Lv Wenbing, Xu Hui, Han Xu, Zhang Hao, Ma Jianhua, Rahmim Arman, Lu Lijun
School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China.
Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China.
Cancers (Basel). 2022 Mar 25;14(7):1674. doi: 10.3390/cancers14071674.
This multi-center study aims to investigate the prognostic value of context-aware saliency-guided radiomics in F-FDG PET/CT images of head and neck cancer (HNC).
806 HNC patients (training vs. validation vs. external testing: 500 vs. 97 vs. 209) from 9 centers were collected from The Cancer Imaging Archive (TCIA). There were 100/384 and 60/123 oropharyngeal carcinoma (OPC) patients with human papillomavirus (HPV) status in training and testing cohorts, respectively. Six types of images were used for radiomics feature extraction and further model construction, namely (i) the original image (Origin), (ii) a context-aware saliency map (SalMap), (iii, iv) high- or low-saliency regions in the original image (highSal or lowSal), (v) a saliency-weighted image (SalxImg), and finally, (vi) a fused PET-CT image (FusedImg). Four outcomes were evaluated, i.e., recurrence-free survival (RFS), metastasis-free survival (MFS), overall survival (OS), and disease-free survival (DFS), respectively. Multivariate Cox analysis and logistic regression were adopted to construct radiomics scores for the prediction of outcome (Rad_Ocm) and HPV-status (Rad_HPV), respectively. Besides, the prognostic value of their integration (Rad_Ocm_HPV) was also investigated.
In the external testing cohort, compared with the Origin model, SalMap and SalxImg achieved the highest C-indices for RFS (0.621 vs. 0.559) and MFS (0.785 vs. 0.739) predictions, respectively, while FusedImg performed the best for both OS (0.685 vs. 0.659) and DFS (0.641 vs. 0.582) predictions. In the OPC HPV testing cohort, FusedImg showed higher AUC for HPV-status prediction compared with the Origin model (0.653 vs. 0.484). In the OPC testing cohort, compared with Rad_Ocm or Rad_HPV alone, Rad_Ocm_HPV performed the best for OS and DFS predictions with C-indices of 0.702 ( = 0.002) and 0.684 ( = 0.006), respectively.
Saliency-guided radiomics showed enhanced performance for both outcome and HPV-status predictions relative to conventional radiomics. The radiomics-predicted HPV status also showed complementary prognostic value.
本多中心研究旨在探讨上下文感知显著性引导的放射组学在头颈部癌（HNC）的F-FDG PET/CT图像中的预后价值。
从癌症影像存档（TCIA）收集了来自9个中心的806例HNC患者（训练组vs.验证组vs.外部测试组：500例vs.97例vs.209例）。训练组和测试组中分别有100/384例和60/123例口咽癌（OPC）患者具有人乳头瘤病毒（HPV）状态信息。使用六种类型的图像进行放射组学特征提取和进一步的模型构建，即（i）原始图像（Origin），（ii）上下文感知显著性图（SalMap），（iii、iv）原始图像中的高显著性或低显著性区域（highSal或lowSal），（v）显著性加权图像（SalxImg），最后是（vi）融合的PET-CT图像（FusedImg）。分别评估了四个结局，即无复发生存期（RFS）、无转移生存期（MFS）、总生存期（OS）和无病生存期（DFS）。采用多变量Cox分析和逻辑回归分别构建用于预测结局（Rad_Ocm）和HPV状态（Rad_HPV）的放射组学评分。此外，还研究了它们整合后的预后价值（Rad_Ocm_HPV）。
在外部测试组中，与Origin模型相比，SalMap和SalxImg在RFS（0.621对0.559）和MFS（0.785对0.739）预测中分别获得了最高的C指数，而FusedImg在OS（0.685对0.659）和DFS（0.641对0.582）预测中表现最佳。在OPC HPV测试组中，与Origin模型相比，FusedImg在HPV状态预测中显示出更高的AUC（0.653对0.484）。在OPC测试组中，与单独的Rad_Ocm或Rad_HPV相比，Rad_Ocm_HPV在OS和DFS预测中表现最佳，C指数分别为0.702（P = 0.002）和0.684（P = 0.006）。
相对于传统放射组学，显著性引导的放射组学在结局和HPV状态预测方面均表现出更高的性能。放射组学预测的HPV状态也显示出互补的预后价值。
