POWDR: 基于小波扩散的病理保持3D MRI外推
POWDR: Pathology-preserving Outpainting with Wavelet Diffusion for 3D MRI
AI总结：
POWDR通过小波扩散模型生成病理保持的3D MRI外推数据，解决医学影像数据稀缺和类别不平衡问题，提升肿瘤分割性能。
摘要：
医学影像数据集常常面临类别不平衡和病理丰富案例有限的问题，这限制了机器学习模型在分割、分类和视觉-语言任务中的性能。为了解决这一挑战，我们提出了POWDR，一种基于条件小波扩散模型的3D MRI病理保持外推框架。与传统增强或无条件合成不同，POWDR在生成解剖上合理的周围组织的同时保留真实的病理区域，从而在不制造病变的情况下实现多样性。我们的方法利用小波域条件来增强高频细节并缓解潜在扩散模型中常见的模糊问题。我们引入了一种随机连接掩码训练策略以克服条件诱导的崩溃并提高病变外的多样性。POWDR在脑MRI上使用BraTS数据集进行评估，并扩展到膝关节MRI以证明组织无关的应用性。定量指标（FID、SSIM、LPIPS）证实了图像的真实性，而多样性分析显示随机掩码训练显著提高了性能（余弦相似度从0.9947降至0.9580；KL散度从0.00026增加到0.01494）。临床相关评估显示使用nnU-Net时肿瘤分割性能有所提升，当添加50个合成案例时Dice分数从0.6992提高到0.7137。组织体积分析显示CSF和GM与真实图像相比没有显著差异。这些发现突显了POWDR作为解决医学影像数据稀缺和类别不平衡的实用解决方案。该方法可扩展到多种解剖结构，并提供了一种可控的框架，用于生成多样化、病理保持的合成数据，以支持稳健的模型开发。
英文摘要：
Medical imaging datasets often suffer from class imbalance and limited availability of pathology-rich cases, which constrains the performance of machine learning models for segmentation, classification, and vision-language tasks. To address this challenge, we propose POWDR, a pathology-preserving outpainting framework for 3D MRI based on a conditioned wavelet diffusion model. Unlike conventional augmentation or unconditional synthesis, POWDR retains real pathological regions while generating anatomically plausible surrounding tissue, enabling diversity without fabricating lesions. Our approach leverages wavelet-domain conditioning to enhance high-frequency detail and mitigate blurring common in latent diffusion models. We introduce a random connected mask training strategy to overcome conditioning-induced collapse and improve diversity outside the lesion. POWDR is evaluated on brain MRI using BraTS datasets and extended to knee MRI to demonstrate tissue-agnostic applicability. Quantitative metrics (FID, SSIM, LPIPS) confirm image realism, while diversity analysis shows significant improvement with random-mask training (cosine similarity reduced from 0.9947 to 0.9580; KL divergence increased from 0.00026 to 0.01494). Clinically relevant assessments reveal gains in tumor segmentation performance using nnU-Net, with Dice scores improving from 0.6992 to 0.7137 when adding 50 synthetic cases. Tissue volume analysis indicates no significant differences for CSF and GM compared to real images. These findings highlight POWDR as a practical solution for addressing data scarcity and class imbalance in medical imaging. The method is extensible to multiple anatomies and offers a controllable framework for generating diverse, pathology-preserving synthetic data to support robust model development.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
