Alibabaei Sanaz, Yousefipour Mohammad, Rahmani Masoumeh, Raminfard Samira, Tahmasbi Marziyeh
Department of Medical Physics, Faculty of Medicine, Semnan University of Medical Sciences, Semnan, Iran.
Department of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.
BMC Med Imaging. 2025 Sep 1;25(1):362. doi: 10.1186/s12880-025-01906-8.
Developing quantitative methods to assess post-surgery treatment response in Glioblastoma Multiforme (GBM) is critical for improving patient outcomes and refining current subjective approaches. This study analyzes the performance of machine learning models trained on radiomic datasets derived from magnetic resonance imaging (MRI) scans of GBM patients.
MRI scans from 143 GBM patients receiving adjuvant therapy post-surgery were acquired and preprocessed. A total of 92 radiomic features, including 68 Gy-level co-occurrence matrix (GLCM)-based features calculated in four directions (0°, 45°, 90°, and 135°) and 24 Curvelet coefficient-based features, were extracted from each patient's segmented tumor cavity. Machine learning classifiers, including Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors (KNN), AdaBoost, CatBoost, LightGBM, XGBoost, Gaussian Naïve Bayes (GNB), and Logistic Regression (LR), were trained on the extracted radiomics selected using sequential feature selection, LASSO, and PCA. Validation was performed with 10-fold cross-validation.
The proposed pipeline achieved an accuracy of 87% in classifying post-surgery treatment responses in GBM patients. This accuracy was achieved with the SVM trained on a combination of GLCM and Curvelet-based radiomics selected via forward sequential algorithm-8, and with KNN trained on GLCM and Curvelet radiomics combination selected using LASSO (alpha = 0.01). The LR model trained on Curvelet-based LASSO-selected radiomics (alpha = 0.01) also showed strong performance.
The results demonstrate that MRI-based radiomics, specifically GLCM and Curvelet features, can effectively train machine learning models to quantitatively assess GBM treatment response. These models serve as valuable tools to complement qualitative evaluations, enhancing accuracy and objectivity in post-surgery outcome assessment.
Not applicable.
开发定量方法以评估多形性胶质母细胞瘤（GBM）术后治疗反应对于改善患者预后和完善当前主观评估方法至关重要。本研究分析了基于GBM患者磁共振成像（MRI）扫描获得的放射组学数据集训练的机器学习模型的性能。
获取并预处理了143例接受术后辅助治疗的GBM患者的MRI扫描图像。从每位患者的分割肿瘤腔中提取了总共92个放射组学特征，包括在四个方向（0°、45°、90°和135°）计算的68个基于灰度共生矩阵（GLCM）的特征以及24个基于曲波系数的特征。使用序贯特征选择、LASSO和主成分分析（PCA）对提取的放射组学特征进行筛选，然后训练包括支持向量机（SVM）、随机森林、K近邻（KNN）、AdaBoost、CatBoost、LightGBM、XGBoost、高斯朴素贝叶斯（GNB）和逻辑回归（LR）在内的机器学习分类器。采用10折交叉验证进行验证。
所提出的流程在对GBM患者术后治疗反应进行分类时达到了87%的准确率。通过对经前向序贯算法-8选择的基于GLCM和曲波的放射组学特征组合训练的SVM以及对经LASSO（α = 0.01）选择的GLCM和曲波放射组学特征组合训练的KNN实现了这一准确率。对经基于曲波的LASSO选择的放射组学特征（α = 0.01）训练的LR模型也表现出强劲性能。
结果表明，基于MRI的放射组学，特别是GLCM和曲波特征，能够有效地训练机器学习模型以定量评估GBM治疗反应。这些模型作为补充定性评估的有价值工具，提高了术后结果评估的准确性和客观性。
不适用。
