MRI深度学习联合免疫评分的直肠癌远处转移预测列线图
本研究回顾性纳入306例直肠癌患者,基于术前T2WI构建深度学习模型,并结合CD3+/CD8+免疫评分及临床指标建立列线图。列线图预测5年无远处转移生存的训练集与测试集AUC分别为0.922和0.914,可有效进行风险分层。
要点
- 列线图整合术前MRI深度学习评分、免疫评分及临床指标,预测5年无远处转移生存AUC达0.914以上。
- 低免疫评分患者远处转移风险更高、无远处转移生存更差(P<0.001)。
- 列线图可将患者分为高、低风险组,高风险组无远处转移生存显著更差。
核心结论
- 整合MRI深度学习评分、免疫评分和临床预测因素的列线图在直肠癌个体化远处转移预测和预后分层中表现良好。
研究设计与样本
- 回顾性单中心研究,纳入306例接受MRI及手术的直肠癌患者,平均年龄59.7±11.2岁。
- 基于术前T2加权图像开发深度学习模型,免疫评分通过术后标本CD3+和CD8+免疫组化确定。
- 采用Cox回归筛选临床预测因素,构建列线图,以C指数、AUC、校准曲线和决策曲线评估模型。
关键影像表现/征象
- 基于术前MRI T2加权图像的深度学习特征用于构建预测模型。
- 低免疫评分与更高的远处转移风险和更差的无远处转移生存相关(P<0.001)。
诊断标准与关键数值
- 训练集和测试集列线图C指数分别为0.807和0.882。
- 预测5年无远处转移生存的训练集AUC为0.922,测试集AUC为0.914。
- 免疫评分基于术后标本CD3+和CD8+T细胞免疫组化结果确定。
- 97例(31.7%)患者出现远处转移或死亡,中位随访45.8个月(IQR,33.9-85.8)。
临床应用与阅片要点
- 该列线图可为直肠癌术后管理提供个体化远处转移风险预测工具。
- 列线图可有效将患者分为高、低风险组,高风险亚组无远处转移生存显著更差(Log-rank,P<0.001)。
局限性
- 回顾性单中心研究设计,模型外部推广性未经多中心验证。
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
RATIONALE AND OBJECTIVES: To evaluate the performance of nomogram integrating MRI-based deep learning (DL) and immunoscore (IS) for predicting distant metastasis (DM) and prognostic stratification in rectal cancer (RC).
MATERIALS AND METHODS: This retrospective single-center study included 306 RC patients (mean age, 59.7±11.2 years) who underwent MRI and surgery. A DL model was developed from preoperative T2-weighted images. The IS was determined on surgical specimens via immunohistochemistry for CD3+ and CD8+ T cells. A nomogram was constructed by integrating the DL_score, IS, and clinical predictors identified by Cox regression. Model performance was assessed using the concordance index (C-index), area under the curve (AUC), calibration curves, and decision curve analysis. Feature importance was measured by the SHapley Additive exPlanations method and patient stratification was assessed through Kaplan-Meier analysis.
RESULTS: At the cutoff date, 97 (31.7%) had experienced DM or death, with a median follow-up of 45.8 months (IQR, 33.9-85.8). Patients with lower IS showed significantly higher DM risk and worse DM-free survival (P < 0.001). The DL_score, IS, and clinical predictors were used to construct the nomogram with C-indexes of 0.807 and 0.882 in training and test set, with AUCs of 0.922 and 0.914 for predicting 5-year DM-free survival. Nomogram effectively stratified patients into high- and low-risk groups and high-risk subgroups had significantly worse DM-free survival (Log-rank, P < 0.001).
CONCLUSIONS: The integrated nomogram demonstrates strong performance for individualized DM risk prediction and prognostic stratification in RC, providing a clinically useful tool for postoperative management.
引用
- Jiang, Sun, Guo, et al. A Nomogram Integrating Deep Learning and Immunoscore for Predicting Distant Metastasis and Prognosis in Rectal Cancer. Acad Radiol. 2026. PMID: 42805866. doi:10.1016/j.acra.2026.09.009
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。