.png){kind=icon}
返回
Efficient end-to-end learning for cell segmentation with machine generated weak annotations
.png){kind=icon}
OA
AI
DOI：10.1038/s42003-023-04608-5.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automated cell segmentation from optical microscopy images is usually the first step in the pipeline of single-cell analysis. Recently, deep-learning based algorithms have shown superior performances for the cell segmentation tasks. However, a disadvantage of deep-learning is the requirement for a large amount of fully annotated training data, which is costly to generate. Weakly-supervised and self-supervised learning is an active research area, but often the model accuracy is inversely correlated with the amount of annotation information provided. Here we focus on a specific subtype of weak annotations, which can be generated programmably from experimental data, thus allowing for more annotation information content without sacrificing the annotation speed. We designed a new model architecture for end-to-end training using such incomplete annotations. We have benchmarked our method on a variety of publicly available datasets, covering both fluorescence and bright-field imaging modality. We additionally tested our method on a microscopy dataset generated by us, using machine-generated annotations. The results demonstrated that our models trained under weak supervision can achieve segmentation accuracy competitive to, and in some cases, surpassing, state-of-the-art models trained under full supervision. Therefore, our method can be a practical alternative to the established full-supervision methods. A cell segmentation model is presented that is trained on weak annotations which can be generated programmably from experimental data, allowing for more annotation information content without sacrificing annotation speed.
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.1
论文数:
1.0W
被引数:
3.2W
机构
暂无机构信息
引用论文
Sparse autoencoder for unsupervised nucleus detection and representation in histopathology images用于组织病理学图像中无监督核检测和表示的稀疏自动编码器.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
ilastik: interactive machine learning for (bio) image analysisilastik: 用于 (生物) 图像分析的交互式机器学习NATURE METHODSOAAI
NATURE METHODSIF32.1
OAAI分享收藏
查看更多内容