Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

An Open Source, Automated Tumor Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

Bai, Yalai ; Cole, Kimberly ; Martinez-morilla, Sandra ; Ahmed, Fahad Shabbir ; Zugazagoitia, Jon ; Staaf, Johan LU orcid ; Bosch-Campos, Ana LU ; Ehinger, Anna LU orcid ; Niméus, Emma LU and Hartman, Johan , et al. (2021) In Clinical Cancer Research 27(20). p.5557-5565
Abstract
Purpose: Although tumor infiltrating lymphocytes (TIL) assessment has been acknowledged to
have both prognostic and predictive importance in triple negative breast cancer (TNBC), it is
subject to inter and intra-observer variability that has prevented widespread adoption. Here we
constructed a machine-learning based breast cancer TIL scoring approach and validated its
prognostic potential in multiple TNBC cohorts.
Experimental Design: Using the QuPath open source software, we built a neural-network
classifier for tumor cells, lymphocytes, fibroblasts and “other” cells on hematoxylin-eosin
(H&E) stained sections. We analyzed the classifier-derived TIL measurements with five unique
constructed TIL... (More)
Purpose: Although tumor infiltrating lymphocytes (TIL) assessment has been acknowledged to
have both prognostic and predictive importance in triple negative breast cancer (TNBC), it is
subject to inter and intra-observer variability that has prevented widespread adoption. Here we
constructed a machine-learning based breast cancer TIL scoring approach and validated its
prognostic potential in multiple TNBC cohorts.
Experimental Design: Using the QuPath open source software, we built a neural-network
classifier for tumor cells, lymphocytes, fibroblasts and “other” cells on hematoxylin-eosin
(H&E) stained sections. We analyzed the classifier-derived TIL measurements with five unique
constructed TIL variables. A retrospective collection of 171 TNBC cases was used as the
discovery set to identify the optimal association of machine-read TIL variables with patient
outcome. For validation we evaluated a retrospective collection of 749 TNBC patients comprised
of four independent validation subsets.
Results: We found that all five machine TIL variables had significant prognostic association
with outcomes (p≤0.01 for all comparisons) but showed cell specific variation in validation sets.
Cox regression analysis demonstrated that all five TIL variables were independently associated
with improved overall survival after adjusting for clinicopathological factors including stage, age
and histological grade (p≤0.003 for all analyses).
Conclusions: Neural net driven cell classifier defined TIL variables were robust and independent
prognostic factors in several independent validation cohorts of TNBC patients. These objective,
open source TIL variables are freely available to download and can now be considered for
testing in a prospective setting to assess clinical utility. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Clinical Cancer Research
volume
27
issue
20
pages
9 pages
publisher
American Association for Cancer Research
external identifiers
  • pmid:34088723
  • scopus:85116526594
ISSN
1078-0432
DOI
10.1158/1078-0432.CCR-21-0325
language
English
LU publication?
yes
id
dad42269-2b99-4532-b57a-dbf2b41c3cd7
date added to LUP
2021-06-04 19:56:31
date last changed
2024-02-20 07:58:08
@article{dad42269-2b99-4532-b57a-dbf2b41c3cd7,
  abstract     = {{Purpose: Although tumor infiltrating lymphocytes (TIL) assessment has been acknowledged to<br>
have both prognostic and predictive importance in triple negative breast cancer (TNBC), it is<br>
subject to inter and intra-observer variability that has prevented widespread adoption. Here we<br>
constructed a machine-learning based breast cancer TIL scoring approach and validated its<br>
prognostic potential in multiple TNBC cohorts.<br>
Experimental Design: Using the QuPath open source software, we built a neural-network<br>
classifier for tumor cells, lymphocytes, fibroblasts and “other” cells on hematoxylin-eosin<br>
(H&amp;E) stained sections. We analyzed the classifier-derived TIL measurements with five unique<br>
constructed TIL variables. A retrospective collection of 171 TNBC cases was used as the<br>
discovery set to identify the optimal association of machine-read TIL variables with patient<br>
outcome. For validation we evaluated a retrospective collection of 749 TNBC patients comprised<br>
of four independent validation subsets.<br>
Results: We found that all five machine TIL variables had significant prognostic association<br>
with outcomes (p≤0.01 for all comparisons) but showed cell specific variation in validation sets.<br>
Cox regression analysis demonstrated that all five TIL variables were independently associated<br>
with improved overall survival after adjusting for clinicopathological factors including stage, age<br>
and histological grade (p≤0.003 for all analyses).<br>
Conclusions: Neural net driven cell classifier defined TIL variables were robust and independent<br>
prognostic factors in several independent validation cohorts of TNBC patients. These objective,<br>
open source TIL variables are freely available to download and can now be considered for<br>
testing in a prospective setting to assess clinical utility.}},
  author       = {{Bai, Yalai and Cole, Kimberly and Martinez-morilla, Sandra and Ahmed, Fahad Shabbir and Zugazagoitia, Jon and Staaf, Johan and Bosch-Campos, Ana and Ehinger, Anna and Niméus, Emma and Hartman, Johan and Acs, Balazs and Rimm, David L}},
  issn         = {{1078-0432}},
  language     = {{eng}},
  month        = {{10}},
  number       = {{20}},
  pages        = {{5557--5565}},
  publisher    = {{American Association for Cancer Research}},
  series       = {{Clinical Cancer Research}},
  title        = {{An Open Source, Automated Tumor Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer}},
  url          = {{http://dx.doi.org/10.1158/1078-0432.CCR-21-0325}},
  doi          = {{10.1158/1078-0432.CCR-21-0325}},
  volume       = {{27}},
  year         = {{2021}},
}