Rxivist logo

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images

By Juan C. Caicedo, Jonathan Roth, Allen Goodman, Tim Becker, Kyle W Karhohs, Matthieu Broisin, Molnar Csaba, Claire McQuin, Shantanu Singh, Fabian J. Theis, Anne E. Carpenter

Posted 31 May 2018
bioRxiv DOI: 10.1101/335216 (published DOI: 10.1002/cyto.a.23863)

Identifying nuclei is often a critical first step in analyzing microscopy images of cells, and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare deep learning strategies and classical approaches. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments and run the proposed evaluation methodology. Our evaluation framework shows that deep learning improves accuracy and can reduce the number of biologically relevant errors by half.

Download data

  • Downloaded 5,847 times
  • Download rankings, all-time:
    • Site-wide: 566 out of 89,482
    • In bioinformatics: 89 out of 8,435
  • Year to date:
    • Site-wide: 1,905 out of 89,482
  • Since beginning of last month:
    • Site-wide: 6,942 out of 89,482

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)