用知识蒸馏增强扩散模型，从少量配对数据生成高质量CT影像。
Improving Cone-Beam CT Image Quality with Knowledge Distillation-Enhanced Diffusion Model in Imbalanced Data Settings
- 结合知识蒸馏与自训练，提升稀疏配对数据下的扩散模型性能。
- 在2800组配对数据上生成5600组伪标签CT，显著优于Pix2pix和CycleGAN。
- 适合放射治疗中需动态调整的临床场景，尤其适用于数据不平衡问题。
在放射治疗中，依赖治疗前的计算机断层扫描（CT）图像面临解剖结构变化带来的挑战，需进行自适应计划。每日锥形束CT（CBCT）成像对于治疗调整至关重要，但其组织密度精度不足。为此，本文提出一种创新方法，利用扩散模型生成CT图像，实现对数据合成的精确控制。通过结合知识蒸馏的自训练策略，最大化治疗过程中的CBCT数据，并辅以少量配对的扇形束CT。该方法嵌入先进的扩散模型中，在包含2800组配对的CBCT与CT扫描、并补充4200组未配对CBCT扫描的精心构建数据集上进行训练，采用布朗桥扩散模型（BBDM）作为教师模型。生成伪标签的CT图像后，形成包含5600组对应图像的数据集。通过均方误差（MSE）、结构相似性（SSIM）、峰值信噪比（PSNR）和感知图像质量指标（LPIPS）的全面评估，结果显示该方法在生成质量上超越传统方法如Pix2pix和CycleGAN，展现出从CBCT扫描生成高质量CT图像的巨大潜力。
原文摘要 · Abstract (English)
In radiation therapy (RT), the reliance on pre-treatment computed tomography (CT) images encounter challenges due to anatomical changes, necessitating adaptive planning. Daily cone-beam CT (CBCT) imaging, pivotal for therapy adjustment, falls short in tissue density accuracy. To address this, our innovative approach integrates diffusion models for CT image generation, offering precise control over data synthesis. Leveraging a self-training method with knowledge distillation, we maximize CBCT data during therapy, complemented by sparse paired fan-beam CTs. This strategy, incorporated into state-of-the-art diffusion-based models, surpasses conventional methods like Pix2pix and CycleGAN. A meticulously curated dataset of 2800 paired CBCT and CT scans, supplemented by 4200 CBCT scans, undergoes preprocessing and teacher model training, including the Brownian Bridge Diffusion Model (BBDM). Pseudo-label CT images are generated, resulting in a dataset combining 5600 CT images with corresponding CBCT images. Thorough evaluation using MSE, SSIM, PSNR and LPIPS demonstrates superior performance against Pix2pix and CycleGAN. Our approach shows promise in generating high-quality CT images from CBCT scans in RT.
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。