基于术前直肠癌MRI的影像组学预测异时性肝转移
本研究纳入130例初诊无远处转移的直肠癌患者,构建DWI、HD T2WI及联合影像组学模型,并联合EMVI、mrT、mrN及肿瘤下缘距肛缘距离建立融合模型。融合模型在测试集AUC达0.911,决策曲线与列线图显示良好临床效能,可辅助制定个体化监测与治疗方案。
要点
- 术前直肠癌MRI影像组学融合模型可有效预测异时性肝转移,测试集AUC为0.911。
- DWI+HD T2WI联合模型预测效能显著优于单一DWI或HD T2WI模型(P<0.05)。
- 融合模型纳入的临床特征包括EMVI、mrT、mrN及肿瘤下缘距肛缘距离。
核心结论
- 基于初诊直肠癌多参数MRI的影像组学联合临床特征融合模型能有效预测异时性肝转移,辅助个体化监测与治疗决策。
研究设计与样本
- 回顾性纳入301例经组织病理学确诊的直肠癌患者中初诊无远处转移的130例,按随访3年内肝转移是否在初诊6个月后检出分为MLM组(n=49)和非MLM组(n=81)。
- 按7:3分层抽样分为训练集(n=91)和测试集(n=39),分别构建DWI模型、HD T2WI模型及DWI+HD T2WI模型,并筛选临床特征(含非影像组学MRI特征)构建融合模型。
- 以测试集评估模型性能,计算训练集与测试集的ROC曲线下面积(AUC)。
诊断标准与关键数值
- 测试集中DWI+HD T2WI模型AUC显著高于单独DWI或HD T2WI模型(P<0.05)。
- 融合模型在测试集的AUC为0.911。
- 筛选出的临床特征包括EMVI、mrT分期、mrN分期及肿瘤下缘距肛缘距离。
临床应用与阅片要点
- 术前直肠癌MRI影像组学分析可整合DWI与高分辨率T2WI特征,联合EMVI、mrT、mrN及肿瘤位置等临床特征提升异时性肝转移预测效能。
- 融合模型以列线图和决策曲线呈现,便于临床在初诊时识别高危患者并制定个体化随访间隔与治疗计划。
局限性
- 单中心回顾性研究,样本量有限(130例),外部验证不足。
- MLM组样本量较小(n=49),模型稳定性需进一步验证。
- 随访时间为3年,更长期异时性肝转移的预测效能未评估。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: At present, there are few effective method to predict metachronous liver metastasis (MLM) from rectal cancer. We aim to investigate the efficacy of radiomics based on multiparametric MRI of first diagnosed rectal cancer in predicting MLM from rectal cancer.
METHODS: From 301 consecutive histopathologically confirmed rectal cancer patients, 130 patients who have no distant metastasis detected at the time of diagnosis were enrolled and divided into MLM group (n = 49) and non-MLM group (n = 81) according to whether liver metastasis be detected later than 6 month after the first diagnosis of rectal cancer within 3 years' follow-up. The 130 patients were divided into a training set (n = 91) and a testing set (n = 39) at a ratio of 7:3 by stratified sampling using SPSS 24.0 software. The DWI model, HD T2WI model, and DWI + HD T2WI model were constructed respectively. The best performing model was selected and combined with the screened clinical features (including non-radiomics MRI features) to construct a fusion model. The testing set was used to evaluate the performance of the models, and the area under the curve (AUC) of receiver operating characteristics (ROC) was calculated for both the training set and the testing set.
RESULTS: The AUC of the DWI + HD T2WI model in the testing set was higher than that of the DWI or the HD T2 model alone with statistically significance (P < 0.05). The screened clinical features were extramural vascular invasion (EMVI), T and N stages in MRI (mrT, mrN), and the distance from the lower edge of the tumor to the anal verge. The AUC of the fusion model in the testing set was 0.911. Decision curves and nomogram also showed that the fusion model had excellent clinical performance.
CONCLUSION: The fusion model of primary rectal cancer MRI based radiomics combing clinical features can effectively predict MLM from rectal cancer, which may assist clinicians in formulating individualized monitoring and treatment plans.
引用
- Li, Kang, Liu, et al. Radiomics based on preoperative rectal cancer MRI to predict the metachronous liver metastasis. Abdom Radiol (NY). 2022. PMID: 36529807. doi:10.1007/s00261-022-03773-1
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。