ADP-DiT：用于阿尔茨海默病进展的文本引导扩散变换器
ADP-DiT: Text-Guided Diffusion Transformer for Brain Image Generation in Alzheimer's Disease Progression
AI总结：
ADP-DiT通过整合临床信息和时间间隔，提升阿尔茨海默病纵向MRI生成的精度与可解释性，实现更精细的时间控制和解剖结构重建。
摘要：
阿尔茨海默病（AD）在个体间进展异质，推动了针对随访磁共振成像（MRI）的个性化合成以支持进展评估。尽管扩散变换器（DiT）作为一种新兴的基于变换器的扩散模型，提供了图像合成的可扩展框架，但纵向AD MRI生成中对随访时间及受试者元数据的临床可解释性控制仍待深入探索。本文提出ADP-DiT，一种具有时间间隔意识且基于临床文本条件的扩散变换器，用于纵向AD MRI合成。ADP-DiT将随访间隔与多领域人口统计、诊断（正常/轻度认知障碍/AD）及神经心理学信息编码为自然语言提示，实现超越粗略诊断阶段的时间特定控制。为有效注入这种条件，我们使用双文本编码器——OpenCLIP用于视觉-语言对齐和T5用于更丰富的临床语言理解。它们的嵌入通过交叉注意机制融合到DiT中，以实现细粒度引导和自适应层归一化进行全局调节。我们进一步通过旋转位置嵌入提升解剖结构保真度，并在预训练的SDXL-VAE潜在空间中进行扩散以实现高效高分辨率重建。在712名受试者（259,038张图像切片）的3,321张纵向3T T1加权扫描数据上，ADP-DiT实现了SSIM 0.8739和PSNR 29.32 dB，比DiT基线提升了+0.1087 SSIM和+6.08 dB PSNR，同时捕捉到与进展相关的改变，如脑室扩大和海马体缩小。这些结果表明，整合全面的、受试者特定的临床条件与架构可以提高纵向AD MRI合成。
英文摘要：
Alzheimer's disease (AD) progresses heterogeneously across individuals, motivating subject-specific synthesis of follow-up magnetic resonance imaging (MRI) to support progression assessment. While Diffusion Transformers (DiT), an emerging transformer-based diffusion model, offer a scalable backbone for image synthesis, longitudinal AD MRI generation with clinically interpretable control over follow-up time and participant metadata remains underexplored. We present ADP-DiT, an interval-aware, clinically text-conditioned diffusion transformer for longitudinal AD MRI synthesis. ADP-DiT encodes follow-up interval together with multi-domain demographic, diagnostic (CN/MCI/AD), and neuropsychological information as a natural-language prompt, enabling time-specific control beyond coarse diagnostic stages. To inject this conditioning effectively, we use dual text encoders-OpenCLIP for vision-language alignment and T5 for richer clinical-language understanding. Their embeddings are fused into DiT through cross-attention for fine-grained guidance and adaptive layer normalization for global modulation. We further enhance anatomical fidelity by applying rotary positional embeddings to image tokens and performing diffusion in a pre-trained SDXL-VAE latent space to enable efficient high-resolution reconstruction. On 3,321 longitudinal 3T T1-weighted scans from 712 participants (259,038 image slices), ADP-DiT achieves SSIM 0.8739 and PSNR 29.32 dB, improving over a DiT baseline by +0.1087 SSIM and +6.08 dB PSNR while capturing progression-related changes such as ventricular enlargement and shrinking hippocampus. These results suggest that integrating comprehensive, subject-specific clinical conditions with architectures can improve longitudinal AD MRI synthesis.
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。
