基于混合CNN-Transformer架构的联邦多任务学习用于膀胱肿瘤分割与MIBC分类
Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture
- Indian Institute of Information Technology Allahabad（印度阿拉巴德信息技术学院）
- Manipal University Jaipur（斋浦尔马尼帕尔大学）
- Norwegian University of Science and Technology（挪威科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出联邦多任务学习框架，采用结合ResNet-34与Swin-Tiny Transformer的Swin Hybrid模型，在FedBCa数据集上实现跨机构膀胱肿瘤分割与MIBC分类，取得最优性能。
AI中文摘要：
从T2加权MRI中准确进行膀胱肿瘤分割和肌层浸润评估对治疗规划至关重要，但由于无法集中汇集患者数据，且不同扫描仪和采集方案的成像特征存在差异，在各医疗机构间开发鲁棒性模型颇具挑战。我们提出一种联邦多任务学习框架，用于在四个临床中心联合开展膀胱肿瘤分割与MIBC（肌层浸润性膀胱癌）/NMIBC（非肌层浸润性膀胱癌）分类。所提出的Swin Hybrid模型结合了用于局部纹理和边界信息的ResNet-34分支，以及用于全局解剖上下文的Swin-Tiny Transformer；分割引导分类机制进一步利用肿瘤定位信息支持MIBC预测。我们还研究了集中式和联邦式训练下的多种增强策略，以提升对多中心变异性的鲁棒性。在FedBCa数据集上的实验表明，Swin Hybrid在评估的架构中于分割和分类间提供了最佳整体平衡；在联邦式训练下，Geo+Elastic增强策略取得了0.8100的DSC（戴斯相似系数）和0.8931的患者级AUC（受试者工作特征曲线下面积），组合得分达0.8474，为最高值。这些结果表明，无需集中患者数据，即可通过联邦式训练在多个机构间有效开展联合分割与分类任务。
英文摘要：
Accurate bladder tumor segmentation and assessment of mus- cle invasion from T2-weighted MRI are important for treatment plan- ning, but developing robust models across institutions is challenging be- cause patient data cannot be centrally pooled and imaging characteristics vary across scanners and acquisition protocols. We propose a federated multi-task learning framework for joint bladder tumor segmentation and MIBC/NMIBC classification across four clinical centers. The proposed Swin Hybrid model combines a ResNet-34 branch for local texture and boundary information with a Swin-Tiny Transformer for global anatomi- cal context. A segmentation-guided classification mechanism further uses tumor localization information to support MIBC prediction. We also investigate several augmentation strategies under both centralized and federated training to improve robustness to multi-center variability. Ex- periments on the FedBCa dataset show that the Swin Hybrid provides the best overall balance between segmentation and classification among the evaluated architectures. Under federated training, Geo+Elastic aug- mentation achieved a DSC of 0.8100 and a patient-level AUC of 0.8931, yielding the highest combined score of 0.8474. These results demonstrate that joint segmentation and classification can be effectively performed across multiple institutions using federated training without centralizing patient data.
