Nuclei Segmentation of Fluorescence Microscopy Images Using Three Dimensional Convolutional Neural Networks

David Joon Ho, Chichen Fu, Paul Salama, Kenneth W. Dunn, Edward J. Delp; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 82-90

Abstract

Fluorescence microscopy enables one to visualize subcellular structures of living tissue or cells in three dimensions. This is especially true for two-photon microscopy using near-infrared light which can image deeper into tissue. To characterize and analyze biological structures, nuclei segmentation is a prerequisite step. Due to the complexity and size of the image data sets, manual segmentation is prohibitive. This paper describes a fully 3D nuclei segmentation method using three dimensional convolutional neural networks. To train the network, synthetic volumes with corresponding labeled volumes are automatically generated. Our results from multiple data sets demonstrate that our method can successfully segment nuclei in 3D.

Related Material

[pdf]
[bibtex]
@InProceedings{Ho_2017_CVPR_Workshops,
author = {Joon Ho, David and Fu, Chichen and Salama, Paul and Dunn, Kenneth W. and Delp, Edward J.},
title = {Nuclei Segmentation of Fluorescence Microscopy Images Using Three Dimensional Convolutional Neural Networks},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}