School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, Guangdong, China.
Nanfang PET Center, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, Guangdong, China.
Ann Nucl Med. 2021 Apr;35(4):458-468. doi: 10.1007/s12149-021-01585-9. Epub 2021 Feb 4.
To develop a radiomics signature to predict locoregional recurrence (LR) and distant metastasis (DM), as extracted from pretreatment 2-deoxy-2-[F]fluoro-D-glucose ([18F]FDG) positron emission tomography/X-ray computed tomography (PET/CT) images in locally advanced nasopharyngeal carcinoma (NPC).
Eighty-five patients with Stage III-IVB NPC underwent pretreatment [F]FDG PET/CT scans and received radiotherapy or chemoradiotherapy. 53 of them achieved disease control, and 32 of them failed after treatment (15: LR, 17: DM). A total of 114 radiomic features were extracted from PET/CT images. For univariate analysis, Wilcoxon test and Chi-square test were used to compare median values of features between different treatment outcomes and predict the risk of treatment failure, respectively. For multivariate analysis, all features were grouped into clusters based on Pearson correlation using hierarchical clustering, and the representative feature of each cluster was chosen by the Relief algorithm. Then sequential floating forward selection (SFFS) coupled with a support vector machine (SVM) classifier were used to derive the optimized feature set in terms of the area under receiver operating characteristic (ROC) curve (AUC). The performance of the model was evaluated by leave-one-out-cross-validation, fivefold cross-validation, tenfold cross-validation.
Twenty features had significant differences between disease control and treatment failure. NPC patients with values of Compactness1, Compactness2, Coarseness_NGTDM or SGE_GLGLM above the median as well as patients with values of Irregularity, RLN_GLRLM or GLV_GLSZM below the median, showed a significant (p < 0.05) higher risk of treatment failure (about 50% vs. 25%). The derived radiomics signature consisted of 5 features with the highest AUC value of 0.8290 (sensitivity: 0.8438, specificity: 0.7736) using leave-one-out-cross-validation.
Locoregional recurrence (LR) and DM of locally advanced NPC can be predicted using radiomics analysis of pretreatment [F]FDG PET/CT. The SFFS feature selection coupled with SVM classifier can derive the optimized feature set with correspondingly highest AUC value for pretreatment prediction of LR and/or DM of NPC.
从局部晚期鼻咽癌（NPC）患者的预处理 2-脱氧-2-[F]氟-D-葡萄糖（[18F]FDG）正电子发射断层扫描/X 射线计算机断层扫描（PET/CT）图像中提取预测局部区域复发（LR）和远处转移（DM）的影像组学特征。
85 例 III-IVB 期 NPC 患者接受了预处理[F]FDG PET/CT 扫描，并接受了放疗或放化疗。其中 53 例患者达到了疾病控制，32 例患者在治疗后失败（15 例：LR，17 例：DM）。共从 PET/CT 图像中提取了 114 个影像组学特征。对于单变量分析，采用 Wilcoxon 检验和卡方检验分别比较不同治疗结果的特征中位数，以预测治疗失败的风险。对于多变量分析，根据 Pearson 相关性将所有特征分为簇，然后使用 Relief 算法选择每个簇的代表性特征。然后，使用顺序浮动向前选择（SFFS）和支持向量机（SVM）分类器，根据接收者操作特征（ROC）曲线下面积（AUC），从特征集中导出最优特征集。通过留一交叉验证、五折交叉验证、十折交叉验证评估模型的性能。
疾病控制与治疗失败之间有 20 个特征存在显著差异。值高于中位数的患者，如 Compactness1、Compactness2、Coarseness_NGTDM 或 SGE_GLGLM，值低于中位数的患者，如 Irregularity、RLN_GLRLM 或 GLV_GLSZM，具有显著更高的治疗失败风险（约 50%比 25%）。通过留一交叉验证，得到的影像组学特征由 5 个特征组成，AUC 值最高为 0.8290（灵敏度：0.8438，特异性：0.7736）。
可以使用预处理[F]FDG PET/CT 的影像组学分析预测局部晚期 NPC 的局部区域复发（LR）和远处转移（DM）。SFFS 特征选择与 SVM 分类器结合，可以为 NPC 的 LR 和/或 DM 的预处理预测得出最优特征集，具有相应的最高 AUC 值。
