Division of Medical Quantum Science, Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan; Sanford Burnham Prebys Medical Discovery Institute, 10901 North Torrey Pines Road, La Jolla, CA 92037, USA.
Division of Medical Quantum Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, Fukuoka, Japan.
Comput Methods Programs Biomed. 2023 Jun;236:107544. doi: 10.1016/j.cmpb.2023.107544. Epub 2023 Apr 13.
To elucidate a novel radiogenomics approach using three-dimensional (3D) topologically invariant Betti numbers (BNs) for topological characterization of epidermal growth factor receptor (EGFR) Del19 and L858R mutation subtypes.
In total, 154 patients (wild-type EGFR, 72 patients; Del19 mutation, 45 patients; and L858R mutation, 37 patients) were retrospectively enrolled and randomly divided into 92 training and 62 test cases. Two support vector machine (SVM) models to distinguish between wild-type and mutant EGFR (mutation [M] classification) as well as between the Del19 and L858R subtypes (subtype [S] classification) were trained using 3DBN features. These features were computed from 3DBN maps by using histogram and texture analyses. The 3DBN maps were generated using computed tomography (CT) images based on the Čech complex constructed on sets of points in the images. These points were defined by coordinates of voxels with CT values higher than several threshold values. The M classification model was built using image features and demographic parameters of sex and smoking status. The SVM models were evaluated by determining their classification accuracies. The feasibility of the 3DBN model was compared with those of conventional radiomic models based on pseudo-3D BN (p3DBN), two-dimensional BN (2DBN), and CT and wavelet-decomposition (WD) images. The validation of the model was repeated with 100 times random sampling.
The mean test accuracies for M classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.810, 0.733, 0.838, 0.782, and 0.799, respectively. The mean test accuracies for S classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.773, 0.694, 0.657, 0.581, and 0.696, respectively.
3DBN features, which showed a radiogenomic association with the characteristics of the EGFR Del19/L858R mutation subtypes, yielded higher accuracy for subtype classifications in comparison with conventional features.
利用三维（3D）拓扑不变贝蒂数（BN）阐明一种新的放射基因组学方法，用于表皮生长因子受体（EGFR）Del19 和 L858R 突变亚型的拓扑特征描述。
回顾性纳入 154 例患者（野生型 EGFR72 例，Del19 突变 45 例，L858R 突变 37 例），并将其随机分为 92 例训练病例和 62 例测试病例。采用支持向量机（SVM）模型，利用 3DBN 特征区分野生型和突变型 EGFR（突变 [M] 分类）以及 Del19 和 L858R 亚型（亚型 [S] 分类）。这些特征是通过体素 CT 值高于几个阈值的坐标定义的点集的计算层析成像（CT）图像的 3DBN 图谱，采用直方图和纹理分析计算得到。基于点集的Čech 复形生成 3DBN 图谱，这些点集是由 CT 值高于几个阈值的体素坐标定义的。M 分类模型采用图像特征和性别及吸烟状态的人口统计学参数构建。通过确定分类准确率来评估 SVM 模型。将 3DBN 模型与基于伪三维 BN（p3DBN）、二维 BN（2DBN）、CT 和小波分解（WD）图像的常规放射组学模型进行比较，以验证 3DBN 模型的可行性。通过 100 次随机抽样重复验证模型。
3DBN、p3DBN、2DBN、CT 和 WD 图像 M 分类的平均测试准确率分别为 0.810、0.733、0.838、0.782 和 0.799。3DBN、p3DBN、2DBN、CT 和 WD 图像 S 分类的平均测试准确率分别为 0.773、0.694、0.657、0.581 和 0.696。
与传统特征相比，3DBN 特征与 EGFR Del19/L858R 突变亚型的特征具有放射基因组学相关性，用于亚型分类的准确率更高。
