Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy.
Radiology Department, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Milan, Italy.
NMR Biomed. 2022 Apr;35(4):e4265. doi: 10.1002/nbm.4265. Epub 2020 Feb 3.
In this paper, several radiomics-based predictive models of response to induction chemotherapy (IC) in sinonasal cancers (SNCs) are built and tested. Models were built as a combination of radiomic features extracted from three types of MRI images: T1-weighted images, T2-weighted images and apparent diffusion coefficient (ADC) maps. Fifty patients (aged 54 ± 12 years, 41 men) were included in this study. Patients were classified according to their response to IC (25 responders and 25 nonresponders). Not all types of images were acquired for all of the patients: 49 had T1-weighted images, 50 had T2-weighted images and 34 had ADC maps. Only in a subset of 33 patients were all three types of image acquired. Eighty-nine radiomic features were extracted from the MRI images. Dimensionality reduction was performed by using principal component analysis (PCA) and by selecting only the three main components. Different algorithms (trees ensemble, K-nearest neighbors, support vector machine, naïve Bayes) were used to classify the patients as either responders or nonresponders. Several radiomic models (either monomodality or multimodality obtained by a combination of T1-weighted, T2-weighted and ADC images) were developed and the performance was assessed through 100 iterations of train and test split. The area under the curve (AUC) of the models ranged from 0.56 to 0.78. Trees ensemble, support vector machine and naïve Bayes performed similarly, but in all cases ADC-based models performed better. Trees ensemble gave the highest AUC (0.78 for the T1-weighted+T2-weighted+ADC model) and was used for further analyses. For trees ensemble, the models based on ADC features performed better than those models that did not use those features (P < 0.02 for one-tail Hanley test, AUC range 0.68-0.78 vs 0.56-0.69) except the T1-weighted+ADC model (AUC 0.71 vs 0.69, nonsignificant differences). The results suggest the relevance of ADC-based radiomics for prediction of response to IC in SNCs.
本文构建并测试了几种基于放射组学的预测模型，用于预测鼻腔鼻窦癌（SNC）对诱导化疗（IC）的反应。模型是基于从三种 MRI 图像（T1 加权图像、T2 加权图像和表观扩散系数（ADC）图）中提取的放射组学特征组合构建的。本研究纳入了 50 名患者（年龄 54±12 岁，男性 41 名）。根据患者对 IC 的反应将其分类（25 名应答者和 25 名无应答者）。并非所有类型的图像都可用于所有患者：49 名患者有 T1 加权图像，50 名患者有 T2 加权图像，34 名患者有 ADC 图。只有在 33 名患者的亚组中采集到了所有三种类型的图像。从 MRI 图像中提取了 89 个放射组学特征。通过主成分分析（PCA）和仅选择三个主要成分进行降维。使用不同的算法（树集成、K-近邻、支持向量机、朴素贝叶斯）对患者进行分类，分为应答者或无应答者。开发了几种放射组学模型（通过 T1 加权、T2 加权和 ADC 图像的组合获得的单模态或多模态），通过 100 次训练和测试分割迭代评估性能。模型的曲线下面积（AUC）范围为 0.56 至 0.78。树集成、支持向量机和朴素贝叶斯的性能相似，但在所有情况下，基于 ADC 的模型表现更好。树集成的 AUC 最高（基于 T1 加权+T2 加权+ADC 模型的 AUC 为 0.78），并用于进一步分析。对于树集成，基于 ADC 特征的模型比不使用这些特征的模型表现更好（单侧 Hanley 检验，P < 0.02，AUC 范围 0.68-0.78 与 0.56-0.69），除了 T1 加权+ADC 模型（AUC 为 0.71 与 0.69，无显著差异）。结果表明，ADC 基放射组学对预测 SNC 对 IC 的反应具有相关性。
