医学基础模型特征作为感知损失用于脑部MRI对比度剂量模拟
Medical Foundation Model Features as Perceptual Loss for Brain MRI Contrast Dose Simulation
浏览论文内容
中文总结 AI 辅助
该研究提出用医学基础模型RadImageNet的特征替代自然图像骨干网络，作为感知损失用于脑部MRI对比度剂量模拟，相关指标略有提升，视觉效果更优。
中文摘要 AI 辅助
感知损失广泛应用于医学图像合成，因为它鼓励在体素级强度相似性之外的高级结构一致性。但在实践中，即使目标领域是磁共振成像（MRI），大多数感知损失仍使用自然图像骨干网络（如VGG16或ResNet50）计算，这种不匹配可能削弱对解剖结构、对比度增强和采集变异性的监督。本研究测试医学基础模型特征是否能成为更适合脑部MRI对比度剂量模拟的感知损失，分为两个阶段：第一阶段，以ImageNet预训练的VGG16和ResNet50为冻结特征提取器，在四个公开医学影像基准（甲状腺超声、乳腺超声、膝关节前交叉韧带MRI、膝关节半月板MRI）上比较RadImageNet、SegVol和BrainIAC，结果RadImageNet在第一阶段表示套件中实现最低平均排名，被选为φ*；第二阶段，仅用φ*替换现有迭代脑部MRI剂量模拟框架中的VGG16特征提取器，生成器、重建损失、对抗损失、辅助损失、优化方案和损失权重保持不变，标准指标变化不大：PSNR从41.63提升至41.74，SSIM从0.9739提升至0.9754，RMSE从0.1384降至0.1369，残留摄取CNR从0.0085降至0.0082；视觉结果显示RadImageNet的主要效果：减少标记结构的残留增强、遵循更忠实的剂量减少轨迹、接近采集的10%低剂量目标。这些结果支持领域对齐的放射学特征作为MRI剂量模拟的实用感知特征空间，临床等效性和更大队列验证留待未来工作。
英文摘要
Perceptual losses are widely used in medical image synthesis because they encourage agreement in high-level structure beyond voxel-wise intensity similarity. In practice, most perceptual losses are still computed with natural-image backbones such as VGG16 or ResNet50, even when the target domain is magnetic resonance imaging (MRI). This mismatch may weaken supervision for anatomy, contrast enhancement, and acquisition variability. We test whether medical foundation model features provide a more suitable perceptual loss for brain MRI contrast dose simulation. The study has two stages. First, we compare RadImageNet, SegVol, and BrainIAC with ImageNet-pretrained VGG16 and ResNet50 as frozen feature extractors on four public medical imaging benchmarks: thyroid ultrasound, breast ultrasound, anterior cruciate ligament knee MRI, and meniscus knee MRI. RadImageNet achieves the lowest mean rank across the Stage I representation suite and is selected as $ϕ^\star$. Second, we replace only the VGG16 feature extractor in an existing iterative brain MRI dose simulation framework with $ϕ^\star$. The generator, reconstruction loss, adversarial loss, auxiliary losses, optimization schedule, and loss weights are kept unchanged. Standard metrics change modestly, with PSNR increasing from 41.63 to 41.74, SSIM from 0.9739 to 0.9754, RMSE decreasing from 0.1384 to 0.1369, and residual-uptake CNR from 0.0085 to 0.0082. The visual results show the main effect: RadImageNet reduces residual enhancement in marked structures, follows a more faithful dose-reduction trajectory, and remains close to the acquired 10% low-dose target. These results support domain-aligned radiology features as a practical perceptual feature space for MRI dose simulation, while leaving clinical equivalence and larger-cohort validation as future work.
发表机构
- Subtle Medical
机构由 AI 辅助整理，请以论文原文为准。
