基于MRI的深度学习预测T1-2期直肠癌淋巴结转移
本研究回顾性纳入611例T1-2期直肠癌患者,利用术前T2加权图像训练多种2D/3D残差网络预测淋巴结转移,并与三位放射科医师独立评估比较。3D ResNet101在测试集表现最佳,AUC为0.79,显著高于医师合并评估的AUC 0.54(p<0.001),提示深度学习模型可优于放射科医师预测淋巴结转移。
要点
- 3D ResNet101模型在测试集预测淋巴结转移AUC为0.79,显著高于医师合并评估的0.54。
- 深度学习模型基于原发肿瘤术前MRI预测淋巴结转移,可作为医师评估的辅助工具。
- 不同网络架构诊断效能存在差异,需选择最优模型用于临床决策支持。
核心结论
- 基于原发肿瘤术前MR图像的深度学习模型预测T1-2期直肠癌淋巴结转移的效能优于放射科医师。
研究设计与样本
- 回顾性研究纳入2013年10月至2021年3月期间接受术前MRI的T1-2期直肠癌患者611例,分为训练集444例、验证集81例和测试集86例。
- 训练并测试四种2D和3D残差网络(ResNet18、ResNet50、ResNet101、ResNet152),基于T2加权图像识别淋巴结转移患者。
- 三位放射科医师独立评估MRI淋巴结状态,诊断结果与深度学习模型比较,采用AUC评估预测性能并使用DeLong方法比较。
诊断标准与关键数值
- 八种深度学习模型在训练集AUC范围为0.80(95%CI: 0.75, 0.85)至0.89(95%CI: 0.85, 0.92)。
- 八种深度学习模型在验证集AUC范围为0.77(95%CI: 0.62, 0.92)至0.89(95%CI: 0.76, 1.00)。
- 3D ResNet101模型在测试集预测淋巴结转移AUC为0.79(95%CI: 0.70, 0.89),显著高于医师合并评估AUC 0.54(95%CI: 0.48, 0.60),p < 0.001。
临床应用与阅片要点
- 对于T1-2期直肠癌患者,可考虑使用基于原发肿瘤术前T2加权图像的3D ResNet101深度学习模型辅助预测淋巴结转移,以弥补放射科医师肉眼评估的不足。
局限性
- 本研究为回顾性单中心设计,样本来自单一机构,可能存在选择偏倚。
- 深度学习模型仅在T2加权图像上训练和测试,未纳入其他序列或临床信息。
- 测试集样本量较小(86例),模型泛化能力需外部验证。
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
OBJECTIVES: This study aimed to investigate whether a deep learning (DL) model based on preoperative MR images of primary tumors can predict lymph node metastasis (LNM) in patients with stage T1-2 rectal cancer.
METHODS: In this retrospective study, patients with stage T1-2 rectal cancer who underwent preoperative MRI between October 2013 and March 2021 were included and assigned to the training, validation, and test sets. Four two-dimensional and three-dimensional (3D) residual networks (ResNet18, ResNet50, ResNet101, and ResNet152) were trained and tested on T2-weighted images to identify patients with LNM. Three radiologists independently assessed LN status on MRI, and diagnostic outcomes were compared with the DL model. Predictive performance was assessed with AUC and compared using the Delong method.
RESULTS: In total, 611 patients were evaluated (444 training, 81 validation, and 86 test). The AUCs of the eight DL models ranged from 0.80 (95% confidence interval [CI]: 0.75, 0.85) to 0.89 (95% CI: 0.85, 0.92) in the training set and from 0.77 (95% CI: 0.62, 0.92) to 0.89 (95% CI: 0.76, 1.00) in the validation set. The ResNet101 model based on 3D network architecture achieved the best performance in predicting LNM in the test set, with an AUC of 0.79 (95% CI: 0.70, 0.89) that was significantly greater than that of the pooled readers (AUC, 0.54 [95% CI: 0.48, 0.60]; p < 0.001).
CONCLUSION: The DL model based on preoperative MR images of primary tumors outperformed radiologists in predicting LNM in patients with stage T1-2 rectal cancer.
KEY POINTS: • Deep learning (DL) models with different network frameworks showed different diagnostic performance for predicting lymph node metastasis (LNM) in patients with stage T1-2 rectal cancer. • The ResNet101 model based on 3D network architecture achieved the best performance in predicting LNM in the test set. • The DL model based on preoperative MR images outperformed radiologists in predicting LNM in patients with stage T1-2 rectal cancer.
引用
- Wan, Hu, Chen, et al. Prediction of lymph node metastasis in stage T1-2 rectal cancers with MRI-based deep learning. Eur Radiol. 2023. PMID: 36905470. doi:10.1007/s00330-023-09450-1
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。