用领域模型特征生成眼底图像，发现传统边缘检测更有效
Exploring the Effectiveness of Deep Features from Domain-Specific Foundation Models in Retinal Image Synthesis
- 用领域专用大模型的深层特征设计距离损失函数
- 传统边缘检测使合成血管结构更清晰锐利
- 领域特定特征对生成效果无提升，适合医学图像生成研究者
医疗影像中神经网络应用受限于严格的隐私规定、数据稀缺、高采集成本及人口偏差。深度生成模型可通过生成合成数据绕过隐私问题，并通过为少数群体生成样本改善公平性。然而，与自然图像不同，医疗影像需同时验证保真度（如Fréchet Inception Score）和形态学、临床准确性。以彩色眼底成像为例，需精确复现视网膜血管网络，包括拓扑结构、连续性和厚度。本研究探讨基于大规模领域数据训练的预训练模型深层激活层的距离损失函数，在眼底图像生成中是否优于感知损失和基于边缘检测的损失函数。通过涵盖领域无关与领域特定任务的综合验证流程发现，领域特定深层特征并未提升自编码器图像生成效果。相反，传统边缘检测滤波器在提升合成样本血管结构锐度方面表现更优。
原文摘要 · Abstract (English)
The adoption of neural network models in medical imaging has been constrained by strict privacy regulations, limited data availability, high acquisition costs, and demographic biases. Deep generative models offer a promising solution by generating synthetic data that bypasses privacy concerns and addresses fairness by producing samples for under-represented groups. However, unlike natural images, medical imaging requires validation not only for fidelity (e.g., Fréchet Inception Score) but also for morphological and clinical accuracy. This is particularly true for colour fundus retinal imaging, which requires precise replication of the retinal vascular network, including vessel topology, continuity, and thickness. In this study, we in-vestigated whether a distance-based loss function based on deep activation layers of a large foundational model trained on large corpus of domain data, colour fundus imaging, offers advantages over a perceptual loss and edge-detection based loss functions. Our extensive validation pipeline, based on both domain-free and domain specific tasks, suggests that domain-specific deep features do not improve autoen-coder image generation. Conversely, our findings highlight the effectiveness of con-ventional edge detection filters in improving the sharpness of vascular structures in synthetic samples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。