Self-supervised deep learning for highly efficient spatial immunophenotyping
Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved..
BACKGROUND: Efficient biomarker discovery and clinical translation depend on the fast and accurate analytical output from crucial technologies such as multiplex imaging. However, reliable cell classification often requires extensive annotations. Label-efficient strategies are urgently needed to reveal diverse cell distribution and spatial interactions in large-scale multiplex datasets.
METHODS: This study proposed Self-supervised Learning for Antigen Detection (SANDI) for accurate cell phenotyping while mitigating the annotation burden. The model first learns intrinsic pairwise similarities in unlabelled cell images, followed by a classification step to map learnt features to cell labels using a small set of annotated references. We acquired four multiplex immunohistochemistry datasets and one imaging mass cytometry dataset, comprising 2825 to 15,258 single-cell images to train and test the model.
FINDINGS: With 1% annotations (18-114 cells), SANDI achieved weighted F1-scores ranging from 0.82 to 0.98 across the five datasets, which was comparable to the fully supervised classifier trained on 1828-11,459 annotated cells (-0.002 to -0.053 of averaged weighted F1-score, Wilcoxon rank-sum test, P = 0.31). Leveraging the immune checkpoint markers stained in ovarian cancer slides, SANDI-based cell identification reveals spatial expulsion between PD1-expressing T helper cells and T regulatory cells, suggesting an interplay between PD1 expression and T regulatory cell-mediated immunosuppression.
INTERPRETATION: By striking a fine balance between minimal expert guidance and the power of deep learning to learn similarity within abundant data, SANDI presents new opportunities for efficient, large-scale learning for histology multiplex imaging data.
FUNDING: This study was funded by the Royal Marsden/ICR National Institute of Health Research Biomedical Research Centre.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:95 |
|---|---|
| Enthalten in: |
EBioMedicine - 95(2023) vom: 01. Sept., Seite 104769 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zhang, Hanyun [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Cell classification |
|---|
| Anmerkungen: |
Date Completed 18.09.2023 Date Revised 21.02.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.ebiom.2023.104769 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM361706251 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM361706251 | ||
| 003 | DE-627 | ||
| 005 | 20240222091339.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ebiom.2023.104769 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1301.xml |
| 035 | |a (DE-627)NLM361706251 | ||
| 035 | |a (NLM)37672979 | ||
| 035 | |a (PII)S2352-3964(23)00335-3 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zhang, Hanyun |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Self-supervised deep learning for highly efficient spatial immunophenotyping |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 18.09.2023 | ||
| 500 | |a Date Revised 21.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved. | ||
| 520 | |a BACKGROUND: Efficient biomarker discovery and clinical translation depend on the fast and accurate analytical output from crucial technologies such as multiplex imaging. However, reliable cell classification often requires extensive annotations. Label-efficient strategies are urgently needed to reveal diverse cell distribution and spatial interactions in large-scale multiplex datasets | ||
| 520 | |a METHODS: This study proposed Self-supervised Learning for Antigen Detection (SANDI) for accurate cell phenotyping while mitigating the annotation burden. The model first learns intrinsic pairwise similarities in unlabelled cell images, followed by a classification step to map learnt features to cell labels using a small set of annotated references. We acquired four multiplex immunohistochemistry datasets and one imaging mass cytometry dataset, comprising 2825 to 15,258 single-cell images to train and test the model | ||
| 520 | |a FINDINGS: With 1% annotations (18-114 cells), SANDI achieved weighted F1-scores ranging from 0.82 to 0.98 across the five datasets, which was comparable to the fully supervised classifier trained on 1828-11,459 annotated cells (-0.002 to -0.053 of averaged weighted F1-score, Wilcoxon rank-sum test, P = 0.31). Leveraging the immune checkpoint markers stained in ovarian cancer slides, SANDI-based cell identification reveals spatial expulsion between PD1-expressing T helper cells and T regulatory cells, suggesting an interplay between PD1 expression and T regulatory cell-mediated immunosuppression | ||
| 520 | |a INTERPRETATION: By striking a fine balance between minimal expert guidance and the power of deep learning to learn similarity within abundant data, SANDI presents new opportunities for efficient, large-scale learning for histology multiplex imaging data | ||
| 520 | |a FUNDING: This study was funded by the Royal Marsden/ICR National Institute of Health Research Biomedical Research Centre | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Cell classification | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Imaging mass cytometry | |
| 650 | 4 | |a Multiplex imaging | |
| 650 | 4 | |a Multiplex immunohistochemistry | |
| 650 | 4 | |a Self-supervised learning | |
| 700 | 1 | |a AbdulJabbar, Khalid |e verfasserin |4 aut | |
| 700 | 1 | |a Grunewald, Tami |e verfasserin |4 aut | |
| 700 | 1 | |a Akarca, Ayse U |e verfasserin |4 aut | |
| 700 | 1 | |a Hagos, Yeman |e verfasserin |4 aut | |
| 700 | 1 | |a Sobhani, Faranak |e verfasserin |4 aut | |
| 700 | 1 | |a Lecat, Catherine S Y |e verfasserin |4 aut | |
| 700 | 1 | |a Patel, Dominic |e verfasserin |4 aut | |
| 700 | 1 | |a Lee, Lydia |e verfasserin |4 aut | |
| 700 | 1 | |a Rodriguez-Justo, Manuel |e verfasserin |4 aut | |
| 700 | 1 | |a Yong, Kwee |e verfasserin |4 aut | |
| 700 | 1 | |a Ledermann, Jonathan A |e verfasserin |4 aut | |
| 700 | 1 | |a Le Quesne, John |e verfasserin |4 aut | |
| 700 | 1 | |a Hwang, E Shelley |e verfasserin |4 aut | |
| 700 | 1 | |a Marafioti, Teresa |e verfasserin |4 aut | |
| 700 | 1 | |a Yuan, Yinyin |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t EBioMedicine |d 2014 |g 95(2023) vom: 01. Sept., Seite 104769 |w (DE-627)NLM244581355 |x 2352-3964 |7 nnns |
| 773 | 1 | 8 | |g volume:95 |g year:2023 |g day:01 |g month:09 |g pages:104769 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.ebiom.2023.104769 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 95 |j 2023 |b 01 |c 09 |h 104769 | ||