Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: A report of The International Immuno-Oncology Biomarker Working Group Review

  

Authors:	Thagaard, J.; Broeckx, G.; Page, D. B.; Jahangir, C. A.; Verbandt, S.; Kos, Z.; Gupta, R.; Khiroya, R.; Abduljabbar, K.; Acosta Haab, G.; Acs, B.; Akturk, G.; Almeida, J. S.; Alvarado-Cabrero, I.; Amgad, M.; Azmoudeh-Ardalan, F.; Badve, S.; Baharun, N. B.; Balslev, E.; Bellolio, E. R.; Bheemaraju, V.; Blenman, K. R. M.; Botinelly Mendonça Fujimoto, L.; Bouchmaa, N.; Burgues, O.; Chardas, A.; Chon U Cheang, M.; Ciompi, F.; Cooper, L. A. D.; Coosemans, A.; Corredor, G.; Dahl, A. B.; Dantas Portela, F. L.; Deman, F.; Demaria, S.; Doré Hansen, J.; Dudgeon, S. N.; Ebstrup, T.; Elghazawy, M.; Fernandez-Martín, C.; Fox, S. B.; Gallagher, W. M.; Giltnane, J. M.; Gnjatic, S.; Gonzalez-Ericsson, P. I.; Grigoriadis, A.; Halama, N.; Hanna, M. G.; Harbhajanka, A.; Hart, S. N.; Hartman, J.; Hauberg, S.; Hewitt, S.; Hida, A. I.; Horlings, H. M.; Husain, Z.; Hytopoulos, E.; Irshad, S.; Janssen, E. A. M.; Kahila, M.; Kataoka, T. R.; Kawaguchi, K.; Kharidehal, D.; Khramtsov, A. I.; Kiraz, U.; Kirtani, P.; Kodach, L. L.; Korski, K.; Kovács, A.; Laenkholm, A. V.; Lang-Schwarz, C.; Larsimont, D.; Lennerz, J. K.; Lerousseau, M.; Li, X.; Ly, A.; Madabhushi, A.; Maley, S. K.; Manur Narasimhamurthy, V.; Marks, D. K.; McDonald, E. S.; Mehrotra, R.; Michiels, S.; Minhas, F. U. A. A.; Mittal, S.; Moore, D. A.; Mushtaq, S.; Nighat, H.; Papathomas, T.; Penault-Llorca, F.; Perera, R. D.; Pinard, C. J.; Pinto-Cardenas, J. C.; Pruneri, G.; Pusztai, L.; Rahman, A.; Rajpoot, N. M.; Rapoport, B. L.; Rau, T. T.; Reis-Filho, J. S.; Ribeiro, J. M.; Rimm, D.; Roslind, A.; Vincent-Salomon, A.; Salto-Tellez, M.; Saltz, J.; Sayed, S.; Scott, E.; Siziopikou, K. P.; Sotiriou, C.; Stenzinger, A.; Sughayer, M. A.; Sur, D.; Fineberg, S.; Symmans, F.; Tanaka, S.; Taxter, T.; Tejpar, S.; Teuwen, J.; Thompson, E. A.; Tramm, T.; Tran, W. T.; van der Laak, J.; van Diest, P. J.; Verghese, G. E.; Viale, G.; Vieth, M.; Wahab, N.; Walter, T.; Waumans, Y.; Wen, H. Y.; Yang, W.; Yuan, Y.; Zin, R. M.; Adams, S.; Bartlett, J.; Loibl, S.; Denkert, C.; Savas, P.; Loi, S.; Salgado, R.; Specht Stovgaard, E.
Review Title:	Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: A report of The International Immuno-Oncology Biomarker Working Group
Abstract:	The clinical significance of the tumor-immune interaction in breast cancer is now established, and tumor-infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple-negative (estrogen receptor, progesterone receptor, and HER2-negative) breast cancer and HER2-positive breast cancer. How computational assessments of TILs might complement manual TIL assessment in trial and daily practices is currently debated. Recent efforts to use machine learning (ML) to automatically evaluate TILs have shown promising results. We review state-of-the-art approaches and identify pitfalls and challenges of automated TIL evaluation by studying the root cause of ML discordances in comparison to manual TIL quantification. We categorize our findings into four main topics: (1) technical slide issues, (2) ML and image analysis aspects, (3) data challenges, and (4) validation issues. The main reason for discordant assessments is the inclusion of false-positive areas or cells identified by performance on certain tissue patterns or design choices in the computational implementation. To aid the adoption of ML for TIL assessment, we provide an in-depth discussion of ML and image analysis, including validation issues that need to be considered before reliable computational reporting of TILs can be incorporated into the trial and routine clinical management of patients with triple-negative breast cancer. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Keywords:	controlled study; histopathology; review; tumor associated leukocyte; lymphocytes, tumor-infiltrating; biomarkers; biological marker; animal; animals; image analysis; practice guideline; immune response; algorithm; tissue level; cell level; guidelines; prognostic biomarker; computer vision; tumor-infiltrating lymphocytes; digital pathology; mammary neoplasms, animal; triple negative breast cancer; triple-negative breast cancer; pitfalls; machine learning; humans; human; deep learning; triple negative breast neoplasms; experimental mammary neoplasm
Journal Title:	Journal of Pathology
Volume:	260
Issue:	5
ISSN:	0022-3417
Publisher:	Wiley Blackwell
Date Published:	2023-01-01
Start Page:	498
End Page:	513
Language:	English
DOI:	10.1002/path.6155
PUBMED:	37608772
PROVIDER:	scopus
DOI/URL:	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85167995389&doi=10.1002%2fpath.6155&partnerID=40&md5=07ad96cc3a20eea19b7cf96916b1c85d
Notes:	Review -- Source: Scopus

https://synapse.mskcc.org/synapse/works/has_related_data_chk/210037