Automatic Preprocessing and Ensemble Learning for Low Quality Cell Image Segmentation

TL;DR

This paper introduces an automatic preprocessing and ensemble learning approach that enhances the segmentation of low-quality cell images by translating them into more recognizable forms and combining multiple segmentation outputs.

Contribution

It presents a novel deep learning framework that automatically preprocesses low-quality images and improves segmentation accuracy without needing high-quality reference images.

Findings

Improved segmentation accuracy on low-quality cell images.

Effective translation of low-quality images into recognizable forms.

Enhanced results through weighted ensemble of multiple segmentation outputs.

Abstract

We propose an automatic preprocessing and ensemble learning for segmentation of cell images with low quality. It is difficult to capture cells with strong light. Therefore, the microscopic images of cells tend to have low image quality but these images are not good for semantic segmentation. Here we propose a method to translate an input image to the images that are easy to recognize by deep learning. The proposed method consists of two deep neural networks. The first network is the usual training for semantic segmentation, and penultimate feature maps of the first network are used as filters to translate an input image to the images that emphasize each class. This is the automatic preprocessing and translated cell images are easily classified. The input cell image with low quality is translated by the feature maps in the first network, and the translated images are fed into the second network for semantic segmentation. Since the outputs of the second network are multiple segmentation results, we conduct the weighted ensemble of those segmentation images. Two networks are trained by end-to-end manner, and we do not need to prepare images with high quality for the translation. We confirmed that our proposed method can translate cell images with low quality to the images that are easy to segment, and segmentation accuracy has improved using the weighted ensemble learning.