用密集解码提升病理肿瘤分割边界精度
Dino-NestedUNet: Unlocking Foundation Vision Encoders for Pathology Tumor Bulk Segmentation via Dense Decoding
- 采用密集路径连接实现特征连续复用
- 在三个数据集上显著优于UNet++和标准Dino-UNet
- 零样本测试证明跨域泛化能力强，适合临床部署
视觉基础模型（如DINOv3）为计算病理学提供丰富语义表征，但现有方法多将冻结的编码器与轻量解码器结合，导致容量不匹配，影响浸润性肿瘤整体分割的边界精度。本文提出Dino-NestedUNet，将预训练DINOv3编码器与嵌套密集解码器结合。解码器采用密集网格结构，替代稀疏跳跃连接和线性上采样，实现中间特征的持续复用与多尺度重校准，使高层语义与低层形态纹理在重建过程中对齐。在三个组织病理学队列（多中心CHTN、机构OSU、CAMELYON16）上评估，结果一致优于UNet++及标准Dino-UNet变体，尤其在跨域迁移场景表现更优。进一步通过零样本评估验证外部泛化能力：仅在CHTN上训练，直接测试未见的TIGER WSIBULK和OSU CRC数据集，无需微调。结果表明，密集解码是解锁基础编码器在边界敏感病理分割中潜力的关键。
原文摘要 · Abstract (English)
Vision foundation models (VFMs), such as DINOv3, provide rich semantic representations that are promising for computational pathology. However, many current adaptations pair frozen VFMs with lightweight decoders, creating a capacity mismatch that often limits boundary fidelity for infiltrative tumor bulk segmentation. This paper presents Dino-NestedUNet, a framework that couples a pre-trained DINOv3 encoder with a Nested Dense Decoder. Instead of sparse skip connections and linear upsampling, the proposed decoder forms a dense grid of intermediate pathways to enable continuous feature reuse and multi-scale recalibration, aligning high-level semantics with low-level morphological textures during reconstruction. We evaluate Dino-NestedUNet on three histopathology cohorts (multi-center CHTN, institutional OSU, and CAMELYON16) and observe consistent improvements over UNet++ and standard Dino-UNet variants, particularly under cross-domain shift. To further assess external generalization, we perform zero-shot evaluation by training on CHTN and directly testing on unseen TIGER WSIBULK and OSU CRC cohorts without fine-tuning. These results suggest that dense decoding is a key ingredient for unlocking foundation encoders in boundary-sensitive pathology segmentation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。