Deep Generative Model-Based Generation of Synthetic Individual-Specific Brain MRI Segmentations

2025-04-15

AI Summary

Individualized brain MRI segmentation typically relies on scarce and costly structural imaging priors, limiting scalability and accessibility. Method: We propose CSegSynth, a novel conditional generative model that synthesizes subject-specific 3D white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) segmentation maps solely from readily available non-imaging data—namely demographics, clinical interviews, and cognitive assessments. CSegSynth integrates multimodal clinical embeddings, conditional variational inference, adversarial training, and diffusion-based architectural optimization. Contribution/Results: To our knowledge, this is the first framework enabling purely non-imaging–driven, subject-specific brain tissue segmentation. Quantitative evaluation shows strong volumetric agreement with ground-truth MRI segmentations: Pearson correlations of 0.80 (WM), 0.82 (GM), and 0.70 (CSF)—significantly outperforming C-VAE, C-GAN, and C-LDM baselines. Our approach establishes a scalable, cost-effective paradigm for neuroimaging modeling without requiring MRI acquisition.

Technology Category

• Computer Vision: Segmentation
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

To the best of our knowledge, all existing methods that can generate synthetic brain magnetic resonance imaging (MRI) scans for a specific individual require detailed structural or volumetric information about the individual's brain. However, such brain information is often scarce, expensive, and difficult to obtain. In this paper, we propose the first approach capable of generating synthetic brain MRI segmentations -- specifically, 3D white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) segmentations -- for individuals using their easily obtainable and often readily available demographic, interview, and cognitive test information. Our approach features a novel deep generative model, CSegSynth, which outperforms existing prominent generative models, including conditional variational autoencoder (C-VAE), conditional generative adversarial network (C-GAN), and conditional latent diffusion model (C-LDM). We demonstrate the high quality of our synthetic segmentations through extensive evaluations. Also, in assessing the effectiveness of the individual-specific generation, we achieve superior volume prediction, with Pearson correlation coefficients reaching 0.80, 0.82, and 0.70 between the ground-truth WM, GM, and CSF volumes of test individuals and those volumes predicted based on generated individual-specific segmentations, respectively.

Problem

• Generates synthetic brain MRI segmentations without detailed structural data
• Uses demographic and cognitive data for individual-specific MRI generation
• Improves volume prediction accuracy for white and gray matter

Innovation

• Generates brain MRI segmentations from demographic data
• Uses novel deep generative model CSegSynth
• Achieves high volume prediction accuracy