Scoring Tumor-Infiltrating Lymphocytes in breast DCIS: A guideline-driven artificial intelligence approach

Matteo Pozzi, Natalie Klubickova, Michela Campora, Frederique Meeuwsen, Joey Spronck, Carlijn Lems, Michelle Stegeman, Leslie Tessier, Mattia Barbareschi, Jeroen van der Laak, Giuseppe Jurman, Francesco Ciompi
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 254:214-225, 2024.

Abstract

This study focuses on the assessment of Tumor-Infiltrating Lymphocytes (TILs) in Breast ductal carcinoma in situ (DCIS) by integrating artificial intelligence with international guidelines. DCIS is a non-invasive cancer with intrinsic potential to evolve to invasive breast cancer (IBC), making it critical to understand factors influencing this progression. TILs are a prognostic biomarker in IBC, but their role in DCIS remains under-explored. This work proposes an automated pipeline for computing TILs scores using deep learning for DCIS segmentation and TILs detection, following the guidelines of the International Immuno-Oncology Biomarker Working Group. We report the inter-observer variability at TILs scoring among Pathologists and show that the AI-based TILs scores have good concordance with human assessments. Future research will aim to reduce false positives in DCIS segmentation and detection, support the reference standard with immunohistochemical staining, and expand the dataset to enhance the robustness of the TILs detection algorithm. Ultimately, this method aims to aid Pathologists in assessing the risk associated with DCIS lesions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v254-pozzi24a, title = {Scoring Tumor-Infiltrating Lymphocytes in breast DCIS: A guideline-driven artificial intelligence approach}, author = {Pozzi, Matteo and Klubickova, Natalie and Campora, Michela and Meeuwsen, Frederique and Spronck, Joey and Lems, Carlijn and Stegeman, Michelle and Tessier, Leslie and Barbareschi, Mattia and Laak, Jeroen van der and Jurman, Giuseppe and Ciompi, Francesco}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {214--225}, year = {2024}, editor = {Ciompi, Francesco and Khalili, Nadieh and Studer, Linda and Poceviciute, Milda and Khan, Amjad and Veta, Mitko and Jiao, Yiping and Haj-Hosseini, Neda and Chen, Hao and Raza, Shan and Minhas, FayyazZlobec, Inti and Burlutskiy, Nikolay and Vilaplana, Veronica and Brattoli, Biagio and Muller, Henning and Atzori, Manfredo and Raza, Shan and Minhas, Fayyaz}, volume = {254}, series = {Proceedings of Machine Learning Research}, month = {06 Oct}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v254/main/assets/pozzi24a/pozzi24a.pdf}, url = {https://proceedings.mlr.press/v254/pozzi24a.html}, abstract = {This study focuses on the assessment of Tumor-Infiltrating Lymphocytes (TILs) in Breast ductal carcinoma in situ (DCIS) by integrating artificial intelligence with international guidelines. DCIS is a non-invasive cancer with intrinsic potential to evolve to invasive breast cancer (IBC), making it critical to understand factors influencing this progression. TILs are a prognostic biomarker in IBC, but their role in DCIS remains under-explored. This work proposes an automated pipeline for computing TILs scores using deep learning for DCIS segmentation and TILs detection, following the guidelines of the International Immuno-Oncology Biomarker Working Group. We report the inter-observer variability at TILs scoring among Pathologists and show that the AI-based TILs scores have good concordance with human assessments. Future research will aim to reduce false positives in DCIS segmentation and detection, support the reference standard with immunohistochemical staining, and expand the dataset to enhance the robustness of the TILs detection algorithm. Ultimately, this method aims to aid Pathologists in assessing the risk associated with DCIS lesions.} }
Endnote
%0 Conference Paper %T Scoring Tumor-Infiltrating Lymphocytes in breast DCIS: A guideline-driven artificial intelligence approach %A Matteo Pozzi %A Natalie Klubickova %A Michela Campora %A Frederique Meeuwsen %A Joey Spronck %A Carlijn Lems %A Michelle Stegeman %A Leslie Tessier %A Mattia Barbareschi %A Jeroen van der Laak %A Giuseppe Jurman %A Francesco Ciompi %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2024 %E Francesco Ciompi %E Nadieh Khalili %E Linda Studer %E Milda Poceviciute %E Amjad Khan %E Mitko Veta %E Yiping Jiao %E Neda Haj-Hosseini %E Hao Chen %E Shan Raza %E Fayyaz MinhasInti Zlobec %E Nikolay Burlutskiy %E Veronica Vilaplana %E Biagio Brattoli %E Henning Muller %E Manfredo Atzori %E Shan Raza %E Fayyaz Minhas %F pmlr-v254-pozzi24a %I PMLR %P 214--225 %U https://proceedings.mlr.press/v254/pozzi24a.html %V 254 %X This study focuses on the assessment of Tumor-Infiltrating Lymphocytes (TILs) in Breast ductal carcinoma in situ (DCIS) by integrating artificial intelligence with international guidelines. DCIS is a non-invasive cancer with intrinsic potential to evolve to invasive breast cancer (IBC), making it critical to understand factors influencing this progression. TILs are a prognostic biomarker in IBC, but their role in DCIS remains under-explored. This work proposes an automated pipeline for computing TILs scores using deep learning for DCIS segmentation and TILs detection, following the guidelines of the International Immuno-Oncology Biomarker Working Group. We report the inter-observer variability at TILs scoring among Pathologists and show that the AI-based TILs scores have good concordance with human assessments. Future research will aim to reduce false positives in DCIS segmentation and detection, support the reference standard with immunohistochemical staining, and expand the dataset to enhance the robustness of the TILs detection algorithm. Ultimately, this method aims to aid Pathologists in assessing the risk associated with DCIS lesions.
APA
Pozzi, M., Klubickova, N., Campora, M., Meeuwsen, F., Spronck, J., Lems, C., Stegeman, M., Tessier, L., Barbareschi, M., Laak, J.v.d., Jurman, G. & Ciompi, F.. (2024). Scoring Tumor-Infiltrating Lymphocytes in breast DCIS: A guideline-driven artificial intelligence approach. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 254:214-225 Available from https://proceedings.mlr.press/v254/pozzi24a.html.

Related Material