Work

Immunocto: A massive immune cell database auto-generated for histopathology

Year: 2025

Type: article

Abstract: H&E image at 40 × magnification, along with a binary mask of the nucleus and a label. The database, which is made publicly available, can be used to train models to study the TIME on routine H&E slides. We show that deep learning models trained on Immunocto result in state-of-the-art performance for lymphocyte detection. The approach demonstrates the benefits of using matched H&E and IF data to generate robust databases for computational pathology applications.

Source: Medical Image Analysis

DOI: 10.1016/j.media.2025.103905

Authors: Mikaël Simard, Zhuoyan Shen, Konstantin Bräutigam, Rasha Abu-Eid, Maria A. Hawkins, Charles-Antoine Collins Fekete

Institutions: University College London, Institute of Cancer Research, University of Birmingham, University College London Hospitals NHS Foundation Trust

Language: English

Topic: AI in cancer detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,170

Funders: UK Research and Innovation, Cancer Research UK, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Swiss Re Foundation