Galli Roberta, Lehner Franz, Richter Sven, Kirsche Katrin, Meinhardt Matthias, Juratli Tareq A, Temme Achim, Kirsch Matthias, Warta Rolf, Herold-Mende Christel, Ricklefs Franz L, Lamszus Katrin, Sievers Philipp, Sahm Felix, Eyüpoglu Ilker Y, Uckermann Ortrud
Faculty of Medicine, Medical Physics and Biomedical Engineering, Technische Universität Dresden, Dresden, Germany.
Department of Neurosurgery, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany.
Neurooncol Adv. 2024 Jun 6;6(1):vdae082. doi: 10.1093/noajnl/vdae082. eCollection 2024 Jan-Dec.
Infrared (IR) spectroscopy allows intraoperative, optical brain tumor diagnosis. Here, we explored it as a translational technology for the identification of aggressive meningioma types according to both, the WHO CNS grading system and the methylation classes (MC).
Frozen sections of 47 meningioma were examined by IR spectroscopic imaging and different classification approaches were compared to discern samples according to WHO grade or MC.
IR spectroscopic differences were more pronounced between WHO grade 2 and 3 than between MC intermediate and MC malignant, although similar spectral ranges were affected. Aggressive types of meningioma exhibited reduced bands of carbohydrates (at 1024 cm) and nucleic acids (at 1080 cm), along with increased bands of phospholipids (at 1240 and 1450 cm). While linear discriminant analysis was able to discern spectra of WHO grade 2 and 3 meningiomas (AUC 0.89), it failed for MC (AUC 0.66). However, neural network classifiers were effective for classification according to both WHO grade (AUC 0.91) and MC (AUC 0.83), resulting in the correct classification of 20/23 meningiomas of the test set.
IR spectroscopy proved capable of extracting information about the malignancy of meningiomas, not only according to the WHO grade, but also for a diagnostic system based on molecular tumor characteristics. In future clinical use, physicians could assess the goodness of the classification by considering classification probabilities and cross-measurement validation. This might enhance the overall accuracy and clinical utility, reinforcing the potential of IR spectroscopy in advancing precision medicine for meningioma characterization.
红外（IR）光谱技术可用于术中对脑肿瘤进行光学诊断。在此，我们探索将其作为一种转化技术，用于根据世界卫生组织（WHO）中枢神经系统分级系统和甲基化类别（MC）来识别侵袭性脑膜瘤类型。
对47例脑膜瘤的冰冻切片进行红外光谱成像检查，并比较不同的分类方法，以根据WHO分级或MC来区分样本。
尽管受影响的光谱范围相似，但WHO 2级和3级之间的红外光谱差异比MC中间型和MC恶性型之间更为明显。侵袭性脑膜瘤类型显示碳水化合物（在1024 cm处）和核酸（在1080 cm处）的谱带减少，同时磷脂（在1240和1450 cm处）的谱带增加。虽然线性判别分析能够区分WHO 2级和3级脑膜瘤的光谱（曲线下面积[AUC]为0.89），但对MC的区分效果不佳（AUC为0.66）。然而，神经网络分类器对于根据WHO分级（AUC为0.91）和MC（AUC为0.83）进行分类均有效，在测试集中23例脑膜瘤中有20例被正确分类。
红外光谱不仅能够根据WHO分级提取有关脑膜瘤恶性程度的信息，还能用于基于分子肿瘤特征的诊断系统。在未来的临床应用中，医生可以通过考虑分类概率和交叉测量验证来评估分类的优劣。这可能会提高整体准确性和临床实用性，增强红外光谱在推进脑膜瘤精准医学特征分析方面的潜力。
