GET：用于医学图像分割的生成式嵌入翻译
GET: Generative Embedding Translation for Medical Image Segmentation
- Texas A&M University（德克萨斯农工大学）
- Alfa Laval（阿法拉伐）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出GET框架，基于Stable Diffusion VAE的冻结潜在空间实现医学图像分割，在多数据集上优于各类基线，参数更少且域偏移下性能提升显著。
AI中文摘要：
生成式分割通过在学习到的潜在表示上操作，为直接像素级预测提供了另一种方案，但有效的图像到掩码翻译必须保留目标结构，同时保持计算效率。我们提出Generative Embedding Translation（GET），这是一种结构化嵌入翻译框架，在Stable Diffusion VAE的冻结潜在空间内逐步将图像嵌入转换为掩码嵌入。GET采用具有107万个可训练参数的U-Net风格嵌入翻译网络，结合移动瓶颈卷积、子采样自注意力和多尺度特征丰富，用于局部建模、全局上下文和多尺度细化。在五个医学分割数据集上，GET的性能优于生成式、CNN和Transformer基线。与最强的生成式基线GMS相比，GET将平均Dice和IoU分别提高0.93%和1.26%，HD95降低0.81像素，可训练参数减少31.41%。在双向BUS-BUSI域偏移下，GET进一步将Dice和IoU分别提高3.51%和3.39%，同时HD95降低27.37像素。我们的代码可在以下网址获取：this https URL。
英文摘要：
Generative segmentation provides an alternative to direct pixel-wise prediction by operating on learned latent representations, but effective image-to-mask translation must preserve target structure while remaining computationally efficient. We propose Generative Embedding Translation (GET), a structured embedding-translation framework that progressively transforms image embeddings into mask embeddings within the frozen latent space of a Stable Diffusion VAE. GET uses a U-Net-style Embedding Translation Network with 1.07M trainable parameters, combining Mobile Bottleneck Convolutions, Subsampled Self-Attention, and Multi-scale Feature Enrichment for local modeling, global context, and multi-scale refinement. Across five medical segmentation datasets, GET outperforms generative, CNN, and Transformer baselines. Compared with the strongest generative baseline, GMS, GET improves average Dice and IoU by 0.93% and 1.26%, reduces HD95 by 0.81 pixels, and uses 31.41% fewer trainable parameters. Under bidirectional BUS-BUSI domain shift, GET further improves Dice and IoU by 3.51% and 3.39%, while reducing HD95 by 27.37 pixels. Our code is available at: https://github.com/maklachur/GET.
