了3个成像时间点的扫描。结果：将治疗前和化疗后的NHL组织MRI纹理图像分为几个亚组，T2加权图像的非线性判别分析的正确分类准确率为96%，具有最佳的区分性。结论：成功地对MRI数据的纹理特征进行了分类，证明了纹理分析是一种潜在的定量表征淋巴瘤组织化疗疗效变化的方法。
Background: To show magnetic resonance imaging (MRI) texture appearance change in non-Hodgkin lymphoma (NHL) during treatment with response controlled by quantitative volume analysis.Methods: A total of 19 patients having NHL with an evaluable lymphoma lesion were scanned at three imaging timepoints with 1.5T device during clinical treatment evaluation. Texture characteristics of images were analyzed and classified with MaZda application and statistical tests.Results: NHL tissue MRI texture imaged before treatment and under chemotherapy was classified within several subgroups, showing best discrimination with 96% correct classification in non-linear discriminant analysis of T2-weighted images. Texture parameters of MRI data were successfully tested with statistical tests to assess the impact of the separability of the parameters in evaluating chemotherapy response in lymphoma tissue.Conclusion: Texture characteristics of MRI data were classified successfully; this proved texture analysis to be potential quantitative means of representing lymphoma tissue changes during chemotherapy response monitoring.