用生成模型合成生物显微图像中的细长纤维，解决标注数据少的问题。
A Conditional Generative Framework for Synthetic Data Augmentation in Segmenting Thin and Elongated Structures in Biological Images
- 基于Pix2Pix的条件生成框架，从二值掩码生成真实感纤维图像。
- 引入纤维感知结构损失，提升生成图像与真实图像的结构相似性。
- 适合需要高质量细长结构标注数据的研究者使用。
细长丝状结构（如微管和肌动蛋白纤维）在生物系统中起关键作用，其分割是定量分析的基础。深度学习虽显著提升了分割性能，但高质量像素级标注数据稀缺，因纤维密集分布和几何特性导致人工标注极为耗时。为此，本文提出基于Pix2Pix架构的条件生成框架，从二值掩码生成显微图像中的真实纤维。同时设计纤维感知结构损失，增强生成图像的结构相似性。实验表明该方法有效，优于未使用合成数据训练的现有模型。
原文摘要 · Abstract (English)
Thin and elongated filamentous structures, such as microtubules and actin filaments, often play important roles in biological systems. Segmenting these filaments in biological images is a fundamental step for quantitative analysis. Recent advances in deep learning have significantly improved the performance of filament segmentation. However, there is a big challenge in acquiring high quality pixel-level annotated dataset for filamentous structures, as the dense distribution and geometric properties of filaments making manual annotation extremely laborious and time-consuming. To address the data shortage problem, we propose a conditional generative framework based on the Pix2Pix architecture to generate realistic filaments in microscopy images from binary masks. We also propose a filament-aware structural loss to improve the structure similarity when generating synthetic images. Our experiments have demonstrated the effectiveness of our approach and outperformed existing model trained without synthetic data.
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。