Self-supervised pseudo-colorizing of masked cells

TL;DR

This paper introduces a novel self-supervised learning method for biomedical microscopy images, using pseudo-colorization of masked cells to improve cell detection, outperforming existing frameworks.

Contribution

The work presents a new self-supervision objective based on pseudo-colorizing masked cells with a physics-informed colormap, enhancing downstream cell detection performance.

Findings

Pseudo-colorization aids semantic segmentation approximation.

Masked cell part reconstruction enriches learned representations.

Pre-training outperforms contrastive, masked autoencoders, and edge-based methods.

Abstract

Self-supervised learning, which is strikingly referred to as the dark matter of intelligence, is gaining more attention in biomedical applications of deep learning. In this work, we introduce a novel self-supervision objective for the analysis of cells in biomedical microscopy images. We propose training deep learning models to pseudo-colorize masked cells. We use a physics-informed pseudo-spectral colormap that is well suited for colorizing cell topology. Our experiments reveal that approximating semantic segmentation by pseudo-colorization is beneficial for subsequent fine-tuning on cell detection. Inspired by the recent success of masked image modeling, we additionally mask out cell parts and train to reconstruct these parts to further enrich the learned representations. We compare our pre-training method with self-supervised frameworks including contrastive learning (SimCLR), masked autoencoders (MAEs), and edge-based self-supervision. We build upon our previous work and train hybrid models for cell detection, which contain both convolutional and vision transformer modules. Our pre-training method can outperform SimCLR, MAE-like masked image modeling, and edge-based self-supervision when pre-training on a diverse set of six fluorescence microscopy datasets. Code is available at: https://github.com/roydenwa/pseudo-colorize-masked-cells