School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, Guangdong, China.
LaTIM, INSERM, UMR 1101, University Brest, Brest, France.
Eur J Nucl Med Mol Imaging. 2023 May;50(6):1720-1734. doi: 10.1007/s00259-023-06118-2. Epub 2023 Jan 24.
This study aimed to investigate the impact of several ComBat harmonization strategies, intra-tumoral sub-volume characterization, and automatic segmentations for progression-free survival (PFS) prediction through radiomics modeling for patients with head and neck cancer (HNC) in PET/CT images.
The HECKTOR MICCAI 2021 challenge set containing PET/CT images and clinical data of 325 oropharynx HNC patients was exploited. A total of 346 IBSI-compliant radiomic features were extracted for each patient's primary tumor volume defined by the reference manual contours. Modeling relied on least absolute shrinkage Cox regression (Lasso-Cox) for feature selection (FS) and Cox proportional-hazards (CoxPH) models were built to predict PFS. Within this methodological framework, 8 different strategies for ComBat harmonization were compared, including before or after FS, in feature groups separately or all features directly, and with center or clustering-determined labels. Features extracted from tumor sub-volume clustering were also investigated for their prognostic additional value. Finally, 3 automatic segmentations (2 threshold-based and a 3D U-Net) were also compared. All results were evaluated with the concordance index (C-index).
Radiomics features without harmonization, combined with clinical factors, led to models with C-index values of 0.69 in the testing set. The best version of ComBat harmonization, i.e., after FS, for feature groups separately and relying on clustering-determined labels, achieved a C-index of 0.71. The use of features extracted from tumor sub-volumes further improved the C-index to 0.72. Models that relied on the automatic segmentations yielded close but slightly lower prognostic performance (0.67-0.70) compared to reference contours.
A standard radiomics pipeline allowed for prediction of PFS in a multicenter HNC cohort. Applying a specific strategy of ComBat harmonization improved the performance. The extraction of intra-tumoral sub-volume features and automatic segmentation could contribute to the improvement and automation of prognosis modeling, respectively.
本研究旨在通过对头颈癌（HNC）患者 PET/CT 图像的放射组学建模，探讨几种 ComBat 调和策略、肿瘤内亚体积特征分析和自动分割对无进展生存期（PFS）预测的影响。
利用 HECKTOR MICCAI 2021 挑战赛包含的 325 例口咽 HNC 患者的 PET/CT 图像和临床数据。为每个患者的原发肿瘤体积提取了 346 个符合 IBSI 标准的放射组学特征，这些体积由参考手动轮廓定义。建模依赖于最小绝对收缩和选择算子 Cox 回归（Lasso-Cox）进行特征选择（FS），并构建 Cox 比例风险（CoxPH）模型来预测 PFS。在这个方法框架内，比较了 8 种不同的 ComBat 调和策略，包括在 FS 之前或之后、分别在特征组中或直接在所有特征中进行，以及使用中心或聚类确定的标签。还研究了从肿瘤亚体积聚类中提取的特征在预测中的附加价值。最后，还比较了 3 种自动分割（2 种基于阈值和 1 种 3D U-Net）。所有结果均采用一致性指数（C 指数）进行评估。
未经调和的放射组学特征与临床因素相结合，在测试集中构建的模型 C 指数为 0.69。最佳版本的 ComBat 调和策略，即在 FS 之后，分别针对特征组，并依赖于聚类确定的标签，实现了 0.71 的 C 指数。使用肿瘤亚体积提取的特征进一步提高了 C 指数至 0.72。依赖于自动分割的模型与参考轮廓相比，预测性能接近但略低（0.67-0.70）。
标准的放射组学流程可对头颈癌多中心队列的 PFS 进行预测。应用特定的 ComBat 调和策略可提高性能。肿瘤内亚体积特征的提取和自动分割分别有助于改善和自动化预后建模。
