Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1205 Geneva, Switzerland.
Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Phys Med Biol. 2021 Oct 14;66(20). doi: 10.1088/1361-6560/ac287d.
We developed multi-modality radiomic models by integrating information extracted fromF-FDG PET and CT images using feature- and image-level fusions, toward improved prognosis for non-small cell lung carcinoma (NSCLC) patients. Two independent cohorts of NSCLC patients from two institutions (87 and 95 patients) were cycled as training and testing datasets. Fusion approaches were applied at two levels, namely feature- and image-levels. For feature-level fusion, radiomic features were extracted individually from CT and PET images and concatenated. Alternatively, radiomic features extracted separately from CT and PET images were averaged. For image-level fusion, wavelet fusion was utilized and tuned with two parameters, namely CT weight and Wavelet Band Pass Filtering Ratio. Clinical and combined clinical + radiomic models were developed. Gray level discretization was performed at 3 different levels (16, 32 and 64) and 225 radiomics features were extracted. Overall survival (OS) was considered as the endpoint. For feature reduction, correlated (redundant) features were excluded using Spearman's correlation, and best combination of top ten features with highest concordance-indices (via univariate Cox model) were selected in each model for further multivariate Cox model. Moreover, prognostic score's median, obtained from the training cohort, was used intact in the testing cohort as a threshold to classify patients into low- versus high-risk groups, and log-rank test was applied to assess differences between the Kaplan-Meier curves. Overall, while models based on feature-level fusion strategy showed limited superiority over single-modalities, image-level fusion strategy significantly outperformed both single-modality and feature-level fusion strategies. As such, the clinical model (C-index = 0.656) outperformed all models from single-modality and feature-level strategies, but was outperformed by certain models from image-level fusion strategy. Our findings indicated that image-level fusion multi-modality radiomics models outperformed single-modality, feature-level fusion, and clinical models for OS prediction of NSCLC patients.
我们通过整合来自 F-FDG PET 和 CT 图像的信息，使用特征级和图像级融合开发了多模态放射组学模型，以改善非小细胞肺癌（NSCLC）患者的预后。两个机构的 NSCLC 患者的两个独立队列（87 名和 95 名患者）被循环作为训练和测试数据集。融合方法应用于两个级别，即特征级和图像级。对于特征级融合，从 CT 和 PET 图像中分别提取放射组学特征并进行拼接。或者，从 CT 和 PET 图像中分别提取的放射组学特征进行平均。对于图像级融合，使用小波融合并使用两个参数进行调整，即 CT 权重和小波带通滤波比。开发了临床和联合临床+放射组学模型。灰度离散化在 3 个不同级别（16、32 和 64）上进行，提取了 225 个放射组学特征。将总生存期（OS）作为终点。对于特征降维，使用 Spearman 相关性排除相关（冗余）特征，并在每个模型中选择具有最高一致性指数的前十个特征的最佳组合（通过单变量 Cox 模型），用于进一步的多变量 Cox 模型。此外，从训练队列中获得的预后评分中位数，作为分类低风险与高风险组的阈值，在测试队列中完整保留，并应用对数秩检验评估 Kaplan-Meier 曲线之间的差异。总体而言，虽然基于特征级融合策略的模型显示出对单模态的有限优势，但图像级融合策略明显优于单模态和特征级融合策略。因此，临床模型（C 指数=0.656）优于单模态和特征级策略的所有模型，但逊于某些来自图像级融合策略的模型。我们的研究结果表明，对于 NSCLC 患者的 OS 预测，图像级融合多模态放射组学模型优于单模态、特征级融合和临床模型。
