整合深度学习病理组学与MRI影像组学预测子宫内膜癌微卫星不稳定性的一种新模型
回顾性纳入136例经手术证实的子宫内膜癌患者,按7:3分为训练集96例和验证集40例,基于mpMRI序列和全切片图像提取影像组学与深度学习病理组学特征构建DLPRM模型。DLPRM在训练集预测MSI状态的AUC为0.960(95%CI 0.936-0.984),验证集AUC为0.917(95%CI 0.824-1.000),决策曲线分析显示DLPRM具有相对更高的临床净获益。
要点
- DLPRM在训练集预测MSI的AUC为0.960(95%CI 0.936-0.984),验证集AUC为0.917(95%CI 0.824-1.000)。
- 最终选取9个影像组学特征和27个病理组学特征分别构建RS和DLPS,DLPS与RS的AUC在训练集和验证集为0.817至0.943。
- 决策曲线分析显示DLPRM具有相对更高的临床净获益。
核心结论
- DLPRM能基于治疗前病理影像组学图像有效预测EC患者的MSI状态,具有较高准确性和稳健性,可能为临床医生对EC的个体化管理提供新工具。
研究设计与样本
- 回顾性研究,共纳入136例经手术证实的EC患者,随机按7:3分为训练集96例和验证集40例;使用ResNet50提取深度学习病理组学特征,Pyradiomics从T2WI、DWI和晚动脉期(AP)序列提取影像组学特征,基于多层感知机(MLP)构建DLPRM,并与RS和DLPS两个单尺度特征模型比较。
诊断标准与关键数值
- DLPRM预测MSI状态:训练集AUC 0.960(95%CI 0.936-0.984),验证集AUC 0.917(95%CI 0.824-1.000);DLPS与RS的AUC在训练集和验证集为0.817至0.943;最终选取9个影像组学特征和27个病理组学特征构建RS和DLPS。
临床应用与阅片要点
- 作者认为DLPRM可基于治疗前病理影像组学图像有效预测EC患者MSI状态,可能为临床医生对EC的个体化管理提供新工具。
局限性
- 原文未报告局限性。
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 develop and validate a novel model based on multiparametric MRI (mpMRI) and whole slide images (WSIs) for predicting microsatellite instability (MSI) status in endometrial cancer (EC) patients.
MATERIALS AND METHODS: A total of 136 surgically confirmed EC patients were included in this retrospective study. Patients were randomly divided into a training set (96 patients) and a validation set (40 patients) in a 7:3 ratio. Deep learning with ResNet50 was used to extract deep-learning pathomics features, while Pyradiomics was applied to extract radiomics features specifically from sequences including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and late arterial phase (AP). we developed a deep learning pathoradiomics model (DLPRM) by multilayer perceptron (MLP) based on radiomics features and pathomics features. Furthermore, we validated the DLPRM comprehensively, and compared it with two single-scale signatures-including the area under the receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1-score. Finally, we employed shapley additive explanations (SHAP) to elucidate the mechanism of prediction model.
RESULTS: After undergoing feature selection, a final set of nine radiomics features and 27 pathomics features were selected to construct the radiomics signature (RS) and the deep learning pathomics signature (DLPS). The DLPRM combining the RS and DLPS had favorable performance for the prediction of MSI status in the training set (AUC 0.960 [95% CI 0.936-0.984]), and in the validation set (AUC 0.917 [95% CI 0.824-1.000]). The AUCs of DLPS and RS ranged from 0.817 to 0.943 across the training and validation sets. The decision curve analysis indicated the DLPRM had relatively higher clinical net benefits.
CONCLUSION: DLPRM can effectively predict MSI status in EC patients based on pretreatment pathoradiomics images with high accuracy and robustness, could provide a novel tool to assist clinicians in individualized management of EC.
引用
- Zhou L, Zheng L, Hong C, et al. A Novel Model for Predicting Microsatellite Instability in Endometrial Cancer: Integrating Deep Learning-Pathomics and MRI-Based Radiomics. Acad Radiol. 2025. PMID: 40866275. doi:10.1016/j.acra.2025.07.050
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。