Leveraging Self-supervised Denoising for Image Segmentation

TL;DR

This paper introduces a method that uses self-supervised denoising networks to enhance microscopy image segmentation, especially with limited noisy data, by improving existing deep learning segmentation models like U-Net and StarDist.

Contribution

It demonstrates how self-supervised denoising can be integrated with existing segmentation models to improve accuracy with less training data in noisy microscopy images.

Findings

Denoising networks improve segmentation quality in microscopy images.

The approach is effective with limited training data.

Enhancements are consistent across different baseline models.

Abstract

Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. However, DL typically needs copious amounts of annotated training data that is for biomedical projects typically not available and excessively expensive to generate. Additionally, tasks become harder in the presence of noise, requiring even more high-quality training data. Hence, we propose to use denoising networks to improve the performance of other DL-based image segmentation methods. More specifically, we present ideas on how state-of-the-art self-supervised CARE networks can improve cell/nuclei segmentation in microscopy data. Using two state-of-the-art baseline methods, U-Net and StarDist, we show that our ideas consistently improve the quality of resulting segmentations, especially when only limited training data for noisy micrographs are available.