Yan Xin, Duan Furui, Chen Lu, Wang Runhong, Li Kexin, Sun Qiao, Fu Kuang
Department of Radiology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, China.
PET/CT Department, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, China.
Curr Oncol. 2025 Jul 30;32(8):431. doi: 10.3390/curroncol32080431.
: Predicting colorectal cancer liver metastasis (CRLM) is essential for prognostic assessment. This study aims to develop and validate an interpretable multimodal machine learning framework based on multiparametric MRI for predicting CRLM, and to enhance the clinical interpretability of the model through SHapley Additive exPlanations (SHAP) analysis and deep learning visualization. : This multicenter retrospective study included 463 patients with pathologically confirmed colorectal cancer from two institutions, divided into training (n = 256), internal testing (n = 111), and external validation (n = 96) sets. Radiomics features were extracted from manually segmented regions on axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). Deep learning features were obtained from a pretrained ResNet101 network using the same MRI inputs. A least absolute shrinkage and selection operator (LASSO) logistic regression classifier was developed for clinical, radiomics, deep learning, and combined models. Model performance was evaluated by AUC, sensitivity, specificity, and F1-score. SHAP was used to assess feature contributions, and Grad-CAM was applied to visualize deep feature attention. : The combined model integrating features across the three modalities achieved the highest performance across all datasets, with AUCs of 0.889 (training), 0.838 (internal test), and 0.822 (external validation), outperforming single-modality models. Decision curve analysis (DCA) revealed enhanced clinical net benefit from the integrated model, while calibration curves confirmed its good predictive consistency. SHAP analysis revealed that radiomic features related to T2WI texture (e.g., ) and clinical biomarkers (e.g., CA19-9) were among the most predictive for CRLM. Grad-CAM visualizations confirmed that the deep learning model focused on tumor regions consistent with radiological interpretation. : This study presents a robust and interpretable multiparametric MRI-based model for noninvasively predicting liver metastasis in colorectal cancer patients. By integrating handcrafted radiomics and deep learning features, and enhancing transparency through SHAP and Grad-CAM, the model provides both high predictive performance and clinically meaningful explanations. These findings highlight its potential value as a decision-support tool for individualized risk assessment and treatment planning in the management of colorectal cancer.
预测结直肠癌肝转移（CRLM）对于预后评估至关重要。本研究旨在开发并验证一种基于多参数MRI的可解释多模态机器学习框架，用于预测CRLM，并通过SHapley加性解释（SHAP）分析和深度学习可视化来增强模型的临床可解释性。：这项多中心回顾性研究纳入了来自两个机构的463例经病理证实的结直肠癌患者，分为训练集（n = 256）、内部测试集（n = 111）和外部验证集（n = 96）。从轴向T2加权成像（T2WI）和扩散加权成像（DWI）上手动分割的区域中提取影像组学特征。使用相同的MRI输入从预训练的ResNet101网络中获得深度学习特征。为临床、影像组学、深度学习和联合模型开发了最小绝对收缩和选择算子（LASSO）逻辑回归分类器。通过AUC、敏感性、特异性和F1分数评估模型性能。使用SHAP评估特征贡献，并应用Grad-CAM可视化深度特征注意力。：整合三种模态特征的联合模型在所有数据集中表现出最高性能，训练集、内部测试集和外部验证集的AUC分别为0.889、0.838和0.822，优于单模态模型。决策曲线分析（DCA）显示联合模型具有更高的临床净效益，而校准曲线证实其具有良好的预测一致性。SHAP分析显示，与T2WI纹理相关的影像组学特征（如 ）和临床生物标志物（如CA19-9）是CRLM最具预测性的因素。Grad-CAM可视化证实深度学习模型关注的肿瘤区域与放射学解释一致。：本研究提出了一种基于多参数MRI的强大且可解释的模型，用于无创预测结直肠癌患者的肝转移。通过整合手工制作的影像组学和深度学习特征，并通过SHAP和Grad-CAM提高透明度，该模型既具有高预测性能，又提供了具有临床意义的解释。这些发现突出了其作为结直肠癌管理中个性化风险评估和治疗计划决策支持工具的潜在价值。
