Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 17, 2025

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

Self-supervised deep learning for highly efficient spatial immunophenotyping.

Hanyun Zhang¹, Khalid AbdulJabbar¹, Tami Grunewald²

¹Centre for Evolution and Cancer, The Institute of Cancer Research, London, UK; Division of Molecular Pathology, The Institute of Cancer Research, London, UK.

|September 6, 2023

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Stabilizing ZnIn<sub>2</sub>S<sub>4</sub> via Phosphorus Doping for Efficient Photocatalytic Trifluoromethylation of Styrene.

Langmuir : the ACS journal of surfaces and colloids·2026

Same author

Oncologic outcomes after poly-4-hydroxybutyrate scaffold in post-mastectomy breast reconstruction: a retrospective, multi-center cohort study.

World journal of surgical oncology·2026

Same author

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026

Same author

Stromal Cell Subsets Modulate T-cell Infiltration in Early Breast Cancer.

Cancer research communications·2026

Same author

Age-related differences in psychological distress and persistent postsurgical pain after surgery for management of non-invasive breast lesions.

Breast cancer research and treatment·2026

Same author

Patient Out-of-Pocket Costs and Healthcare Utilization Related to Mastectomy vs Breast Conservation: A Claims-Based Study.

Journal of surgical oncology·2026

Self-supervised Learning for Antigen Detection (SANDI) enables accurate cell phenotyping in multiplex imaging with minimal annotations. This deep learning approach accelerates biomarker discovery and clinical translation for histology data.

Area of Science:

Computational pathology
Biomedical imaging analysis
Machine learning in healthcare

Background:

Multiplex imaging technologies are crucial for biomarker discovery and clinical translation.
Accurate cell classification in large-scale multiplex datasets is hindered by extensive annotation requirements.
Label-efficient strategies are needed to analyze cell distribution and spatial interactions.

Purpose of the Study:

To introduce Self-supervised Learning for Antigen Detection (SANDI), a novel method for accurate cell phenotyping in multiplex imaging.
To reduce the annotation burden in analyzing complex histology datasets.
To enable efficient, large-scale learning for multiplex imaging data.

Main Methods:

SANDI utilizes self-supervised learning to identify intrinsic similarities in unlabeled cell images.

Keywords:

Cell classification Deep learning Imaging mass cytometry Multiplex imaging Multiplex immunohistochemistry Self-supervised learning

More Related Videos

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

Related Experiment Videos

Last Updated: Jul 17, 2025

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

A subsequent classification step maps learned features to cell labels using a small set of annotated references.

The model was trained and tested on five multiplex datasets including multiplex immunohistochemistry and imaging mass cytometry data.

Main Results:

SANDI achieved high weighted F1-scores (0.82–0.98) with only 1% of cells annotated, comparable to fully supervised methods.
The performance was consistent across four multiplex immunohistochemistry and one imaging mass cytometry dataset.
Analysis of ovarian cancer slides revealed spatial interactions between PD1-expressing T helper cells and T regulatory cells, suggesting immune interplay.

Conclusions:

SANDI offers a powerful solution for histology multiplex imaging by balancing minimal expert guidance with deep learning capabilities.
The method facilitates efficient, large-scale analysis of histology data, accelerating biomarker discovery.
SANDI opens new avenues for leveraging deep learning in the analysis of complex biological imaging datasets.