发表机构
Netherlands Cancer Institute（荷兰癌症研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究从对比前乳腺MRI切片推断对比度增强的问题，提出MIRAGE方法，结合多种损失与监督形式，在多中心数据上评估，该方法在多个指标排名第一，显著提升病变定位，揭示了保真度与效用的权衡。
AI 中文摘要
从一个对比前的乳腺MRI切片推断对比度增强是不确定的，因为对比后的外观包含在基线解剖结构中未唯一编码的生理信息。仅优化配对像素保真度会抑制不确定的病变增强，而对抗性或随机生成目标可能有利于逼真的对比后外观，但不能保证患者特定的病变保真度。我们引入了MIRAGE，这是一种残差2D U-Net，它将全局重建和感知损失与仅在训练期间可用的三种病变感知监督形式相结合：对漏诊肿瘤增强的不对称惩罚、多尺度辅助肿瘤分割以及通过冻结的对比后肿瘤分割nnU-Net进行引导。我们使用八个基于图像、区域、放射组学和分割的互补指标在多中心MAMA-SYNTH数据的301个病例上评估了该方法。MIRAGE在六个指标上排名第一，并且在下游病变定位方面比调整后的pix2pix、条件扩散和潜在桥接匹配基线有显著改善。生成替代方法在LPIPS或对比度分类方面保留了优势，揭示了明显的保真度-效用权衡。留一法和留一对象消融表明，这些损失在病变定位方面部分冗余，但对外观、放射组学和边界准确性有不同影响。这些结果支持任务感知合成，同时也表明其明显的最优性取决于用于定义效用的下游模型和指标。
英文摘要
Inferring contrast enhancement from one pre-contrast breast MRI slice is underdetermined: post-contrast appearance contains physiological information that is not uniquely encoded in baseline anatomy. Optimizing only paired pixel fidelity can suppress uncertain lesion enhancement, whereas adversarial or stochastic generative objectives can favor realistic post-contrast appearance without guaranteeing patient-specific lesion fidelity. We introduce MIRAGE, a residual 2D U-Net that combines global reconstruction and perceptual losses with three forms of lesion-aware supervision available only during training: an asymmetric penalty for missed tumor enhancement, multi-scale auxiliary tumor segmentation, and guidance through a frozen post-contrast tumor segmentation nnU-Net. We evaluate the method on 301 cases from the multi-centre MAMA-SYNTH data using eight complementary image-, region-, radiomics-, and segmentation-based metrics. MIRAGE ranks first on six metrics and markedly improves downstream lesion localization over tuned pix2pix, conditional diffusion, and latent bridge-matching baselines. The generative alternatives retain advantages in LPIPS or contrast classification, revealing a clear fidelity-utility trade-off. Leave-one-in and leave-one-out ablations show that the losses are partly redundant for lesion localization but exert distinct effects on appearance, radiomics, and boundary accuracy. These results support task-aware synthesis while also showing that its apparent optimality is conditional on the downstream models and metrics used to define utility.
Comments9 pages, 2 figures, 3 tables
