Free annotated data for deep learning in microscopy? A hitchhiker's guide

TL;DR

This paper reviews recent methods that enable training deep learning models in microscopy with less annotated data by leveraging knowledge from other fields, addressing practical challenges in data annotation.

Contribution

It provides an overview of emerging techniques that relax data annotation requirements in microscopy deep learning, facilitating broader adoption.

Findings

Methods successfully reduce annotation effort

Knowledge transfer from other fields improves microscopy models

Potential for more practical deep learning applications in microscopy

Abstract

In microscopy, the time burden and cost of acquiring and annotating large datasets that many deep learning models take as a prerequisite, often appears to make these methods impractical. Can this requirement for annotated data be relaxed? Is it possible to borrow the knowledge gathered from datasets in other application fields and leverage it for microscopy? Here, we aim to provide an overview of methods that have recently emerged to successfully train learning-based methods in bio-microscopy.