Improving Proton MR Spectroscopy of Brain Tissue for Noninvasive Diagnostics
Improving Proton MR Spectroscopy of Brain Tissue for Noninvasive Diagnostics
复制标题
DOI：
10.1002/jmri.22332
复制
发表时间：
2010-10-01
影响因子：
4.4
通讯作者：
Wilkes, Jon G.
中科院分区：
文献类型：
--
作者：
Alusta, Pierre;Im, Inessa;Wilkes, Jon G.
目的：研究影响磁共振波谱（MRS）作为一种非侵入性脑病变检测和表征以及指导治疗进展的潜在应用的预处理方法。材料和方法：采用线性插值法重新校准两个参考点（以补偿磁场的非均匀性），对光谱进行加权（以强调一致的峰并降低化学噪声），并基于97个生物标志物的化学位移位置进行建模。通过比较Leave-One-Out （LOO）交叉验证和外部验证来评估139个分类扫描的结果。结果：对于9种脑组织类别的区分，使用重新校准、方差加权和生物标志物建模将MRS光谱的LOO分类从31%提高到95%。对47个未知样本进行的两种最佳九类模型的外部验证，与病理诊断相比，准确率分别为96%或100%。结论：对磁共振光谱进行预处理，可显著提高其在模式识别模型自动会诊中的诊断效能。几种技术的结合使用大大增加了可用的质子MRS信息含量。在九个组织类别中准确分配未知数代表了一个显着的改进，对于一个更苛刻的任务，比以前报道过的。
Purpose: To examine preprocessing methods affecting the potential use of Magnetic Resonance Spectroscopy (MRS) as a noninvasive modality for detection and characterization of brain lesions and for directing therapy progress.Materials and Methods: Two reference point re-calibration with linear interpolation (to compensate for magnetic field nonhomogeneity), weighting of spectra (to emphasize consistent peaks and depress chemical noise), and modeling based on chemical shift locations of 97 biomarkers were investigated. Results for 139 categorized scans were assessed by comparing Leave-One-Out (LOO) cross-validation and external validation.Results: For distinction of nine brain tissue categories, use of re-calibration, variance weighting, and biomarker modeling improved LOO classification of MRS spectra from 31% to 95%. External validation of the two best nine-category models on 47 unknown samples gave 96% or 100% accuracy, respectively, compared with pathological diagnosis.Conclusion: Preprocessing of MRS spectra can significantly improve their diagnostic utility for automated consultation of pattern recognition models. Use of several techniques in combination greatly increases available proton MRS information content. Accurate assignment of unknowns among nine tissue classes represents a significant improvement, for a much more demanding task, than has been previously reported.