DIC Image Segmentation of Dense Cell Populations by Combining Deep Learning and Watershed
| Authors | |
|---|---|
| Year of publication | 2019 |
| Type | Article in Proceedings |
| Conference | IEEE 16th International Symposium on Biomedical Imaging |
| MU Faculty or unit | |
| Citation | |
| web | https://ieeexplore.ieee.org/document/8759594 |
| Doi | http://dx.doi.org/10.1109/ISBI.2019.8759594 |
| Keywords | Image Segmentation; Differential Interface Contrast; Convolutional Neural Networks; Watershed |
| Attached files | |
| Description | Image segmentation of dense cell populations acquired using label-free optical microscopy techniques is a challenging problem. In this paper, we propose a novel approach based on a combination of deep learning and watershed transform to segment differential interference contrast (DIC) images with high accuracy. The main idea of our approach is to train a convolutional neural network to detect both cellular markers and cellular areas and based on these predictions to split the individual cells by using the watershed transform. The approach was developed based on the images of dense HeLa cell populations included in the Cell Tracking Challenge database. Our approach was ranked the best in segmentation, detection, as well as the overall performance as evaluated on the challenge datasets. |
| Related projects: |