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

2025-11-24

AI Summary

To address the challenge of automated cell counting in fluorescence microscopy images—characterized by high cell density, morphological diversity, and heterogeneous staining—this work introduces the first large-scale cell counting dataset (3,023 images with >430,000 point annotations) and proposes SAM-Counter, the first point-supervised cell counting method tailored for the Segment Anything Model (SAM). SAM-Counter synergistically integrates density map regression with SAM’s zero-shot transfer capability to significantly improve localization accuracy for small, ambiguous targets. Evaluated on a rigorous test set spanning 10–2,126 cells per image, it achieves a mean absolute error (MAE) of 22.12, outperforming state-of-the-art methods and demonstrating superior robustness. Additionally, this work establishes a standardized benchmark covering three paradigms—regression-based, crowd-counting-inspired, and cell-specific counting—thereby providing both a high-quality data foundation and a scalable algorithmic framework for automated cell analysis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• Manual cell counting is labor-intensive and error-prone for biomedical applications
• Existing datasets are limited with insufficient annotated microscopy images
• High cell density and morphological diversity challenge automated counting methods

Innovation

• Introduces large-scale annotated dataset with 3023 images
• Benchmarks regression and crowd-counting methods on test set
• Adapts Segment Anything Model for microscopy cell counting