School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China; Department of Electronic Engineering, Information School, Yunnan University, Kunming 650091, China.
School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou 510515, China.
Comput Methods Programs Biomed. 2023 Mar;230:107341. doi: 10.1016/j.cmpb.2023.107341. Epub 2023 Jan 7.
Accurate risk stratification is crucial for enabling personalized treatment for head and neck cancer (HNC). Current PET/CT image-based prognostic methods include radiomics analysis and convolutional neural network (CNN), while extracting radiomics or deep features in grid Euclidean space has inherent limitations for risk stratification. Here, we propose a functional-structural sub-region graph convolutional network (FSGCN) for accurate risk stratification of HNC.
This study collected 642 patients from 8 different centers in The Cancer Imaging Archive (TCIA), 507 patients from 5 centers were used for training, and 135 patients from 3 centers were used for testing. The tumor was first clustered into multiple sub-regions by using PET and CT voxel information, and radiomics features were extracted from each sub-region to characterize its functional and structural information, a graph was then constructed to format the relationship/difference among different sub-regions in non-Euclidean space for each patient, followed by a residual gated graph convolutional network, the prognostic score was finally generated to predict the progression-free survival (PFS).
In the testing cohort, compared with radiomics or FSGCN or clinical model alone, the model PETCT_CT + Cli that integrates FSGCN prognostic score and clinical parameter achieved the highest C-index and AUC of 0.767 (95% CI: 0.759-0.774) and 0.781 (95% CI: 0.774-0.788), respectively for PFS prediction. Besides, it also showed good prognostic performance on the secondary endpoints OS, RFS, and MFS in the testing cohort, with C-index of 0.786 (95% CI: 0.778-0.795), 0.775 (95% CI: 0.767-0.782) and 0.781 (95% CI: 0.772-0.789), respectively.
The proposed FSGCN can better capture the metabolic or anatomic difference/interaction among sub-regions of the whole tumor imaged with PET/CT. Extensive multi-center experiments demonstrated its capability and generalization of prognosis prediction in HNC over conventional radiomics analysis.
对头颈癌（HNC）进行准确的风险分层对于实现个体化治疗至关重要。目前基于 PET/CT 图像的预后方法包括放射组学分析和卷积神经网络（CNN），然而，在欧式网格空间中提取放射组学或深度特征对于风险分层存在固有局限性。在这里，我们提出了一种用于 HNC 准确风险分层的功能-结构子区域图卷积网络（FSGCN）。
本研究从癌症成像档案（TCIA）中的 8 个不同中心收集了 642 名患者，其中 507 名患者来自 5 个中心用于训练，135 名患者来自 3 个中心用于测试。首先通过使用 PET 和 CT 体素信息将肿瘤聚类成多个子区域，然后从每个子区域中提取放射组学特征以描述其功能和结构信息，为每个患者构建一个图以格式化非欧几里得空间中不同子区域之间的关系/差异，然后是一个残差门控图卷积网络，最后生成预后评分以预测无进展生存期（PFS）。
在测试队列中，与放射组学或 FSGCN 或临床模型单独相比，集成了 FSGCN 预后评分和临床参数的模型 PETCT_CT+Cli 在预测 PFS 方面达到了最高的 C 指数和 AUC，分别为 0.767（95%CI：0.759-0.774）和 0.781（95%CI：0.774-0.788）。此外，它在测试队列中的次要终点 OS、RFS 和 MFS 上也表现出良好的预后性能，C 指数分别为 0.786（95%CI：0.778-0.795）、0.775（95%CI：0.767-0.782）和 0.781（95%CI：0.772-0.789）。
所提出的 FSGCN 可以更好地捕捉 PET/CT 成像的整个肿瘤的子区域之间的代谢或解剖差异/相互作用。广泛的多中心实验证明了它在 HNC 中的预后预测能力和泛化能力优于传统的放射组学分析。
