Patherea: Cell Detection and Classification for the 2020s

TL;DR

Patherea is a comprehensive framework for cell detection and classification that introduces a new challenging dataset, improves evaluation protocols, and achieves state-of-the-art results on existing benchmarks.

Contribution

It presents a unified detection and classification framework, a new large-scale challenging dataset, and improved evaluation protocols for pathology image analysis.

Findings

State-of-the-art performance on public datasets

Identification of performance saturation on existing benchmarks

Introduction of a more challenging dataset for future research

Abstract

We present Patherea, a unified framework for point-based cell detection and classification that enables the development and fair evaluation of state-of-the-art methods. To support this, we introduce a large-scale dataset that replicates the clinical workflow for Ki-67 proliferation index estimation. Our method directly predicts cell locations and classes without relying on intermediate representations. It incorporates a hybrid Hungarian matching strategy for accurate point assignment and supports flexible backbones and training regimes, including recent pathology foundation models. Patherea achieves state-of-the-art performance on public datasets - Lizard, BRCA-M2C, and BCData - while highlighting performance saturation on these benchmarks. In contrast, our newly proposed Patherea dataset presents a significantly more challenging benchmark. Additionally, we identify and correct common errors in current evaluation protocols and provide an updated benchmarking utility for standardized assessment. The Patherea dataset and code are publicly available to facilitate further research and fair comparisons.