机器学习放射组学可预测肝内胆管细胞癌切除术后早期肝复发。

Machine learning radiomics can predict early liver recurrence after resection of intrahepatic cholangiocarcinoma.

机构信息

Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, USA; Department of Surgery, Brigham and Women's Hospital, Boston, MA, USA.

Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, USA; Department of Surgery, Cangzhou Central Hospital, Cangzhou, Hebei, China.

出版信息

HPB (Oxford). 2022 Aug;24(8):1341-1350. doi: 10.1016/j.hpb.2022.02.004. Epub 2022 Feb 17.

BACKGROUND

Most patients recur after resection of intrahepatic cholangiocarcinoma (IHC). We studied whether machine-learning incorporating radiomics and tumor size could predict intrahepatic recurrence within 1-year.

METHODS

This was a retrospective analysis of patients with IHC resected between 2000 and 2017 who had evaluable computed tomography imaging. Texture features (TFs) were extracted from the liver, tumor, and future liver remnant (FLR). Random forest classification using training (70.3%) and validation cohorts (29.7%) was used to design a predictive model.

RESULTS

138 patients were included for analysis. Patients with early recurrence had a larger tumor size (7.25 cm [IQR 5.2-8.9] vs. 5.3 cm [IQR 4.0-7.2], P = 0.011) and a higher rate of lymph node metastasis (28.6% vs. 11.6%, P = 0.041), but were not more likely to have multifocal disease (21.4% vs. 17.4%, P = 0.643). Three TFs from the tumor, FD1, FD30, and IH4 and one from the FLR, ACM15, were identified by feature selection. Incorporation of TFs and tumor size achieved the highest AUC of 0.84 (95% CI 0.73-0.95) in predicting recurrence in the validation cohort.

CONCLUSION

This study demonstrates that radiomics and machine-learning can reliably predict patients at risk for early intrahepatic recurrence with good discrimination accuracy.

背景

大多数肝内胆管癌（IHC）患者在切除后会复发。我们研究了机器学习结合放射组学和肿瘤大小是否可以预测 1 年内肝内复发。

方法

这是一项回顾性分析，纳入了 2000 年至 2017 年间接受可评估 CT 成像的 IHC 切除患者。从肝脏、肿瘤和未来肝段（FLR）中提取纹理特征（TFs）。使用训练队列（70.3%）和验证队列（29.7%）的随机森林分类来设计预测模型。

结果

共纳入 138 例患者进行分析。早期复发患者肿瘤较大（7.25cm[IQR 5.2-8.9]比 5.3cm[IQR 4.0-7.2]，P=0.011），淋巴结转移率较高（28.6%比 11.6%，P=0.041），但多发病灶的可能性并无差异（21.4%比 17.4%，P=0.643）。通过特征选择，从肿瘤中确定了三个 TFs，FD1、FD30 和 IH4，以及从 FLR 中确定了一个 TF，ACM15。TFs 和肿瘤大小的综合运用在验证队列中预测复发的 AUC 最高，为 0.84（95%CI 0.73-0.95）。