Cell segmentation from telecentric bright-field transmitted light microscopy images using a Residual Attention U-Net: a case study on HeLa line

TL;DR

This study develops a deep learning-based residual attention U-Net model for accurate segmentation of living HeLa cells in bright-field microscopy images, outperforming simpler architectures and enabling precise cell delineation.

Contribution

It introduces a residual attention U-Net architecture tailored for cell segmentation, combining attention and residual mechanisms to improve accuracy over existing models.

Findings

Residual attention U-Net achieved the highest Mean-IoU of 0.9530.

Combining attention and residual mechanisms improved segmentation accuracy.

Watershed method applied to segmentation results provided detailed cell boundaries.

Abstract

Living cell segmentation from bright-field light microscopy images is challenging due to the image complexity and temporal changes in the living cells. Recently developed deep learning (DL)-based methods became popular in medical and microscopy image segmentation tasks due to their success and promising outcomes. The main objective of this paper is to develop a deep learning, U-Net-based method to segment the living cells of the HeLa line in bright-field transmitted light microscopy. To find the most suitable architecture for our datasets, a residual attention U-Net was proposed and compared with an attention and a simple U-Net architecture. The attention mechanism highlights the remarkable features and suppresses activations in the irrelevant image regions. The residual mechanism overcomes with vanishing gradient problem. The Mean-IoU score for our datasets reaches 0.9505, 0.9524, and 0.9530 for the simple, attention, and residual attention U-Net, respectively. The most accurate semantic segmentation results was achieved in the Mean-IoU and Dice metrics by applying the residual and attention mechanisms together. The watershed method applied to this best -- Residual Attention -- semantic segmentation result gave the segmentation with the specific information for each cell.