Abstract
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.
Abstract (translated)
在医学影像领域，神经网络模型的采用受到严格隐私法规、数据稀缺性、高昂获取成本以及人口统计学偏差的限制。深度生成模型通过生成合成数据来解决这些问题，这些数据可以绕过隐私问题，并为代表性不足的人群提供样本，从而促进公平性。然而，与自然图像不同，医学影像需要进行验证以确保其保真度（如Fréchet Inception Score）、形态学和临床准确性。特别是对于彩色眼底视网膜成像而言，精确复制包括血管拓扑结构、连续性和厚度在内的视网膜血管网络尤为重要。 在这项研究中，我们调查了一种基于大规模基础模型训练的大规模领域数据深层激活层的距离损失函数是否比感知损失和边缘检测损失函数具有优势。我们的验证管道涵盖了无域特异性和有特定领域的任务，结果表明专门的深度特征并不能改进自编码器图像生成的效果。相反，我们的研究强调了传统边缘检测滤波器在提高合成样本中血管结构清晰度方面的有效性。
URL
https://arxiv.org/abs/2506.11753
