Cellpose+, a morphological analysis tool for feature extraction of stained cell images

TL;DR

This paper extends the Cellpose framework to include feature extraction for stained cell images, enabling automated morphological analysis using deep learning on a new dataset of DAPI and FITC stained cells.

Contribution

The paper introduces Cellpose+ with added feature extraction capabilities and applies it to a new dataset, enhancing automated morphological analysis of stained cells.

Findings

Successful extension of Cellpose with feature extraction.

Application to DAPI and FITC stained cell images.

Improved efficiency in cell morphological analysis.

Abstract

Advanced image segmentation and processing tools present an opportunity to study cell processes and their dynamics. However, image analysis is often routine and time-consuming. Nowadays, alternative data-driven approaches using deep learning are potentially offering automatized, accurate, and fast image analysis. In this paper, we extend the applications of Cellpose, a state-of-the-art cell segmentation framework, with feature extraction capabilities to assess morphological characteristics. We also introduce a dataset of DAPI and FITC stained cells to which our new method is applied.