Morelli Letizia, Paganelli Chiara, Marvaso Giulia, Parrella Giovanni, Annunziata Simone, Vicini Maria Giulia, Zaffaroni Mattia, Pepa Matteo, Summers Paul Eugene, De Cobelli Ottavio, Petralia Giuseppe, Jereczek-Fossa Barbara Alicja, Baroni Guido
Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy.
Department of Radiation Oncology, European Institute of Oncology (IEO), Milan, Italy.
Med Phys. 2024 Nov;51(11):8096-8107. doi: 10.1002/mp.17355. Epub 2024 Aug 22.
Prostate cancer (PCa) is a highly heterogeneous disease, making tailored treatment approaches challenging. Magnetic resonance imaging (MRI), notably diffusion-weighted imaging (DWI) and the derived Apparent Diffusion Coefficient (ADC) maps, plays a crucial role in PCa characterization. In this context, radiomics is a very promising approach able to disclose insights from MRI data. However, the sensitivity of radiomic features to MRI settings, encompassing DWI protocols and multicenter variations, requires the development of robust and generalizable models.
To develop a comprehensive radiomics framework for noninvasive PCa characterization using ADC maps, focusing on identifying reliable imaging biomarkers against intra- and inter-institution variations.
Two patient cohorts, including an internal cohort (118 PCa patients) used for both training (75%) and hold-out testing (25%), and an external cohort (50 PCa patients) for independent testing, were employed in the study. DWI images were acquired with three different DWI protocols on two different MRI scanners: two DWI protocols acquired on a 1.5-T scanner for the internal cohort, and one DWI protocol acquired on a 3-T scanner for the external cohort. One hundred and seven radiomics features (i.e., shape, first order, texture) were extracted from ADC maps of the whole prostate gland. To address variations in DWI protocols and multicenter variability, a dedicated pipeline, including two-way ANOVA, sequential-feature-selection (SFS), and ComBat features harmonization was implemented. Mann-Whitney U-tests (α = 0.05) were performed to find statistically significant features dividing patients with different tumor characteristics in terms of Gleason score (GS) and T-stage. Support-Vector-Machine models were then developed to predict GS and T-stage, and the performance was assessed through the area under the curve (AUC) of receiver-operating-characteristic curves.
Downstream of ANOVA, two subsets of 38 and 41 features stable against DWI protocol were identified for GS and T-stage, respectively. Among these, SFS revealed the most predictive features, yielding an AUC of 0.75 (GS) and 0.70 (T-stage) in the hold-out test. Employing ComBat harmonization improved the external-test performance of the GS model, raising AUC from 0.72 to 0.78.
By incorporating stable features with a harmonization procedure and validating the model on an external dataset, model robustness, and generalizability were assessed, highlighting the potential of ADC and radiomics for PCa characterization.
前列腺癌（PCa）是一种高度异质性疾病，这使得量身定制的治疗方法具有挑战性。磁共振成像（MRI），尤其是扩散加权成像（DWI）及其衍生的表观扩散系数（ADC）图，在PCa特征描述中起着关键作用。在这种背景下，放射组学是一种非常有前景的方法，能够从MRI数据中揭示见解。然而，放射组学特征对MRI设置（包括DWI协议和多中心差异）的敏感性，要求开发强大且可推广的模型。
开发一个使用ADC图对PCa进行无创特征描述的综合放射组学框架，重点是识别针对机构内和机构间差异的可靠成像生物标志物。
本研究采用了两个患者队列，包括一个内部队列（118例PCa患者），用于训练（75%）和保留测试（25%），以及一个外部队列（50例PCa患者）用于独立测试。在两台不同的MRI扫描仪上使用三种不同的DWI协议采集DWI图像：在1.5-T扫描仪上为内部队列采集两种DWI协议，在3-T扫描仪上为外部队列采集一种DWI协议。从整个前列腺的ADC图中提取了107个放射组学特征（即形状、一阶、纹理）。为了解决DWI协议的差异和多中心变异性，实施了一个专门的流程，包括双向方差分析、顺序特征选择（SFS）和ComBat特征协调。进行曼-惠特尼U检验（α = 0.05），以找到在Gleason评分（GS）和T分期方面区分具有不同肿瘤特征患者的统计学显著特征。然后开发支持向量机模型来预测GS和T分期，并通过接收者操作特征曲线的曲线下面积（AUC）评估性能。
在方差分析之后，分别为GS和T分期确定了38个和41个对DWI协议稳定的特征子集。其中，SFS揭示了最具预测性的特征，在保留测试中GS的AUC为0.75，T分期的AUC为0.70。采用ComBat协调提高了GS模型的外部测试性能，AUC从0.72提高到0.78。
通过将稳定特征与协调程序相结合，并在外部数据集上验证模型，评估了模型的稳健性和可推广性，突出了ADC和放射组学在PCa特征描述中的潜力。
