Journal
BMC BIOINFORMATICS
Volume 22, Issue 1, Pages -Publisher
BMC
DOI: 10.1186/s12859-021-04245-x
Keywords
Super-resolution; STORM; Convolutional neural networks; Mask R-CNN; UNet; StarDist; ANCIS; Nuclei segmentation
Categories
Funding
- National Institute of Health [R33CA225494, R01CA232593, R01CA254112, T15LM007059]
Ask authors/readers for more resources
Segmentation of nuclei in super-resolution images poses a challenging task. This study applies Mask R-CNN and UNet architectures to segment nuclei in super-resolution images. Results show that neural networks trained on conventional fluorescence microscopy images do not accurately segment super-resolution images, but training the network on super-resolution data achieves nuclei segmentation accuracy exceeding 0.8, with Mask R-CNN architecture performing the best.
Background: Automated segmentation of nuclei in microscopic images has been conducted to enhance throughput in pathological diagnostics and biological research. Segmentation accuracy and speed has been significantly enhanced with the advent of convolutional neural networks. A barrier in the broad application of neural networks to nuclei segmentation is the necessity to train the network using a set of application specific images and image labels. Previous works have attempted to create broadly trained networks for universal nuclei segmentation; however, such networks do not work on all imaging modalities, and best results are still commonly found when the network is retrained on user specific data. Stochastic optical reconstruction microscopy (STORM) based super-resolution fluorescence microscopy has opened a new avenue to image nuclear architecture at nanoscale resolutions. Due to the large size and discontinuous features typical of super-resolution images, automatic nuclei segmentation can be difficult. In this study, we apply commonly used networks (Mask R-CNN and UNet architectures) towards the task of segmenting super-resolution images of nuclei. First, we assess whether networks broadly trained on conventional fluorescence microscopy datasets can accurately segment super-resolution images. Then, we compare the resultant segmentations with results obtained using networks trained directly on our super-resolution data. We next attempt to optimize and compare segmentation accuracy using three different neural network architectures. Results: Results indicate that super-resolution images are not broadly compatible with neural networks trained on conventional bright-field or fluorescence microscopy images. When the networks were trained on super-resolution data, however, we attained nuclei segmentation accuracies (Fl-Score) in excess of 0.8, comparable to past results found when conducting nuclei segmentation on conventional fluorescence microscopy images. Overall, we achieved the best results utilizing the Mask R-CNN architecture. Conclusions: We found that convolutional neural networks are powerful tools capable of accurately and quickly segmenting localization-based super-resolution microscopy images of nuclei. While broadly trained and widely applicable segmentation algorithms are desirable for quick use with minimal input, optimal results are still found when the network is both trained and tested on visually similar images. We provide a set of Colab notebooks to disseminate the software into the broad scientific community (https://github.com/YangLiuLab/Super-Resolution-Nuclei-Segmentation).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available