Fiz Francesco, Rossi Noemi, Langella Serena, Ruzzenente Andrea, Serenari Matteo, Ardito Francesco, Cucchetti Alessandro, Gallo Teresa, Zamboni Giulia, Mosconi Cristina, Boldrini Luca, Mirarchi Mariateresa, Cirillo Stefano, De Bellis Mario, Pecorella Ilaria, Russolillo Nadia, Borzi Martina, Vara Giulio, Mele Caterina, Ercolani Giorgio, Giuliante Felice, Ravaioli Matteo, Guglielmi Alfredo, Ferrero Alessandro, Sollini Martina, Chiti Arturo, Torzilli Guido, Ieva Francesca, Viganò Luca
Department of Nuclear Medicine, IRCCS Humanitas Research Hospital, 20089 Milan, Italy.
MOX Laboratory, Department of Mathematics, Politecnico di Milano, 20133 Milan, Italy.
Cancers (Basel). 2023 Aug 22;15(17):4204. doi: 10.3390/cancers15174204.
Standard imaging cannot assess the pathology details of intrahepatic cholangiocarcinoma (ICC). We investigated whether CT-based radiomics may improve the prediction of tumor characteristics. All consecutive patients undergoing liver resection for ICC (2009-2019) in six high-volume centers were evaluated for inclusion. On the preoperative CT, we segmented the ICC (Tumor-VOI, i.e., volume-of-interest) and a 5-mm parenchyma rim around the tumor (Margin-VOI). We considered two types of pathology data: tumor grading (G) and microvascular invasion (MVI). The predictive models were internally validated. Overall, 244 patients were analyzed: 82 (34%) had G3 tumors and 139 (57%) had MVI. For G3 prediction, the clinical model had an AUC = 0.69 and an Accuracy = 0.68 at internal cross-validation. The addition of radiomic features extracted from the portal phase of CT improved the model performance (Clinical data+Tumor-VOI: AUC = 0.73/Accuracy = 0.72; +Tumor-/Margin-VOI: AUC = 0.77/Accuracy = 0.77). Also for MVI prediction, the addition of portal phase radiomics improved the model performance (Clinical data: AUC = 0.75/Accuracy = 0.70; +Tumor-VOI: AUC = 0.82/Accuracy = 0.73; +Tumor-/Margin-VOI: AUC = 0.82/Accuracy = 0.75). The permutation tests confirmed that a combined clinical-radiomic model outperforms a purely clinical one ( < 0.05). The addition of the textural features extracted from the arterial phase had no impact. In conclusion, the radiomic features of the tumor and peritumoral tissue extracted from the portal phase of preoperative CT improve the prediction of ICC grading and MVI.
标准成像无法评估肝内胆管癌（ICC）的病理细节。我们研究了基于CT的影像组学是否可以改善对肿瘤特征的预测。对六个高容量中心（2009 - 2019年）所有因ICC接受肝切除术的连续患者进行纳入评估。在术前CT上，我们分割了ICC（肿瘤感兴趣区，即肿瘤体积，Tumor - VOI）以及肿瘤周围5毫米的实质边缘（边缘感兴趣区，Margin - VOI）。我们考虑了两种病理数据：肿瘤分级（G）和微血管侵犯（MVI）。对预测模型进行了内部验证。总共分析了244例患者：82例（34%）为G3级肿瘤，139例（57%）有MVI。对于G3预测，临床模型在内部交叉验证时AUC = 0.69，准确率 = 0.68。从CT门静脉期提取的影像组学特征的加入改善了模型性能（临床数据 + 肿瘤 - VOI：AUC = 0.73/准确率 = 0.72； + 肿瘤/边缘 - VOI：AUC = 0.77/准确率 = 0.77）。同样对于MVI预测，门静脉期影像组学特征的加入也改善了模型性能（临床数据：AUC = 0.75/准确率 = 0.70； + 肿瘤 - VOI：AUC = 0.82/准确率 = 0.73； + 肿瘤/边缘 - VOI：AUC = 0.82/准确率 = 0.75）。置换检验证实联合临床 - 影像组学模型优于单纯的临床模型（<0.05）。从动脉期提取的纹理特征的加入没有影响。总之，术前CT门静脉期提取的肿瘤及瘤周组织的影像组学特征改善了ICC分级和MVI的预测。
