GRUU-Net: Integrated convolutional and gated recurrent neural network for cell segmentation
Cell segmentation in microscopy images is a common and challenging task. In recent years, deep neural networks achieved remarkable improvements in the field of computer vision. The dominant paradigm in segmentation is using convolutional neural networks, less common are recurrent neural networks. In...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
31 May 2019
|
| In: |
Medical image analysis
Year: 2019, Volume: 56, Pages: 68-79 |
| ISSN: | 1361-8423 |
| DOI: | 10.1016/j.media.2019.04.011 |
| Online Access: | Verlag, Volltext: https://doi.org/10.1016/j.media.2019.04.011 Verlag: http://www.sciencedirect.com/science/article/pii/S1361841518306753 
|
| Author Notes: | T. Wollmann, M. Gunkel, I. Chung, H. Erfle, K. Rippe, K. Rohr |
| Summary: | Cell segmentation in microscopy images is a common and challenging task. In recent years, deep neural networks achieved remarkable improvements in the field of computer vision. The dominant paradigm in segmentation is using convolutional neural networks, less common are recurrent neural networks. In this work, we propose a new deep learning method for cell segmentation, which integrates convolutional neural networks and gated recurrent neural networks over multiple image scales to exploit the strength of both types of networks. To increase the robustness of the training and improve segmentation, we introduce a novel focal loss function. We also present a distributed scheme for optimized training of the integrated neural network. We applied our proposed method to challenging data of glioblastoma cell nuclei and performed a quantitative comparison with state-of-the-art methods. Insights on how our extensions affect training and inference are also provided. Moreover, we benchmarked our method using a wide spectrum of all 22 real microscopy datasets of the Cell Tracking Challenge. |
|---|---|
| Item Description: | Gesehen am 21.10.2019 |
| Physical Description: | Online Resource |
| ISSN: | 1361-8423 |
| DOI: | 10.1016/j.media.2019.04.011 |