整合治疗前MRI与全切片图像的多任务深度学习预测局部晚期鼻咽癌诱导化疗反应与生存
Multi-task deep learning integrating pretreatment MRI and whole slide images predicts induction chemotherapy response and survival in locally advanced nasopharyngeal carcinoma.
文献信息
| PMID | 42832514 |
|---|---|
| 原文 | 在 PubMed 查看原文 ↗ |
| 发表日期 | 2026 |
| 作者 | Jing Hou |
| 作者单位 | Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, Hunan, People's Republic of China. |
| 期刊 | PLOS digital health |
| SCI 分区 | Q1 |
| IF | 7.7 |
| 研究类型 | AI/ML · 临床 |
| 所属专科 | 鼻咽癌 |
中文摘要
背景： 预测诱导化疗（IC）反应和总生存期（OS）对于优化局部晚期鼻咽癌（LANPC）患者的治疗至关重要。本研究旨在开发并验证一个整合治疗前MRI与全切片图像（WSIs）的多任务深度学习模型，以预测LANPC的IC反应和OS。方法：回顾性收集404例LANPC患者的治疗前MRI和WSIs，构建多任务模型（MoEMIL），用于同时预测早期IC反应和OS。在我们的队列中，未观察到疾病进展病例；因此，反应差组仅由疾病稳定患者组成。MoEMIL采用多实例学习处理WSIs，使用PyRadiomics和卷积神经网络（ResNet50）提取MRI特征，并通过多门混合专家架构融合多模态特征。应用聚类约束注意力多实例学习和梯度加权类激活映射进行可视化和解释。结果：MoEMIL有效将患者分层为IC反应好和反应差组，在训练集、验证集和测试集中的曲线下面积分别为0.917、0.869和0.801。在测试集中，MoEMIL在两个终点上均显著优于深度学习放射组学模型和TNM分期。与病理组学模型相比，MoEMIL在OS方面取得显著改善（P=0.0049），在IC反应方面有边缘改善（P=0.064）。该模型可将患者分层为高和低OS风险组（P<0.05）。结论：MoEMIL可能作为LANPC早期诱导化疗反应预测和预后分层的辅助工具。
英文摘要
Predicting response to induction chemotherapy (IC) and overall survival (OS) is critical for optimizing treatment in patients with locally advanced nasopharyngeal carcinoma (LANPC). This study aimed to develop and validate a multi-task deep learning model integrating pretreatment MRI and whole slide images (WSIs) to predict IC response and OS in LANPC. Pretreatment MRI and WSIs from 404 patients with LANPC were retrospectively collected to construct a multi-task model (MoEMIL) for the simultaneous prediction of early IC response and OS. In our cohort, no progressive disease cases were observed; therefore, the poor responder group consisted exclusively of patients with stable disease. MoEMIL employed multi-instance learning to process WSIs, PyRadiomics and a convolutional neural network (ResNet50) to extract MRI features, and fused multimodal features through a multi-gate mixture-of-experts architecture. Clustering-constrained attention multiple instance learning and gradient-weighted class activation mapping were applied for visualization and interpretation. MoEMIL effectively stratified patients into good and poor IC response groups, achieving areas under the curve of 0.917, 0.869, and 0.801 in the train, validation, and test sets, respectively. In the test set, MoEMIL significantly outperformed the deep learning radiomics model and TNM staging for both endpoints. Compared to the Pathomics model, MoEMIL achieved significant improvement for OS (P = 0.0049) and borderline improvement for IC response (P = 0.064). The model could stratify patients into high- and low-risk OS groups (P < 0.05). MoEMIL might be an adjunctive tool for early induction chemotherapy response prediction and prognostic stratification in LANPC.