发表机构
Northeastern University; Australian National University（东北大学; 澳大利亚国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RFS-UNet通过利用解码器统计量对高分辨率跳跃连接进行有界残差通道重校准，在骨选择性DRR合成中提升PSNR 0.254 dB并降低平均MAE 3.91%，验证了解码器状态作为条件信号的有效性。
AI 中文摘要
骨选择性数字重建放射影像（DRR）合成依赖于高分辨率编码器细节，然而静态跳跃连接无法根据不断演化的解码器表示来条件化重用。我们探究解码器状态是否在高分辨率跳跃重用中提供了超出仅编码器自重校准的有用信息。RFS-UNet在512^2和256^2跳跃处使用池化编码器和对齐解码器统计量进行有界残差通道重校准，同时保持主干网络不变。在匹配种子seed-2026的隔离解码器条件比较中，RFS相比Self-RFS将验证PSNR提高了0.254 dB。在三个种子上，锁定测试PSNR从33.225±0.048 dB提升至33.537±0.128 dB；RFS在179/200个保留CT病例中降低了MAE，并将平均MAE降低了3.91%。它仅增加了0.117%的参数和1.169%的计次Conv2d操作。这些结果支持解码器状态作为受控配对投影合成中高分辨率特征重用的有效条件信号。
英文摘要
Bone-selective synthesis from digitally reconstructed radiographs (DRRs) requires separating skeletal signal from overlying tissue while preserving anatomical detail. U-Net skip connections supply fine encoder features, but their transfer is independent of decoder context. We introduce RFS-UNet, which lets the decoder participate in high-resolution channel recalibration. Pooled encoder and decoder features jointly predict a bounded residual scale, initialized to preserve the original skip transfer. The module operates at the two finest resolutions and integrates directly into the backbone. On a rebuilt patient-unique cohort, RFS improves test PSNR over U-Net-64 by 0.10 dB. A three-seed comparison with encoder-only recalibration supports the contribution of decoder context. RFS also offers a lower-latency alternative to CBAM, with 2.25 times faster inference in matched profiling. Decoder-conditioned reuse thus improves bone-selective synthesis through a compact architectural change.
Comments5 pages, 3 figures, and 3 tables. Manuscript prepared for ICASSP 2027
