Molecular and metabolic pattern classification for detection of brain glioma progression.
Molecular and metabolic pattern classification for detection of brain glioma progression.
复制标题
DOI：
10.1016/j.ejrad.2013.06.033
复制
发表时间：
2014-02
影响因子：
3.3
通讯作者：
Mountz, James M.
中科院分区：
文献类型：
--
作者：
Imani, Farzin;Boada, Fernando E.;Lieberman, Frank S.;Davis, Denise K.;Mountz, James M.
区分脑肿瘤进展和放射治疗引起的坏死的能力对于适当的患者管理至关重要。为了提高鉴别诊断，我们结合氟-18 2-氟-脱氧葡萄糖正电子发射断层扫描（18 F-FDG PET），质子磁共振波谱（1 H MRS）和组织学数据，开发了一个多参数机器学习模型。我们招募了12名治疗后疑似肿瘤进展的2级和3级胶质瘤患者。所有患者均行18F-FDGPET和1HMRS检查，获得肿瘤和参考区域的最大标准化摄取值（SUVmax）。生成肿瘤的胆碱（Cho）、肌酸（Cr）和N-乙酰天冬氨酸（NAA）的多个2D图。以影像学生物标志物和组织学数据为输入向量，建立支持向量机（SVM）学习模型。临床随访和多项连续MRI研究的组合作为评估临床结局的基础。评价所有载体组合的诊断准确性和交叉验证。使用受试者工作特征（ROC）图计算个体参数的最佳截止值。SVM和ROC分析均表明，SUVmax的病变是最显着的单一诊断参数（75%的准确性），其次是Cho浓度（67%的准确性）。所有配对参数的支持向量机分析显示，SUVmax和Cho浓度组合可以达到83%的准确率。病变的SUVmax与白色物质的SUVmax配对以及肿瘤Cho与肿瘤Cr配对均显示83%的准确性。这些是两种模式中最重要的配对诊断参数。结合所有四个参数并没有改善结果。然而，另外两个参数，Cho和Cr的脑实质对侧的肿瘤，准确性提高到92%。这项研究表明，支持向量机模型可以提高检测胶质瘤进展更准确地比单参数成像方法。国家癌症研究所，癌症中心支持补助补充奖，成像反应评估小组。
The ability to differentiate between brain tumor progression and radiation therapy induced necrosis is critical for appropriate patient management. In order to improve the differential diagnosis, we combined fluorine-18 2-fluoro-deoxyglucose positron emission tomography (18 F-FDG PET), proton magnetic resonance spectroscopy (1 H MRS) and histological data to develop a multi-parametric machine-learning model. We enrolled twelve post-therapy patients with grade 2 and 3 gliomas that were suspicious of tumor progression. All patients underwent 18 F-FDG PET and 1 H MRS. Maximal standardized uptake value (SUVmax) of the tumors and reference regions were obtained. Multiple 2D maps of choline (Cho), creatine (Cr), and N-acetylaspartate (NAA) of the tumors were generated. A support vector machine (SVM) learning model was established to take imaging biomarkers and histological data as input vectors. A combination of clinical follow-up and multiple sequential MRI studies served as the basis for assessing the clinical outcome. All vector combinations were evaluated for diagnostic accuracy and cross validation. The optimal cutoff value of individual parameters was calculated using Receiver operating characteristic (ROC) plots. The SVM and ROC analyses both demonstrated that SUVmax of the lesion was the most significant single diagnostic parameter (75% accuracy) followed by Cho concentration (67% accuracy). SVM analysis of all paired parameters showed SUVmax and Cho concentration in combination could achieve 83% accuracy. SUVmax of the lesion paired with SUVmax of the white matter as well as the tumor Cho paired with the tumor Cr both showed 83% accuracy. These were the most significant paired diagnostic parameters of either modality. Combining all four parameters did not improve the results. However, addition of two more parameters, Cho and Cr of brain parenchyma contralateral to the tumor, increased the accuracy to 92%. This study suggests that SVM models may improve detection of glioma progression more accurately than single parametric imaging methods. National Cancer Institute, Cancer Center Support Grant Supplement Award, Imaging Response Assessment Teams.
登录
查看更多内容
影响因子：
3.3
作者：
Fayed, Nicolas;Davila, Jorge;Olmos, Salvador
通讯作者：
Olmos, Salvador
影响因子：
2.9
作者：
Herminghaus, S;Pilatus, U;Zanella, FE
通讯作者：
Zanella, FE
影响因子：
1.8
作者：
Watson, CC
通讯作者：
Watson, CC
影响因子：
3.3
作者：
KREIS, R;ERNST, T;ROSS, BD
通讯作者：
ROSS, BD
影响因子：
1.3
作者：
Wang, SX;Boethius, J;Ericson, K
通讯作者：
Ericson, K