Sistema de Salut de Catalunya
Institut Català de la Salut
[Zerdes I] Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden. Theme Cancer, Karolinska Comprehensive Cancer Center and University Hospital, Stockholm, Sweden. [Matikas A] Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden. Breast Center, Theme Cancer, Karolinska Comprehensive Cancer Center and University Hospital, Stockholm, Sweden. [Mezheyeuski A] Department of Immunology, Genetics, and Pathology, Uppsala University, Uppsala, Sweden. 5 Molecular Oncology Group, Vall d’Hebron Institute of Oncology (VHIO), Barcelona, Spain. [Manikis G] Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden. Computational BioMedicine Laboratory (CBML), Foundation for Research and Technology-Hellas (FORTH), Heraklion, Greece. [Acs B] Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden. Department of Clinical Pathology and Cancer Diagnostics, Karolinska University Hospital, Stockholm, Sweden. [Johansson H] Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden
Vall d'Hebron Barcelona Hospital Campus
2025-04-22T07:48:36Z
2025-04-22T07:48:36Z
2025-03-07
Machine learning; Tumor-immune microenvironment; Breast cancer
Aprendizaje automático; Microambiente inmunitario tumoral; Cáncer de mama
Aprenentatge automàtic; Microambient immunitari tumoral; Càncer de mama
Breast cancer (BC) represents a heterogeneous ecosystem and elucidation of tumor microenvironment components remains essential. Our study aimed to depict the composition and prognostic correlates of immune infiltrate in early BC, at a multiplex and spatial resolution. Pretreatment tumor biopsies from patients enrolled in the EORTC 10994/BIG 1-00 randomized phase III neoadjuvant trial (NCT00017095) were used; the CNN11 classifier for H&E-based digital TILs (dTILs) quantification and multiplex immunofluorescence were applied, coupled with machine learning (ML)-based spatial features. dTILs were higher in the triple-negative (TN) subtype, and associated with pathological complete response (pCR) in the whole cohort. Total CD4+ and intra-tumoral CD8+ T-cells expression was associated with pCR. Higher immune-tumor cell colocalization was observed in TN tumors of patients achieving pCR. Immune cell subsets were enriched in TP53-mutated tumors. Our results indicate the feasibility of ML-based algorithms for immune infiltrate characterization and the prognostic implications of its abundance and tumor-host interactions.
Open access funding provided by Karolinska Institute.
Article
Published version
English
Mama - Càncer - Aspectes immunològics; Mama - Càncer - Tractament; Limfòcits; Cèl·lules canceroses; Aprenentatge automàtic; DISEASES::Neoplasms::Neoplasms by Site::Breast Neoplasms; Other subheadings::Other subheadings::Other subheadings::/immunology; ANATOMY::Cells::Blood Cells::Leukocytes::Leukocytes, Mononuclear::Lymphocytes::Lymphocytes, Tumor-Infiltrating; PHENOMENA AND PROCESSES::Mathematical Concepts::Algorithms::Artificial Intelligence::Machine Learning; ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT::Therapeutics::Combined Modality Therapy::Neoadjuvant Therapy; ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT::Diagnosis::Prognosis; ENFERMEDADES::neoplasias::neoplasias por localización::neoplasias de la mama; Otros calificadores::Otros calificadores::Otros calificadores::/inmunología; ANATOMÍA::células::células sanguíneas::leucocitos::leucocitos mononucleares::linfocitos::linfocitos infiltrantes de tumor; FENÓMENOS Y PROCESOS::conceptos matemáticos::algoritmos::inteligencia artificial::aprendizaje automático; TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS::terapéutica::tratamiento combinado::tratamiento neoadyuvante; TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS::diagnóstico::pronóstico
Nature Portfolio
npj Breast Cancer;11
https://doi.org/10.1038/s41523-025-00730-1
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
