用扩散模型生成脑结构影像，结合功能数据识别疾病生物标志物
GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis
- 基于3D自编码器与视觉变换器的潜空间扩散模型
- 通过功能连接数据实现个性化脑结构生成，提升疾病分析精度
- 适合精神分裂症等脑疾病的影像辅助诊断研究者使用
基于深度学习的生成模型在医学影像中展现出巨大潜力，尤其在基于MRI的模态转换与多模态融合方面。本研究提出GM-LDM框架，利用潜空间扩散模型（LDM）提升MRI生成任务的效率与精度。该框架采用在大规模ABCD MRI数据集上预训练的3D自编码器，通过KL散度损失实现统计一致性；并采用基于视觉变换器（ViT）的编码器-解码器作为去噪网络，优化生成质量。该方法可灵活引入功能性网络连接（FNC）等条件数据，支持个性化脑影像生成、生物标志物识别及功能到结构信息的转换，适用于精神分裂症等脑疾病的研究。
原文摘要 · Abstract (English)
Generative models based on deep learning have shown significant potential in medical imaging, particularly for modality transformation and multimodal fusion in MRI-based brain imaging. This study introduces GM-LDM, a novel framework that leverages the latent diffusion model (LDM) to enhance the efficiency and precision of MRI generation tasks. GM-LDM integrates a 3D autoencoder, pre-trained on the large-scale ABCD MRI dataset, achieving statistical consistency through KL divergence loss. We employ a Vision Transformer (ViT)-based encoder-decoder as the denoising network to optimize generation quality. The framework flexibly incorporates conditional data, such as functional network connectivity (FNC) data, enabling personalized brain imaging, biomarker identification, and functional-to-structural information translation for brain diseases like schizophrenia.
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。