多期CT深度学习术前风险分层2-5cm胃GIST
这项回顾性多中心研究纳入427例病理确诊的2-5cm胃GIST患者,开发并外部验证基于平扫、动脉期和静脉期CT的MPFNet深度学习框架。该网络采用并行ResNet50编码器、跨期注意力模块及相位自适应加权,用于术前危险分层。内部测试集AUC为0.935,外部验证集AUC为0.894,较临床-影像组学联合模型提供增量区分能力。
要点
- MPFNet融合平扫、动脉期和静脉期CT,对2-5cm胃GIST术前危险分层具有潜在辅助价值。
- 外部验证假阴性集中于中危肿瘤(11例中9例),阅片时对中等风险病灶应保持谨慎。
- 不同CT扫描仪间模型表现存在差异,推广至新设备时需注意性能波动。
核心结论
- MPFNet在回顾性外部验证中较临床-影像组学联合模型提供增量区分能力,校准可接受。
- 该模型用于2-5cm胃GIST术前危险分层及切除方案决策支持仍需前瞻性评估。
研究设计与样本
- 回顾性多中心研究纳入427例病理确诊胃GIST患者,病灶大小2-5cm。
- 中心A患者2015年1月至2022年6月构成开发集,共240例,采用五折交叉验证进行模型选择、调参与早停。
- 中心A患者2022年7月至2023年12月构成时间独立内部测试集,共59例。
- 中心B共128例作为外部验证集,采用平扫、动脉期和静脉期CT图像分析。
- 参考对照包括临床-影像组学联合模型及三位放射科医师。
关键影像表现/征象
- 多期CT框架分析平扫、动脉期及静脉期图像,通过跨期注意力模块融合不同时相特征,未见具体形态学征象描述。
诊断标准与关键数值
- 内部测试集MPFNet AUC为0.935(95% CI:0.852-0.981),联合模型为0.872,P=0.016,NRI为0.58,IDI为0.112。
- 外部验证MPFNet AUC为0.894(95% CI:0.827-0.942),联合模型为0.831,P=0.091,NRI为0.41,IDI为0.078。
- 外部验证校准截距为-0.14,斜率为0.87(95% CI:0.64-1.10),Brier评分为0.118。
- 阈值概率为0.30-0.50时,决策曲线分析显示净获益超过联合模型。
- 外部验证中三位放射科医师的AUC范围为0.735-0.812,低于MPFNet。
临床应用与阅片要点
- MPFNet可整合多期CT信息用于2-5cm胃GIST术前危险分层,可能辅助规划切除方式。
- 外部验证假阴性集中于中危肿瘤,需警惕中等风险病灶被低估的可能性。
- 外部扫描仪上模型性能低于中心A的两台扫描仪,跨设备推广时应评估适用性。
局限性
- 该研究为回顾性设计,模型临床应用需前瞻性评估验证。
- 模型在不同CT扫描仪间表现存在差异,外部设备上的泛化能力受限。
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: To develop and externally validate a multi-phase CT deep learning framework for preoperative risk stratification of 2-5 cm gastric gastrointestinal stromal tumors (GISTs).
METHODS: This retrospective multicenter study included 427 patients with pathologically confirmed gastric GISTs. At Center A, patients treated from January 2015 to June 2022 formed the development set (n=240), in which all model selection, tuning, and early stopping were performed by five-fold cross-validation, and patients treated from July 2022 to December 2023 formed a temporally independent internal test set (n=59); Center B (n=128) served as the external validation set. Unenhanced, arterial, and venous CT images were analyzed with the Multi-Phase Fusion Network (MPFNet), which combines parallel ResNet50 encoders with a Cross-Phase Attention Module and phase-adaptive weighting. Incremental value over a combined clinical-radiomics reference model was assessed with the difference in AUC, net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration intercept and slope, and decision curve analysis; three radiologists served as additional comparators.
RESULTS: On the internal test set, MPFNet achieved an AUC of 0.935 (95% CI: 0.852-0.981) versus 0.872 for the combined model (P=0.016; NRI 0.58, IDI 0.112). On external validation, the AUC was 0.894 (95% CI: 0.827-0.942) versus 0.831 (P=0.091; NRI 0.41, IDI 0.078), with a calibration intercept of -0.14, slope of 0.87 (95% CI: 0.64-1.10), and Brier score of 0.118; net benefit exceeded that of the combined model at threshold probabilities of 0.30-0.50. The AUC was also higher than that of three radiologists (0.735-0.812 externally). External false negatives were concentrated in intermediate-risk tumors (9 of 11), and performance was lower on the external scanner than on the two Center A scanners.
CONCLUSION: In retrospective external validation, MPFNet provided incremental discrimination over a combined clinical-radiomics model with acceptable calibration for preoperative risk stratification of 2-5 cm gastric GISTs. Its use as a decision-support tool for planning the resection approach requires prospective evaluation.
引用
- Guo, Yu, Xu, et al. Cross-phase attention-based multi-phase CT deep learning for preoperative risk stratification of gastric gastrointestinal stromal tumors in a multicenter study. Eur J Radiol. 2026. PMID: 42801804. doi:10.1016/j.ejrad.2026.113237
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。