arXiv cs.AI· Xihe Qiu, Yang Dai, Xiaoyu Tan, Sijia Li, Fenghao Sun, Lu Gan, Liang Liu·· 9 天前AI 评分24
SRUG：一种用于医学图像翻译的融合驱动生成器网络
SRUG: A Fusion-Driven Generator Network for Medical Image Translation
AI 导读
SRUG 是一种监督式独立融合驱动生成器，通过确定性源到目标映射实现配对 MRI 合成，无需生成器-判别器对抗、变分隐变量采样或迭代扩散去噪。该模型采用适配图像重建的残差编码器与嵌套多尺度解码器（NMD），结合 L1 损失和多尺度结构损失（MSS loss）联合监督。
正文 · 原文
Abstract:MRI sequence synthesis aims to recover missing image contrast while preserving patient-specific anatomy. The choice of generation mechanism affects both optimization and the way source information reaches the synthesized image. In this study, we propose SRUG, a supervised standalone fusion-driven generator that learns a deterministic source-to-target mapping for paired MRI synthesis. Its direct reconstruction formulation removes generator-discriminator competition and requires neither variational latent sampling nor iterative diffusion denoising. To support structural fidelity within this formulation, SRUG uses a residual encoder adapted for image reconstruction, with a full-resolution convolutional stem, pooling-separated feature stages, and channel recalibration embedded in the residual branches. A nested multi-scale decoder (NMD) repeatedly fuses the resulting spatial features and predicts the target sequence through a single output head. L1 loss and Multi-Scale Structural Loss (MSS loss) jointly supervise the prediction, connecting the direct generation objective to anatomical detail recovery. Experiments on BraTS 2023 show competitive reconstruction fidelity and structural consistency across three MRI translation tasks. Architecture ablations assess the effects of channel recalibration, NMD, and structural supervision within the same generator framework. Additional evaluation on IXI supports applicability to another dataset and modality pair, while zero-shot testing on BraTS 2019 provides preliminary evidence of cross-dataset transferability. These results support direct supervised generation as a practical approach to paired MRI sequence synthesis, with the adapted encoding and reconstruction pathway providing the basis for structural preservation. The SRUG implementation is publicly available at this https URL.
| Comments: | 18 pages, 15 figures, 4 tables. Code: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2601.04785 [cs.CV] |
| (or arXiv:2601.04785v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2601.04785 arXiv-issued DOI via DataCite |
Submission history
From: Yang Dai [view email]
[v1]
Thu, 8 Jan 2026 10:10:03 UTC (11,406 KB)
[v2]
Thu, 8 Oct 2026 08:44:54 UTC (20,659 KB)
来源：arXiv cs.AI · arxiv.org