Sepehri Shima, Tankyevych Olena, Iantsen Andrei, Visvikis Dimitris, Hatt Mathieu, Cheze Le Rest Catherine
LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.
University Hospital Poitiers, Nuclear Medicine Department, Poitiers, France.
Front Oncol. 2021 Oct 18;11:726865. doi: 10.3389/fonc.2021.726865. eCollection 2021.
The aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (F-FDG PET/CT) images based on a "rough" volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses.
A cohort of 138 patients with stage II-III NSCLC treated with radiochemotherapy recruited retrospectively ( = 87) and prospectively ( = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined "rough" VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity.
Overall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 . 0.88 and 0.78 . 0.77).
Our findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.
本研究旨在探讨利用正电子发射断层扫描和计算机断层扫描与2-脱氧-2-[氟-18]氟-D-葡萄糖（F-FDG PET/CT）图像中的放射组学特征，基于包含肿瘤的“粗略”感兴趣体积（VOI）而非精确勾画来构建非小细胞肺癌（NSCLC）预后模型的能力，精确勾画肿瘤是放射组学分析中一个耗时的重要瓶颈。
回顾性（n = 87）和前瞻性（n = 51）招募了138例接受放化疗的II - III期NSCLC患者。比较了两种方法：首先，从PET（使用自动模糊局部自适应贝叶斯算法，FLAB）和CT（使用3D Slicer™的半自动方法）组件中勾画的原发性肿瘤体积中提取放射组学特征。两种勾画均在先前手动定义的包含肿瘤及其周围组织的“粗略”VOI内进行，这用于第二种方法：从这个替代VOI中提取相同的特征。然后将两组特征与临床变量相结合，并使用回顾性招募的患者作为训练集，前瞻性招募的患者作为测试集，通过相同的机器学习（ML）管道进行处理。考虑使用逻辑回归（LR）、随机森林（RF）和支持向量机（SVM），以及通过平均输出概率达成的共识，进行特征选择和建模以预测总生存期（OS）作为二元分类（中位OS或6个月OS）。根据平衡准确性、敏感性和特异性对所得模型进行比较。
总体而言，使用勾画的肿瘤体积特征可获得更好的性能。在ML算法和两个临床终点中均一致观察到这一点。然而，性能损失并不显著，特别是当考虑三种ML算法的共识时（0.89对0.88以及0.78对0.77）。
我们的研究结果表明，依靠更快、更简便的VOI定义，跳过耗时的肿瘤勾画步骤，从而促进整个放射组学工作流程的自动化，在基于放射组学的建模中实现相似水平的预后准确性是可行的。相关代价是所得模型的性能有所损失，尽管当依赖多个模型的共识时，这种损失可大大减轻。
