CellFMCount: A Fluorescence Microscopy Dataset, Benchmark, and Methods for Cell Counting

TL;DR

This paper introduces a large annotated microscopy dataset with over 430,000 cells, benchmarks existing methods, and proposes a new adaptation of the Segment Anything Model for improved automated cell counting.

Contribution

It provides a new large-scale dataset, benchmarks multiple methods, and adapts SAM for microscopy, advancing automated cell counting research.

Findings

The dataset contains 3,023 images with over 430,000 annotated cells.

Benchmark results show varying performance across methods, with density-map adaptation outperforming others.

SAM-Counter achieved a MAE of 22.12, surpassing existing approaches.

Abstract

Accurate cell counting is essential in various biomedical research and clinical applications, including cancer diagnosis, stem cell research, and immunology. Manual counting is labor-intensive and error-prone, motivating automation through deep learning techniques. However, training reliable deep learning models requires large amounts of high-quality annotated data, which is difficult and time-consuming to produce manually. Consequently, existing cell-counting datasets are often limited, frequently containing fewer than $500$ images. In this work, we introduce a large-scale annotated dataset comprising $3{,}023$ images from immunocytochemistry experiments related to cellular differentiation, containing over $430{,}000$ manually annotated cell locations. The dataset presents significant challenges: high cell density, overlapping and morphologically diverse cells, a long-tailed distribution of cell count per image, and variation in staining protocols. We benchmark three categories of existing methods: regression-based, crowd-counting, and cell-counting techniques on a test set with cell counts ranging from $10$ to $2{,}126$ cells per image. We also evaluate how the Segment Anything Model (SAM) can be adapted for microscopy cell counting using only dot-annotated datasets. As a case study, we implement a density-map-based adaptation of SAM (SAM-Counter) and report a mean absolute error (MAE) of $22.12$, which outperforms existing approaches (second-best MAE of $27.46$). Our results underscore the value of the dataset and the benchmarking framework for driving progress in automated cell counting and provide a robust foundation for future research and development.