3D Convolutional Networks-Based Mitotic Event Detection in Time-Lapse Phase Contrast Microscopy Image Sequences of Stem Cell Populations
Abstract
In this paper, we propose a straightforward and effective method for mitotic event detection in time-lapse phase contrast microscopy image sequences of stem cell populations. Different from most of recent methods leveraging temporal modeling to learn the latent dynamics within one mitotic event, we mainly target on the data-driven spatio-temporal visual feature learning for mitotic event representation to bypass the difficulties in both robust hand-crafted feature designing and complicated temporal dynamic learning. Specially, we design the architecture of the convolutional neural networks with 3D filters to extract the holistic feature of the volumetric region where individual mitosis event occurs. Then, the extracted features can be directly feeded into the off-the-shelf classifiers for model learning or inference. Moreover, we prepare a novel and challenging dataset for mitosis detection. The comparison experiments demonstrate the superiority of the proposed method.
Cite
Text
Nie et al. "3D Convolutional Networks-Based Mitotic Event Detection in Time-Lapse Phase Contrast Microscopy Image Sequences of Stem Cell Populations." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016. doi:10.1109/CVPRW.2016.171Markdown
[Nie et al. "3D Convolutional Networks-Based Mitotic Event Detection in Time-Lapse Phase Contrast Microscopy Image Sequences of Stem Cell Populations." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016.](https://mlanthology.org/cvprw/2016/nie2016cvprw-3d/) doi:10.1109/CVPRW.2016.171BibTeX
@inproceedings{nie2016cvprw-3d,
title = {{3D Convolutional Networks-Based Mitotic Event Detection in Time-Lapse Phase Contrast Microscopy Image Sequences of Stem Cell Populations}},
author = {Nie, Weizhi and Li, Wenhui and Liu, Anan and Hao, Tong and Su, Yuting},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2016},
pages = {1359-1366},
doi = {10.1109/CVPRW.2016.171},
url = {https://mlanthology.org/cvprw/2016/nie2016cvprw-3d/}
}