# Cell image classification: a comparative overview

## TL;DR

This paper reviews and compares three cell image classification methods—feature extraction, neural networks, and transport-based morphometry—across multiple datasets, highlighting their strengths and applications in biology and medicine.

## Contribution

It provides a comprehensive comparison of three distinct approaches for cell image classification and evaluates their performance on various datasets.

## Key findings

- Neural networks perform best on complex datasets.
- Transport-based morphometry offers robustness to image variations.
- Feature extraction methods are computationally efficient.

## Abstract

Cell image classification methods are currently being used in numerous applications in cell biology and medicine. Applications include understanding the effects of genes and drugs in screening experiments, understanding the role and subcellular localization of different proteins, as well as diagnosis and prognosis of cancer from images acquired using cytological and histological techniques. We review three different approaches for cell image classification: numerical feature extraction, end to end classification with neural networks, and transport-based morphometry. In addition, we provide comparisons on four different cell imaging datasets to highlight the relative strength of each method.