Hsieh Hsun-Ping, Wu Ding-You, Hung Kuo-Chuan, Lim Sher-Wei, Chen Tai-Yuan, Fan-Chiang Yang, Ko Ching-Chung
Department of Electrical Engineering, National Cheng Kung University, Tainan 70101, Taiwan.
Department of Anesthesiology, Chi Mei Medical Center, Tainan City 71004, Taiwan.
J Pers Med. 2022 Mar 24;12(4):522. doi: 10.3390/jpm12040522.
A subset of parasagittal and parafalcine (PSPF) meningiomas may show early progression/recurrence (P/R) after surgery. This study applied machine learning using combined clinical and texture features to predict P/R in PSPF meningiomas. A total of 57 consecutive patients with pathologically confirmed (WHO grade I) PSPF meningiomas treated in our institution between January 2007 to January 2019 were included. All included patients had complete preoperative magnetic resonance imaging (MRI) and more than one year MRI follow-up after surgery. Preoperative contrast-enhanced T1WI, T2WI, T1WI, and T2 fluid-attenuated inversion recovery (FLAIR) were analyzed retrospectively. The most significant 12 clinical features (extracted by LightGBM) and 73 texture features (extracted by SVM) were combined in random forest to predict P/R, and personalized radiomic scores were calculated. Thirteen patients (13/57, 22.8%) had P/R after surgery. The radiomic score was a high-risk factor for P/R with hazard ratio of 15.73 (p < 0.05) in multivariate hazards analysis. In receiver operating characteristic (ROC) analysis, an AUC of 0.91 with cut-off value of 0.269 was observed in radiomic scores for predicting P/R. Subtotal resection, low apparent diffusion coefficient (ADC) values, and high radiomic scores were associated with shorter progression-free survival (p < 0.05). Among different data input, machine learning using combined clinical and texture features showed the best predictive performance, with an accuracy of 91%, precision of 85%, and AUC of 0.88. Machine learning using combined clinical and texture features may have the potential to predict recurrence in PSPF meningiomas.
矢状窦旁和大脑镰旁（PSPF）脑膜瘤的一部分在手术后可能会出现早期进展/复发（P/R）。本研究应用机器学习结合临床和纹理特征来预测PSPF脑膜瘤的P/R。纳入了2007年1月至2019年1月在我们机构接受治疗的57例经病理证实（WHO I级）的PSPF脑膜瘤患者。所有纳入患者均有完整的术前磁共振成像（MRI），且术后有超过一年的MRI随访。回顾性分析术前对比增强T1WI、T2WI、T1WI和T2液体衰减反转恢复（FLAIR）序列。将12个最显著的临床特征（由LightGBM提取）和73个纹理特征（由支持向量机提取）结合到随机森林中以预测P/R，并计算个性化的影像组学评分。13例患者（13/57，22.8%）术后出现P/R。在多因素风险分析中，影像组学评分是P/R的高危因素，风险比为15.73（p<0.05）。在受试者工作特征（ROC）分析中，影像组学评分预测P/R的曲线下面积（AUC）为0.91，截断值为0.269。次全切除、低表观扩散系数（ADC）值和高影像组学评分与无进展生存期缩短相关（p<0.05）。在不同的数据输入中，结合临床和纹理特征的机器学习显示出最佳的预测性能，准确率为91%，精确率为85%，AUC为0.88。结合临床和纹理特征的机器学习可能有潜力预测PSPF脑膜瘤的复发。
