paper-with-me

Papers

Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study

2026-03-04 · Madhura Edirisooriya, Dasuni Kawya, Ishan Kumarasinghe, Isuri Devindi, Mary M. Maleckar, Roshan Ragel, Isuru Nawinne, Vajira Thambawita arxiv

Deep learning in cardiac MRI (CMR) is fundamentally constrained by both data scarcity and privacy regulations. This study systematically benchmarks three generative architectures: Denoising Diffusion Probabilistic Models (DDPM), Latent Diffusion Models (LDM), and Flow Matching (FM) for synthetic CMR generation. Utilizing a two-stage pipeline where anatomical masks condition image synthesis, we evaluate generated data across three critical axes: fidelity, utility, and privacy. Our results show that diffusion-based models, particularly DDPM, provide the most effective balance between downstream segmentation utility, image fidelity, and privacy preservation under limited-data conditions, while FM demonstrates promising privacy characteristics with slightly lower task-level performance. These findings quantify the trade-offs between cross-domain generalization and patient confidentiality, establishing a framework for safe and effective synthetic data augmentation in medical imaging.

📄 PDF Abstract BibTeX arXiv:2603.04340

Code (0)

등록된 구현이 없습니다.

Tasks

Domain GeneralizationData Augmentation

Similar Papers 제목 키워드 기반

Synthetic Cardiac MRI Image Generation using Deep Generative Models

2026-03-25 · Ishan Kumarasinghe, Dasuni Kawya, Madhura Edirisooriya, Isuri Devindi 외 arxiv

Synthetic cardiac MRI (CMRI) generation has emerged as a promising strategy to overcome the scarcity of annotated medical imaging data. Recent advances in GANs, VAEs, diffusion probabilistic models, and flow-matching tec…

Domain GeneralizationImage Generation

Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation

2026-04-08 · Qian Ma, Sarah Rajtmajer arxiv

Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy an…

Synthetic Data Generation

You Don't Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images

2023-05-25 · Xiaodan Xing, Federico Felder, Yang Nan, Giorgos Papanastasiou 외

Synthetic images generated from deep generative models have the potential to address data scarcity and data privacy issues. The selection of synthesis models is mostly based on image quality measurements, and most resear…

Data AugmentationImage GenerationPrivacy Preserving

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data

2025-06-02 · Yan Zhou, Bradley Malin, Murat Kantarcioglu

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-…

Privacy PreservingSynthetic Data Generation

High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training

2025-10-07 · Zhuoyi Huang, Nutan Sahoo, Anamika Kumari, Girish Kumar 외 arxiv

The development of machine learning for cardiac care is severely hampered by privacy restrictions on sharing real patient electrocardiogram (ECG) data. Although generative AI offers a promising solution, the real-world u…