Patherea : cell detection and classification for the 2020s

Štepec, Dejan (author), Jerše, Maja (author), Đokić, Snežana (author), Jeruc, Jera (author), Zidar, Nina (author), Skočaj, Danijel (author)

We present Patherea, a unified framework for point-based cell detection and classification in histopathology. Our method directly predicts cell locations and classes without intermediate representations and incorporates a hybrid Hungarian matching strategy for more accurate point assignment. Patherea supports flexible backbones and training regimes and leverages pathology foundation models for point-based detection, a capability not feasible with most existing point-based methods. To support method development and benchmarking, we introduce the largest fully manually labeled dataset for Ki-67 IHC, annotated by expert pathologists on full-resolution whole-slide images following standard clinical protocols. We evaluate our approach on existing public point-based datasets–Lizard, BRCA-M2C, and BCData–demonstrating superior F1 scores compared to recent point-based detection methods, while revealing performance saturation on these benchmarks. The Patherea dataset provides a complementary benchmark, capturing clinically relevant low-abundance cell classes where current approaches underperform. Finally, we identify and correct common errors in existing evaluation protocols and provide a benchmarking utility for reproducible assessment. The Patherea dataset and code are publicly released to support future research and fair comparisons.

• Language: English
• Keywords: classification, detection, Ki-67, vision transformer, pathology
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science ; MF - Faculty of Medicine
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: 17 str.
• Numbering: Vol. 108, art. 103868
• PID: 20.500.12556/RUL-181427
• UDC: 616
• ISSN on article: 1361-8423
• DOI: 10.1016/j.media.2025.103868
• COBISS.SI-ID: 265987331
• Publication date in RUL: 07.04.2026

Record is a part of a journal

• Title: Medical image analysis
• Publisher: Elsevier
• ISSN: 1361-8423
• COBISS.SI-ID: 23054085

Licences

• License: CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
• Link: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Description: The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.

Secondary language

• Language: Slovenian
• Keywords: klasifikacija, zaznavanje, vidni transformator, patologija

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P3-0054
• Name: Patologija in molekularna genetika

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0214
• Name: Računalniški vid