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

Research output: Contribution to journalArticle

Standard

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; Bosch-Campos, Ana; Ehinger, Anna; Niméus, Emma; Hartman, Johan; Acs, Balazs; Rimm, David L.

In: Clinical Cancer Research, 04.06.2021, p. clincanres.0325.2021.

Research output: Contribution to journalArticle

Harvard

APA

Bai, Y., Cole, K., Martinez-morilla, S., Ahmed, F. S., Zugazagoitia, J., Staaf, J., Bosch-Campos, A., Ehinger, A., Niméus, E., Hartman, J., Acs, B., & Rimm, D. L. (2021). An Open Source, Automated Tumor Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer. Clinical Cancer Research, clincanres.0325.2021. [clincanres.0325.2021]. https://doi.org/10.1158/1078-0432.CCR-21-0325

CBE

MLA

Vancouver

Author

Bai, Yalai ; Cole, Kimberly ; Martinez-morilla, Sandra ; Ahmed, Fahad Shabbir ; Zugazagoitia, Jon ; Staaf, Johan ; Bosch-Campos, Ana ; Ehinger, Anna ; Niméus, Emma ; Hartman, Johan ; Acs, Balazs ; Rimm, David L. / An Open Source, Automated Tumor Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer. In: Clinical Cancer Research. 2021 ; pp. clincanres.0325.2021.

RIS

TY - JOUR

T1 - An Open Source, Automated Tumor Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

AU - Bai, Yalai

AU - Cole, Kimberly

AU - Martinez-morilla, Sandra

AU - Ahmed, Fahad Shabbir

AU - Zugazagoitia, Jon

AU - Staaf, Johan

AU - Bosch-Campos, Ana

AU - Ehinger, Anna

AU - Niméus, Emma

AU - Hartman, Johan

AU - Acs, Balazs

AU - Rimm, David L

PY - 2021/6/4

Y1 - 2021/6/4

N2 - 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.

AB - 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.

U2 - 10.1158/1078-0432.CCR-21-0325

DO - 10.1158/1078-0432.CCR-21-0325

M3 - Article

C2 - 34088723

SP - clincanres.0325.2021

JO - Clinical Cancer Research

JF - Clinical Cancer Research

SN - 1078-0432

M1 - clincanres.0325.2021

ER -