GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Hu, Jingling, Yang, Sihan, Jia, Yuda, Bi, Vince, Calhoun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911007044009984
author Xu, Hu
Jingling, Yang
Sihan, Jia
Yuda, Bi
Vince, Calhoun
author_facet Xu, Hu
Jingling, Yang
Sihan, Jia
Yuda, Bi
Vince, Calhoun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12719
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis
Xu, Hu
Jingling, Yang
Sihan, Jia
Yuda, Bi
Vince, Calhoun
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.12719