Automated Cell Foreground-Background Segmentation with Phase-Contrast Microscopy Images: An Alternative to Machine Learning Segmentation Methods with Small-Scale Data.

Guochang Ye,Mehmet Kaya

doi:10.3390/bioengineering9020081

Abstract

Cell segmentation is a critical step for image-based experimental analysis. Existing cell segmentation methods are neither entirely automated nor perform well under basic laboratory microscopy. This study proposes an efficient and automated cell segmentation method involving morphological operations to automatically achieve cell segmentation for phase-contrast microscopes. Manual/visual counting of cell segmentation serves as the control group (156 images as ground truth) to evaluate the proposed method’s performance. The proposed technology’s adaptive performance is assessed at varying conditions, including artificial blurriness, illumination, and image size. Compared to the Trainable Weka Segmentation method, the Empirical Gradient Threshold method, and the ilastik segmentation software, the proposed method achieved better segmentation accuracy (dice coefficient: 90.07, IoU: 82.16%, and 6.51% as the average relative error on measuring cell area). The proposed method also has good reliability, even under unfavored imaging conditions at which manual labeling or human intervention is inefficient. Additionally, similar degrees of segmentation accuracy were confirmed when the ground truth data and the generated data from the proposed method were applied individually to train modified U-Net models (16848 images). These results demonstrated good accuracy and high practicality of the proposed cell segmentation method with phase-contrast microscopy image data.

Highlights

In a cell culture laboratory, checking the cells under the microscope is a daily routine.Based on the image observed under a microscope, experienced researchers can only have an approximated sense about the confluence of culturing cells, the morphology of the cells, and if contamination happens [1]
The proposed method achieved 91.20% as the dice coefficient and 84.87% as Intersection over Union (IoU) compared to the target data used in the ground truth model
We developed a simple but effective cell segmentation method consisting of fundamental image processing techniques

Summary

Introduction

In a cell culture laboratory, checking the cells under the microscope is a daily routine.Based on the image observed under a microscope, experienced researchers can only have an approximated sense about the confluence of culturing cells, the morphology of the cells, and if contamination happens [1]. 30 -[1-(phenylaminocarbonyl)-3,4-tetrazolium]-bis(4-methoxy6-nitro)benzene sulfonic acid hydrate) [4], are used to measure this parameter indirectly, but these methods lean on costly instruments and professionally trained technicians. They are highly invasive or require cell staining, which disturbs the growth of the cell or even causes the termination of cell culture [5]. If these experimental conditions are not always available, the visual inspection of cell images under the microscope can be a solution, followed by manual segmentation of cell clusters. It is unavoidable that these manual measurements are prone to subjective errors when a lab technician does not have sufficient

Methods

Results

Discussion

Conclusion