arrow
返回

Interactive Cell Segmentation Based on Active and Semi-Supervised Learning

delete2016-03-01
delete47
PRE
AI
H
Hang Su *
Z
Zhaozheng Yin
S
Seungil Huh
T
Takeo Kanade
Jun Zhu 封面图
Jun Zhu (Jun Zhu)
DOI:10.1109/TMI.2015.2494582delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Automatic cell segmentation can hardly be flawless due to the complexity of image data particularly when time-lapse experiments last for a long time without biomarkers. To address this issue, we propose an interactive cell segmentation method by classifying feature-homogeneous superpixels into specific classes, which is guided by human interventions. Specifically, we propose to actively select the most informative superpixels by minimizing the expected prediction error which is upper bounded by the transductive Rademacher complexity, and then query for human annotations. After propagating the user-specified labels to the remaining unlabeled superpixels via an affinity graph, the error-prone superpixels are selected automatically and request for human verification on them; once erroneous segmentation is detected and subsequently corrected, the information is propagated efficiently over a gradually-augmented graph to un-labeled superpixels such that the analogous errors are fixed meanwhile. The correction propagation step is efficiently conducted by introducing a verification propagation matrix rather than rebuilding the affinity graph and re-performing the label propagation from the beginning. We repeat this procedure until most superpixels are classified into a specific category with high confidence. Experimental results performed on three types of cell populations validate that our interactive cell segmentation algorithm quickly reaches high quality results with minimal human interventions and is significantly more efficient than alternative methods, since the most informative samples are selected for human annotation/verification early.
Keyword:
Active learning
cell segmentation
label propagation
microscopy image analysis
verification propagation
AI总结

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

IEEE Transactions on Medical Imaging 封面图
IEEE Transactions on Medical Imaging
IF:
9.8
论文数:
6.4K
被引数:
4.7W

机构

University of Missouri System 封面图
University of Missouri System
学者数:
3.0W
论文数: 2.7W
被引数: 3.2W
G
Google Incorporated
学者数:
3.5K
论文数: 1.8K
被引数: 9.7K
清华大学 封面图
清华大学
学者数:
1.1W
论文数: 4.0K
被引数: 9.9W
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
A tale of two millennials
err2017-06-20
err0
errOAAI
errAlexa Delbosc; Kelcie Ralph
err分享
err收藏
err分享
err收藏
err分享
err收藏
Re-engaging with Sustainability in the Anthropocene Era
err
IF0
err2018-08-23
err0
PREAI
errAndrew J. Hoffman; P. Devereaux Jennings
err分享
err收藏
学者 查看更多内容