Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster session 02

309P - Machine learning-based characterization of tumor-immune microenvironment at a spatial and multiplexed resolution in early breast cancer: A sub-study of the EORTC 10994/BIG 1-00 randomized phase III trial with long-term follow-up

Date

21 Oct 2023

Session

Poster session 02

Topics

Translational Research

Tumour Site

Breast Cancer

Presenters

Ioannis Zerdes

Citation

Annals of Oncology (2023) 34 (suppl_2): S278-S324. 10.1016/S0923-7534(23)01258-9

Authors

I. Zerdes1, A. Matikas1, A. Mezheyeuski2, B. Acs3, H. Johansson4, G. Manikis5, C. Boyaci3, C.E. Boman1, C. Poncet6, M. Ignatiadis7, Y. Bai8, D. Rimm8, G. MacGrogan9, D.A. Cameron10, J. Bergh1, H. Bonnefoi11, T. Foukakis1

Author affiliations

  • 1 Department Of Oncology-pathology & Breast Center, Karolinska Institutet & Karolinska University Hospital, Comprehensive Cancer Center, 171 64 - Stockholm/SE
  • 2 Immunology, Genetics And Pathology, Uppsala University - Rudbecklaboratoriet, 752 37 - Uppsala/SE
  • 3 Department Of Oncology-pathology & Department Of Clinical Pathology And Cancer Diagnostics, Karolinska Institutet & Karolinska University Hospital, Comprehensive Cancer Center, 141 83 - Stockholm/SE
  • 4 Department Of Oncology-pathology, Karolinska Institutet, 171 64 - Stockholm/SE
  • 5 Computational Biomedicine Laboratory (cbml), Foundation for Research and Technology-Hellas (FORTH), Heraklion/GR
  • 6 Statistical Department, EORTC AISBL/IVZW - European Organisation for Research and Treatment of Cancer, 1200 - Brussels/BE
  • 7 Department Of Medical Oncology, Institute Jules Bordet, 1070 - Brussels/BE
  • 8 Department Of Pathology, Yale University School of Medicine - Yale Cancer Center, 06520 - New Haven/US
  • 9 Department Of Biopathology, Institute Bergonié - Centre Régional de Lutte Contre le Cancer (CLCC), 33000 - Bordeaux/FR
  • 10 Edinburgh Cancer Centre, Western General Hospital, Crewe Road South, Institute of Genetics and Cancer, University of Edinburgh, EH4 2XU - Edinburgh/GB
  • 11 Medical Oncology Department, Institute Bergonié - Centre Régional de Lutte Contre le Cancer (CLCC), 33000 - Bordeaux/FR

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 309P

Background

Data support the role of immune infiltrate in breast cancer (BC) prognosis and therapy prediction. The aim of this study was to characterize the immune landscape in early BC at a multiplex and spatial resolution using machine learning (ML)-based algorithms and investigate its potential prognostic value.

Methods

Tissue microarrays (TMA) were constructed from pretreatment samples from patients enrolled in the EORTC 10994/BIG 1-00 neoadjuvant randomized phase III trial (taxane/anthracycline vs FEC). An automated algorithm for digital TIL (dTIL) quantification was applied on H&E stained TMA. Multiplex fluorescent immunohistochemistry (mfIHC) was performed for an immune antibody panel and cell phenotyping/localization was applied with a ML-based software. TP53 mutational status was available for a subset of patients. Logistic and Cox regression models investigated the association of immune-related metrics with pathological complete response (pCR) and progression-free survival (PFS), respectively.

Results

Median follow-up was 11.4 years. 587 patients had dTIL and 478 had mfIHC data. Among the dTIL variables, easTIL [sum of TIL area (mm2)/stroma area (mm2)] were higher in the triple-negative subtype and an independent predictor of pCR (ORadj= 1.59, 95% CI 1.00 – 2.54, p=0.05) in the whole cohort. No significant association with PFS was noted. However, a significant interaction was observed between esTIL (TIL/stromal cells) and TP53 mutational status (p= 0.028); higher esTIL abundance was prognostic for worse PFS only in patients with TP53 wild-type tumors. CD8+ T-cells were the most abundant cell subset in both tumor and stroma compartments. Expression of total CD4+ (ORadj= 1.79, 95% CI 1.07 – 2.97, p=0.026) and intra-tumoral CD8+ T-cells (ORadj= 1.83, 95% CI 1.05 – 3.20, p=0.033) was independently associated with improved pCR.

Conclusions

Our data indicate that ML-based models could be used for studying the immune infiltrate in BC. Abundance of dTIL and spatial distribution of immune markers contain prognostic information, which might depend on TP53 mutational status. Further validation is warranted.

Clinical trial identification

NCT00017095.

Editorial acknowledgement

Legal entity responsible for the study

European Organisation for Research and Treatment of Cancer (EORTC).

Funding

The clinical trial was funded by: the US National Cancer Institute (grants 2U10 CA11488-31 through 5U10 CA011488-40, Bethesda, MD, USA), French Ligue Nationale Contre le Cancer (donation through the EORTC Charitable Trust), European Union (fp6 Active p53 grant), Pharmacia (educational grant to EORTC Headquarters), and Sanofi-Aventis (educational grants to EORTC Headquarters and Clinical Trial Office at Karolinska University, and provided docetaxel for this trial). The biomarker study presented here was funded by: Region Stockholm, Percy Falks Foundation, Iris, Stig and Gerry Castenbäcks Foundation, Swedish Cancer Society and the Research Funds at Radiumhemmet.

Disclosure

A. Matikas: Financial Interests, Institutional, Coordinating PI, International co-PI of academic trial ARIADNE (EU CT: 2022-501504-95-00): AstraZeneca, Novartis, Veracyte; Non-Financial Interests, Advisory Role: Veracyte, Roche. M. Ignatiadis: Financial Interests, Personal, Invited Speaker: Novartis; Financial Interests, Personal, Other, Independent Monitoring Committee: Seattle Genetics; Financial Interests, Institutional, Coordinating PI: Pfizer, Roche, Natera, Inivata, Rejuveron; Non-Financial Interests, Officer: EORTC; Financial Interests, Personal, Other, Travel Grants: Roche, Gilead. D. Rimm: Financial Interests, Personal, Advisory Board: Amgen, AstraZeneca, Cell Signaling Technology , Cepheid, Danaher, GSK, Konica/Minolta, Lilly, Merck, Monopteros, Nanostring, PAIGE.AI, Regeneron, Roche, Ventana; Financial Interests, Personal, Advisory Role: Fluidigm, Immunogen, NextCure, Odonate, Sanofi, Verily; Financial Interests, Institutional, Other: Amgen, Cepheid, Navigate BioPharma, NextCure, Konica/Minolta, Akoya; Financial Interests, Personal, Royalties: Rarecyte. D.A. Cameron: Financial Interests, Institutional, Advisory Board: Roche, Pfizer, AstraZeneca, Daiichi Sankyo, SeaGen, Synthon, Zymeworks; Financial Interests, Institutional, Other, Have done advisory boards, spoken at a webinar and involved in a manuscript with Lilly - all recompense to my institution: Lilly; Financial Interests, Institutional, Other, Have done advisory boards and been involved in a health economic analysis and publication. All recompense to my institution: Novartis; Financial Interests, Institutional, Coordinating PI, funding and drug for UK participation in a French led Novartis funded study. Institutional funding received for consultancy work: Novartis; Non-Financial Interests, Principal Investigator, one of three PIs for the Ameera-6 trial - which has now closed early as the company have stopped all development of the drug: Sanofi; Other, Chair of the board of this small Scottish charity for secondary breast cancer: Make Seconds Count; Other, Chair of the Board of B.I.G. - a group of international breast cancer research groups: Breast International Group; Other, Chair of the European Breast Cancer Council which organises the bi-annual EBCC meetings: EBCC. J. Bergh: Financial Interests, Institutional, Advisory Board: Amgen, AstraZeneca, Bayer, Merck, Pfizer, Roche, Sanofi-Aventis; Financial Interests, Personal, Other, Co-author on a chapter in UpToDate on prognostic and predictive factors in early, non-metastatic breast cancer. Honoraria to Asklepios Medicine HB: UpToDate; Financial Interests, Personal, Stocks/Shares, consultant for this diagnostic company in early development: Stratipath . H. Bonnefoi: Financial Interests, Personal, Advisory Board: AstraZeneca/ Daiichi Sankyo; Financial Interests, Institutional, Coordinating PI, UCBG3-06 prospective study: Bayer. T. Foukakis: Financial Interests, Institutional, Invited Speaker: Roche, AstraZeneca, Gilead Sciences; Financial Interests, Personal, Advisory Board: Novartis, Veracyte, Exact Sciences, Affibody; Financial Interests, Personal, Invited Speaker: Pfizer; Financial Interests, Personal, Royalties, Authorship of two chapters in UpToDate: Wolters Kluwer; Financial Interests, Institutional, Coordinating PI, Clinical trial support (research grant and study drug): Pfizer, AstraZeneca; Financial Interests, Institutional, Coordinating PI, Clinical trial support (research grant and study drug): Novartis. All other authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.