arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.05511cs.CV
收藏

基于时间箭头预测的活细胞显微镜自监督密集表示学习

Self-supervised dense representation learning for live-cell microscopy with time arrow prediction

École polytechnique fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Benjamin Gallusser, Max Stieber, Martin Weigert

AI总结:

提出基于时间箭头预测的自监督预训练方法,从无标注活细胞视频中学习密集图像表示,在细胞分割与检测任务上优于监督方法,尤其在标注有限时表现突出。

摘要:

针对显微镜图像的最先进目标检测和分割方法依赖于监督机器学习,这需要耗费大量人工对训练数据进行标注。在此,我们提出了一种基于时间箭头预测预训练的自监督方法,该方法直接从原始、无标注的活细胞显微镜视频中学习密集图像表示。我们的方法建立在预测时间翻转图像区域正确顺序的任务之上,通过单图像特征提取器提取特征,随后由作用于融合特征上的时间箭头预测头进行处理。我们证明,所得的密集表示能够在像素级别捕捉本质上时间不对称的生物过程,例如细胞分裂。我们进一步在多个活细胞显微镜数据集上展示了这些表示的实用性,包括用于分裂细胞的检测和分割,以及细胞状态分类。我们的方法优于监督方法,特别是在仅有有限真实标注可用时(这也是实践中常见的情况)。我们在 https://github.com/weigertlab/tarrow 提供了代码。

英文摘要:

State-of-the-art object detection and segmentation methods for microscopy images rely on supervised machine learning, which requires laborious manual annotation of training data. Here we present a self-supervised method based on time arrow prediction pre-training that learns dense image representations from raw, unlabeled live-cell microscopy videos. Our method builds upon the task of predicting the correct order of time-flipped image regions via a single-image feature extractor followed by a time arrow prediction head that operates on the fused features. We show that the resulting dense representations capture inherently time-asymmetric biological processes such as cell divisions on a pixel-level. We furthermore demonstrate the utility of these representations on several live-cell microscopy datasets for detection and segmentation of dividing cells, as well as for cell state classification. Our method outperforms supervised methods, particularly when only limited ground truth annotations are available as is commonly the case in practice. We provide code at https://github.com/weigertlab/tarrow.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑