Pasquini Luca, Napolitano Antonio, Tagliente Emanuela, Dellepiane Francesco, Lucignani Martina, Vidiri Antonello, Ranazzi Giulio, Stoppacciaro Antonella, Moltoni Giulia, Nicolai Matteo, Romano Andrea, Di Napoli Alberto, Bozzao Alessandro
Neuroradiology Unit, NESMOS Department, Sant'Andrea Hospital, La Sapienza University, Via di Grottarossa 1035, 00189 Rome, Italy.
Neuroradiology Service, Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY 10065, USA.
J Pers Med. 2021 Apr 9;11(4):290. doi: 10.3390/jpm11040290.
Isocitrate dehydrogenase (IDH) mutant and wildtype glioblastoma multiforme (GBM) often show overlapping features on magnetic resonance imaging (MRI), representing a diagnostic challenge. Deep learning showed promising results for IDH identification in mixed low/high grade glioma populations; however, a GBM-specific model is still lacking in the literature. Our aim was to develop a GBM-tailored deep-learning model for IDH prediction by applying convoluted neural networks (CNN) on multiparametric MRI. We selected 100 adult patients with pathologically demonstrated WHO grade IV gliomas and IDH testing. MRI sequences included: MPRAGE, T1, T2, FLAIR, rCBV and ADC. The model consisted of a 4-block 2D CNN, applied to each MRI sequence. Probability of IDH mutation was obtained from the last dense layer of a softmax activation function. Model performance was evaluated in the test cohort considering categorical cross-entropy loss (CCEL) and accuracy. Calculated performance was: rCBV (accuracy 83%, CCEL 0.64), T1 (accuracy 77%, CCEL 1.4), FLAIR (accuracy 77%, CCEL 1.98), T2 (accuracy 67%, CCEL 2.41), MPRAGE (accuracy 66%, CCEL 2.55). Lower performance was achieved on ADC maps. We present a GBM-specific deep-learning model for IDH mutation prediction, with a maximal accuracy of 83% on rCBV maps. Highest predictivity achieved on perfusion images possibly reflects the known link between IDH and neoangiogenesis through the hypoxia inducible factor.
异柠檬酸脱氢酶（IDH）突变型和野生型多形性胶质母细胞瘤（GBM）在磁共振成像（MRI）上常表现出重叠特征，这构成了诊断挑战。深度学习在混合低/高级别胶质瘤群体的IDH识别方面显示出有前景的结果；然而，文献中仍缺乏GBM特异性模型。我们的目的是通过在多参数MRI上应用卷积神经网络（CNN）来开发一种针对GBM的深度学习模型用于IDH预测。我们选择了100例经病理证实为WHO四级胶质瘤且进行了IDH检测的成年患者。MRI序列包括：MPRAGE、T1、T2、FLAIR、rCBV和ADC。该模型由一个4模块的二维CNN组成，应用于每个MRI序列。IDH突变的概率从softmax激活函数的最后一个全连接层获得。在测试队列中，考虑分类交叉熵损失（CCEL）和准确率来评估模型性能。计算得到的性能如下：rCBV（准确率83%，CCEL 0.64）、T1（准确率77%，CCEL 1.4）、FLAIR（准确率77%，CCEL 1.98）、T2（准确率67%，CCEL 2.41）、MPRAGE（准确率66%，CCEL 2.55）。ADC图的性能较低。我们提出了一种用于IDH突变预测的GBM特异性深度学习模型，在rCBV图上的最大准确率为83%。灌注图像上实现的最高预测性可能反映了IDH与通过缺氧诱导因子的新生血管生成之间的已知联系。
