用扩散模型生成假显微图像，提升单细胞检测精度。
Diffusion-Based Synthetic Brightfield Microscopy Images for Enhanced Single Cell Detection
- 用U-Net扩散模型生成合成显微图像。
- 混合真实与合成数据后，检测准确率提升且成本低。
- 专家难区分真假图像，适合数据稀缺场景。
在明场显微镜下精准检测单个细胞对生物研究至关重要，但数据稀缺和标注瓶颈限制了深度学习方法的发展。本文研究无条件生成模型用于合成明场显微图像，并评估其对目标检测性能的影响。基于U-Net的扩散模型被训练并生成不同比例的合成与真实图像数据集。在YOLOv8、YOLOv9和RT-DETR上的实验表明，使用合成数据训练可实现更高的检测准确率（成本极低）。人类专家评估显示生成图像具有高度真实性，专家无法区分真假图像（准确率50%）。结果表明，基于扩散的合成数据生成是增强真实数据集的有前景方向，能减少对大量人工标注的依赖，并可能提升细胞检测模型的鲁棒性。
原文摘要 · Abstract (English)
Accurate single cell detection in brightfield microscopy is crucial for biological research, yet data scarcity and annotation bottlenecks limit the progress of deep learning methods. We investigate the use of unconditional models to generate synthetic brightfield microscopy images and evaluate their impact on object detection performance. A U-Net based diffusion model was trained and used to create datasets with varying ratios of synthetic and real images. Experiments with YOLOv8, YOLOv9 and RT-DETR reveal that training with synthetic data can achieve improved detection accuracies (at minimal costs). A human expert survey demonstrates the high realism of generated images, with experts not capable to distinguish them from real microscopy images (accuracy 50%). Our findings suggest that diffusion-based synthetic data generation is a promising avenue for augmenting real datasets in microscopy image analysis, reducing the reliance on extensive manual annotation and potentially improving the robustness of cell detection models.
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。