Developer

This pipeline is released and integrated into the BMAP by the author of the DOI：10.1364/OSAC.388082

Benchmark Data

4360 raw image tiles from 20 raw DIC (differential interference contrast) images were used to test the pipeline.
It demonstrated a 99.35% consistent recall rate of experienced manual counting, and decreased the time required from 5 minutes on average to only 5 seconds for each image.

Workflow

Reference

Yan Kong, Hui Li, Yongyong Ren, Georgi Z. Genchev, Xiaolei Wang, Hongyu Zhao, Zhiping Xie, and Hui Lu, "Automated yeast cells segmentation and counting using a parallel U-Net based two-stage framework," OSA Continuum 3, 982-992 (2020)

Data

1562 yeast cells from 10 DIC format files

Evaluation Metrics

Precision， Recall, F1-score, Miss Rate (MR), The Aggregated Jaccard Index (AJI)

Results

Reference

Yan Kong, Hui Li, Yongyong Ren, Georgi Z. Genchev, Xiaolei Wang, Hongyu Zhao, Zhiping Xie, and Hui Lu, "Automated yeast cells segmentation and counting using a parallel U-Net based two-stage framework," OSA Continuum 3, 982-992 (2020)

Versions

V1.0: The pipeline is stored in Code Repository: CRS1043594848571240448. The computational docker enrionment is stored in Software Repository: SRS1043185794040475648

Reproducibility

The pipeline utilizes code CRS1043594848571240448 and Docker image SRS1043185794040475648, both of which are stored in the BMAP repositories.

Usage

1. Select the application 'Yeast cell counter'
2. Click on the 'Analysis' button
3. Click on the 'Cell counter'
4. Fill in the request parameters

Note: the dic file name should include the subfolder name and the extension name (eg. data/yeast.dic).
5. Upload the compressed data in gz or rar format.

6. View the results