拓扑感知的参数高效适配用于跨数据集视网膜血管分割
Topology-Aware Parameter-Efficient Adaptation for Cross-Dataset Retinal Vessel Segmentation
浏览论文内容
中文总结 AI 辅助
提出TAPDecoderFT框架，通过共享源参数、低秩残差和可训练解码路径，在严格参数预算下实现拓扑感知的视网膜血管分割，优于现有方法并接近全微调性能。
中文摘要 AI 辅助
视网膜血管分割在多域部署中要求源模型适应在成像条件和标注规范上存在差异的域。传统的参数高效微调减少了目标特定的存储，但其高度受限的适配子空间可能不足以重建细小的、连通的血管结构。因此，我们研究应如何分配目标特定的容量，以使拓扑感知的监督在严格的每域参数预算下仍然有效。基于这一原则，我们提出了TAPDecoderFT，一种拓扑响应、角色结构的适配框架。具体而言，TAPDecoderFT在部署域之间共享固定的源参数状态，使用低秩残差进行目标特定的私有/融合特征混合，并保留一个可训练的高分辨率重建路径，包括解码器、输出头和细化模块。为了促进结构上忠实的预测，紧凑的目标状态与一个区域重叠和拓扑感知的目标联合优化，该目标鼓励中心线连续性和细分支恢复。它在所有六个方向上相比GenericLoRA-r4和窄TAP-r4提高了DSC和clDice，并与全微调相当。
英文摘要
Retinal vessel segmentation in multi-domain deployment requires a source model to adapt to domains that differ in imaging conditions and annotation conventions. Conventional parameter-efficient fine-tuning reduces target-specific storage, but its highly restricted adaptation subspace can be insufficient for reconstructing thin, connected vascular structures. We therefore ask how target-specific capacity should be allocated so that topology-aware supervision remains effective under a strict per-domain parameter budget. Based on this principle, we propose TAPDecoderFT, a topology-responsive, role-structured adaptation framework. Specifically, TAPDecoderFT shares a fixed source parameter state across deployment domains, uses low-rank residuals for target-specific private/fusion feature mixing, and retains a trainable dense-reconstruction path comprising the decoder, output head, and refinement module. To promote structurally faithful predictions, the compact target state is jointly optimized with a region-overlap and topology-aware objective that encourages centerline continuity and thin-branch recovery. It improves both DSC and clDice over GenericLoRA-r4 and narrow TAP-r4 in all six directions and is comparable to full fine-tuning.
