用文本生成MRI图像，解决数据少、贵、隐私难问题
MRI Image Generation Based on Text Prompts
- 用Stable Diffusion模型，结合真实MRI数据微调生成脑部影像
- 生成图像与文本提示语义一致，FID和MS-SSIM指标提升
- 合成数据可增强小样本训练，助力医学图像分类任务
本研究探索基于文本提示的Stable Diffusion（SD）模型生成MRI图像，以应对真实MRI数据集获取难的问题，如高成本、罕见病例样本少及隐私风险。将预训练于自然图像的SD模型，利用3T fastMRI数据集与0.3T M4Raw数据集进行微调，目标是生成不同磁场强度下的脑部T1、T2和FLAIR图像。通过弗雷切特起始距离（FID）和多尺度结构相似性（MS-SSIM）等定量指标评估，微调后模型在图像质量和文本提示语义一致性上均有提升。进一步使用0.35T小规模MRI数据集进行简单分类任务验证，结果表明，由微调后的SD模型生成的合成图像可有效用于数据增强，提升MRI对比度分类任务的性能。总体表明，文本驱动的MRI图像生成具有可行性，可为医疗AI应用提供有力支持。
原文摘要 · Abstract (English)
This study explores the use of text-prompted MRI image generation with the Stable Diffusion (SD) model to address challenges in acquiring real MRI datasets, such as high costs, limited rare case samples, and privacy concerns. The SD model, pre-trained on natural images, was fine-tuned using the 3T fastMRI dataset and the 0.3T M4Raw dataset, with the goal of generating brain T1, T2, and FLAIR images across different magnetic field strengths. The performance of the fine-tuned model was evaluated using quantitative metrics,including Fréchet Inception Distance (FID) and Multi-Scale Structural Similarity (MS-SSIM), showing improvements in image quality and semantic consistency with the text prompts. To further evaluate the model's potential, a simple classification task was carried out using a small 0.35T MRI dataset, demonstrating that the synthetic images generated by the fine-tuned SD model can effectively augment training datasets and improve the performance of MRI constrast classification tasks. Overall, our findings suggest that text-prompted MRI image generation is feasible and can serve as a useful tool for medical AI applications.
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。