FCaS: Fine-grained Cardiac Image Synthesis based on 3D Template Conditional Diffusion Model

2025-03-12

AI Summary

Addressing challenges in cardiac medical imaging—including difficulty reconstructing fine-grained anatomical structures (e.g., coronary vessels), stringent topological consistency requirements, high 3D morphological heterogeneity, and severe scarcity of annotated data—this paper proposes a Template-guided Bidirectional Conditional Diffusion Model (TCDM). TCDM introduces, for the first time, a 3D template-driven generative mechanism; integrates a deformable mask generation module (MGM) to alleviate reliance on high-quality reference masks; and incorporates a confidence-aware adaptive learning (CAL) strategy that leverages skip-sampling variance (SSV) estimation to optimize downstream segmentation pretraining. Experiments demonstrate that TCDM achieves state-of-the-art performance in both topological fidelity and visual quality, significantly improving segmentation accuracy for cardiac substructures. The method establishes a novel paradigm for few-shot cardiac image synthesis.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Solving medical imaging data scarcity through semantic image generation has attracted significant attention in recent years. However, existing methods primarily focus on generating whole-organ or large-tissue structures, showing limited effectiveness for organs with fine-grained structure. Due to stringent topological consistency, fragile coronary features, and complex 3D morphological heterogeneity in cardiac imaging, accurately reconstructing fine-grained anatomical details of the heart remains a great challenge. To address this problem, in this paper, we propose the Fine-grained Cardiac image Synthesis(FCaS) framework, established on 3D template conditional diffusion model. FCaS achieves precise cardiac structure generation using Template-guided Conditional Diffusion Model (TCDM) through bidirectional mechanisms, which provides the fine-grained topological structure information of target image through the guidance of template. Meanwhile, we design a deformable Mask Generation Module (MGM) to mitigate the scarcity of high-quality and diverse reference mask in the generation process. Furthermore, to alleviate the confusion caused by imprecise synthetic images, we propose a Confidence-aware Adaptive Learning (CAL) strategy to facilitate the pre-training of downstream segmentation tasks. Specifically, we introduce the Skip-Sampling Variance (SSV) estimation to obtain confidence maps, which are subsequently employed to rectify the pre-training on downstream tasks. Experimental results demonstrate that images generated from FCaS achieves state-of-the-art performance in topological consistency and visual quality, which significantly facilitates the downstream tasks as well. Code will be released in the future.

Problem

• Generates fine-grained cardiac images using 3D template diffusion.
• Addresses scarcity of high-quality cardiac imaging data.
• Improves downstream medical segmentation tasks with adaptive learning.

Innovation

• 3D template conditional diffusion model
• Deformable Mask Generation Module
• Confidence-aware Adaptive Learning strategy